From f91c8faed1216d49a62b121089a33fd2a8950d8a Mon Sep 17 00:00:00 2001
From: Yann Dubois <yanndubois96@gmail.com>
Date: Thu, 7 Mar 2024 13:20:44 -0800
Subject: [PATCH] update added models

---
 notebooks/length_correction.ipynb             | 8534 +++++++++--------
 src/alpaca_eval/constants.py                  |   37 +-
 ...ted_alpaca_eval_gpt4_turbo_leaderboard.csv |    4 +-
 3 files changed, 4328 insertions(+), 4247 deletions(-)

diff --git a/notebooks/length_correction.ipynb b/notebooks/length_correction.ipynb
index cb0edac6..800bba1b 100644
--- a/notebooks/length_correction.ipynb
+++ b/notebooks/length_correction.ipynb
@@ -148,7 +148,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "We are comparing to 33 Arena models\n"
+      "We are comparing to 36 Arena models\n"
      ]
     }
    ],
@@ -444,8 +444,8 @@
      "output_type": "stream",
      "text": [
       "Arena vs Length\n",
-      "Spearman Corr: 0.281\n",
-      "Kendall Corr: 0.194\n"
+      "Spearman Corr: 0.284\n",
+      "Kendall Corr: 0.197\n"
      ]
     }
    ],
@@ -492,12 +492,12 @@
       "Adversarial rank gain: 0.0\n",
       "\n",
       "## Correlation with Arena (higher is better)\n",
-      "Spearman Corr: 0.930\n",
-      "Kendall Corr: 0.811\n",
+      "Spearman Corr: 0.939\n",
+      "Kendall Corr: 0.826\n",
       "\n",
-      "## Correlation with length (closer to spearman=0.28, kendall=0.19 is better)\n",
-      "Spearman Corr: 0.467\n",
-      "Kendall Corr: 0.324\n",
+      "## Correlation with length (closer to spearman=0.28, kendall=0.20 is better)\n",
+      "Spearman Corr: 0.465\n",
+      "Kendall Corr: 0.322\n",
       "\n",
       "## Top 10 models\n"
      ]
@@ -508,13 +508,13 @@
        "gpt4_1106_preview_verbose                64.303601\n",
        "gpt4_1106_preview                        50.000000\n",
        "Snorkel-Mistral-PairRM-DPO-best-of-16    34.860133\n",
+       "Contextual-KTO-Mistral-PairRM            33.227355\n",
        "pairrm-Yi-34B-Chat                       31.241283\n",
        "Snorkel-Mistral-PairRM-DPO               30.220053\n",
        "Yi-34B-Chat                              29.659947\n",
        "claude-3-opus-20240229                   29.041764\n",
        "Qwen1.5-72B-Chat                         26.498283\n",
        "claude-3-sonnet-20240229                 25.556325\n",
-       "Mixtral-8x7B-Instruct-v0.1_verbose       24.614063\n",
        "Name: win_rate, dtype: float64"
       ]
      },
@@ -700,18 +700,18 @@
       "# Report for **balanced_win_rate**\n",
       "\n",
       "## Gameability (lower is better)\n",
-      "Verbosity gameability (relative std metric): 12.0%\n",
-      "Conciseness gameability (relative std metric): 18.2%\n",
+      "Verbosity gameability (relative std metric): 12.1%\n",
+      "Conciseness gameability (relative std metric): 18.4%\n",
       "Adversarial winrate gain: 40.8\n",
-      "Adversarial rank gain: 108.0\n",
+      "Adversarial rank gain: 110.0\n",
       "\n",
       "## Correlation with Arena (higher is better)\n",
-      "Spearman Corr: 0.933\n",
-      "Kendall Corr: 0.807\n",
+      "Spearman Corr: 0.947\n",
+      "Kendall Corr: 0.829\n",
       "\n",
-      "## Correlation with length (closer to spearman=0.28, kendall=0.19 is better)\n",
-      "Spearman Corr: 0.125\n",
-      "Kendall Corr: 0.085\n",
+      "## Correlation with length (closer to spearman=0.28, kendall=0.20 is better)\n",
+      "Spearman Corr: 0.148\n",
+      "Kendall Corr: 0.103\n",
       "\n",
       "## Top 10 models\n"
      ]
@@ -719,16 +719,16 @@
     {
      "data": {
       "text/plain": [
-       "gpt4_1106_preview_verbose                55.464179\n",
-       "gpt4_1106_preview                             50.0\n",
-       "gpt4_gamed                               44.532377\n",
-       "gpt4_1106_preview_concise                42.476316\n",
-       "claude-3-opus-20240229                   39.494379\n",
-       "Qwen1.5-72B-Chat                         37.072419\n",
-       "gpt4                                     36.503486\n",
-       "claude-3-sonnet-20240229                 35.516836\n",
-       "gpt4_0613_verbose                        32.752569\n",
-       "Snorkel-Mistral-PairRM-DPO-best-of-16     31.50451\n",
+       "gpt4_1106_preview_verbose    55.464179\n",
+       "gpt4_1106_preview                 50.0\n",
+       "gpt4_gamed                   44.532377\n",
+       "gpt4_1106_preview_concise    42.476316\n",
+       "claude-3-opus-20240229       39.494379\n",
+       "mistral-large-2402           37.141506\n",
+       "Qwen1.5-72B-Chat             37.072419\n",
+       "gpt4                         36.503486\n",
+       "claude-3-sonnet-20240229     35.516836\n",
+       "gpt4_0613_verbose            32.752569\n",
        "Name: balanced_win_rate, dtype: object"
       ]
      },
@@ -792,1504 +792,1532 @@
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_bc1a2_row0_col3, #T_bc1a2_row35_col6, #T_bc1a2_row54_col6, #T_bc1a2_row92_col6, #T_bc1a2_row97_col6 {\n",
+       "#T_f9ded_row0_col3, #T_f9ded_row37_col6, #T_f9ded_row40_col6, #T_f9ded_row99_col6, #T_f9ded_row100_col6 {\n",
        "  background-color: #e3edf3;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row0_col6, #T_bc1a2_row1_col3, #T_bc1a2_row1_col6, #T_bc1a2_row7_col6, #T_bc1a2_row26_col6, #T_bc1a2_row31_col6, #T_bc1a2_row40_col6, #T_bc1a2_row55_col6, #T_bc1a2_row72_col3, #T_bc1a2_row100_col6, #T_bc1a2_row104_col6, #T_bc1a2_row125_col3, #T_bc1a2_row125_col6, #T_bc1a2_row126_col3, #T_bc1a2_row128_col3 {\n",
+       "#T_f9ded_row0_col6, #T_f9ded_row1_col3, #T_f9ded_row1_col6, #T_f9ded_row7_col6, #T_f9ded_row28_col6, #T_f9ded_row33_col6, #T_f9ded_row42_col6, #T_f9ded_row57_col6, #T_f9ded_row74_col3, #T_f9ded_row102_col6, #T_f9ded_row106_col6, #T_f9ded_row127_col3, #T_f9ded_row127_col6, #T_f9ded_row128_col3, #T_f9ded_row130_col3 {\n",
        "  background-color: #f7f6f6;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row2_col3, #T_bc1a2_row29_col3 {\n",
+       "#T_f9ded_row2_col3, #T_f9ded_row31_col3 {\n",
        "  background-color: #fbd0b9;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row2_col6, #T_bc1a2_row56_col3, #T_bc1a2_row66_col3, #T_bc1a2_row71_col3, #T_bc1a2_row75_col3, #T_bc1a2_row78_col6, #T_bc1a2_row86_col6, #T_bc1a2_row112_col3, #T_bc1a2_row118_col3 {\n",
-       "  background-color: #f8f1ed;\n",
+       "#T_f9ded_row2_col6, #T_f9ded_row11_col6, #T_f9ded_row22_col3, #T_f9ded_row41_col6, #T_f9ded_row43_col3, #T_f9ded_row48_col6, #T_f9ded_row53_col3, #T_f9ded_row61_col3, #T_f9ded_row65_col6, #T_f9ded_row82_col3, #T_f9ded_row92_col6, #T_f9ded_row95_col3, #T_f9ded_row98_col3, #T_f9ded_row106_col3, #T_f9ded_row112_col3, #T_f9ded_row115_col6 {\n",
+       "  background-color: #f9f0eb;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row3_col3, #T_bc1a2_row5_col3, #T_bc1a2_row33_col6, #T_bc1a2_row69_col6, #T_bc1a2_row70_col3 {\n",
+       "#T_f9ded_row3_col3, #T_f9ded_row5_col3, #T_f9ded_row72_col3 {\n",
        "  background-color: #fbe5d8;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row3_col6, #T_bc1a2_row5_col6, #T_bc1a2_row6_col6, #T_bc1a2_row13_col6, #T_bc1a2_row48_col6, #T_bc1a2_row82_col3, #T_bc1a2_row120_col3, #T_bc1a2_row123_col3 {\n",
+       "#T_f9ded_row3_col6, #T_f9ded_row5_col6, #T_f9ded_row6_col6, #T_f9ded_row15_col6, #T_f9ded_row50_col6, #T_f9ded_row84_col3, #T_f9ded_row122_col3, #T_f9ded_row125_col3 {\n",
        "  background-color: #f7f5f4;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row4_col3, #T_bc1a2_row49_col3, #T_bc1a2_row111_col3 {\n",
+       "#T_f9ded_row4_col3, #T_f9ded_row51_col3, #T_f9ded_row51_col6, #T_f9ded_row66_col6, #T_f9ded_row113_col3 {\n",
        "  background-color: #fce0d0;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row4_col6, #T_bc1a2_row8_col6, #T_bc1a2_row38_col3, #T_bc1a2_row53_col3, #T_bc1a2_row74_col3, #T_bc1a2_row117_col3, #T_bc1a2_row122_col3, #T_bc1a2_row127_col3 {\n",
+       "#T_f9ded_row4_col6, #T_f9ded_row8_col6, #T_f9ded_row40_col3, #T_f9ded_row55_col3, #T_f9ded_row76_col3, #T_f9ded_row119_col3, #T_f9ded_row124_col3, #T_f9ded_row129_col3 {\n",
        "  background-color: #f8f4f2;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row6_col3, #T_bc1a2_row26_col3, #T_bc1a2_row37_col6 {\n",
+       "#T_f9ded_row6_col3, #T_f9ded_row28_col3 {\n",
        "  background-color: #fae8de;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row7_col3, #T_bc1a2_row34_col3, #T_bc1a2_row36_col3, #T_bc1a2_row39_col3 {\n",
+       "#T_f9ded_row7_col3, #T_f9ded_row35_col6, #T_f9ded_row36_col3, #T_f9ded_row38_col3, #T_f9ded_row41_col3, #T_f9ded_row71_col6 {\n",
        "  background-color: #fbe6da;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row8_col3, #T_bc1a2_row13_col3, #T_bc1a2_row31_col3, #T_bc1a2_row46_col3, #T_bc1a2_row69_col3, #T_bc1a2_row85_col3, #T_bc1a2_row88_col3 {\n",
+       "#T_f9ded_row8_col3, #T_f9ded_row15_col3, #T_f9ded_row33_col3, #T_f9ded_row48_col3, #T_f9ded_row71_col3, #T_f9ded_row87_col3, #T_f9ded_row90_col3 {\n",
        "  background-color: #fae7dc;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row9_col3, #T_bc1a2_row21_col3, #T_bc1a2_row27_col3, #T_bc1a2_row43_col3, #T_bc1a2_row47_col3, #T_bc1a2_row55_col3, #T_bc1a2_row61_col3, #T_bc1a2_row62_col3, #T_bc1a2_row86_col3, #T_bc1a2_row90_col3, #T_bc1a2_row109_col3 {\n",
-       "  background-color: #f9ede5;\n",
+       "#T_f9ded_row9_col3, #T_f9ded_row30_col3, #T_f9ded_row72_col6 {\n",
+       "  background-color: #fddcc9;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row9_col6, #T_bc1a2_row16_col3, #T_bc1a2_row35_col3, #T_bc1a2_row43_col6, #T_bc1a2_row47_col6, #T_bc1a2_row62_col6, #T_bc1a2_row76_col6, #T_bc1a2_row94_col6, #T_bc1a2_row120_col6, #T_bc1a2_row122_col6, #T_bc1a2_row123_col6, #T_bc1a2_row127_col6 {\n",
-       "  background-color: #f5f6f7;\n",
+       "#T_f9ded_row9_col6, #T_f9ded_row17_col6, #T_f9ded_row32_col3, #T_f9ded_row44_col3, #T_f9ded_row54_col3, #T_f9ded_row70_col3, #T_f9ded_row75_col6, #T_f9ded_row78_col3, #T_f9ded_row89_col3, #T_f9ded_row93_col6, #T_f9ded_row105_col6, #T_f9ded_row110_col3, #T_f9ded_row117_col3 {\n",
+       "  background-color: #f9eee7;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row10_col3, #T_bc1a2_row19_col3, #T_bc1a2_row49_col6, #T_bc1a2_row64_col6 {\n",
-       "  background-color: #fcdfcf;\n",
+       "#T_f9ded_row10_col3, #T_f9ded_row23_col3, #T_f9ded_row27_col6, #T_f9ded_row29_col3, #T_f9ded_row45_col3, #T_f9ded_row49_col3, #T_f9ded_row57_col3, #T_f9ded_row63_col3, #T_f9ded_row64_col3, #T_f9ded_row83_col6, #T_f9ded_row88_col3, #T_f9ded_row92_col3, #T_f9ded_row111_col3 {\n",
+       "  background-color: #f9ede5;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row10_col6, #T_bc1a2_row20_col3, #T_bc1a2_row39_col6, #T_bc1a2_row41_col3, #T_bc1a2_row51_col3, #T_bc1a2_row59_col3, #T_bc1a2_row80_col3, #T_bc1a2_row90_col6, #T_bc1a2_row93_col3, #T_bc1a2_row96_col3, #T_bc1a2_row104_col3, #T_bc1a2_row110_col3 {\n",
-       "  background-color: #f9f0eb;\n",
+       "#T_f9ded_row10_col6, #T_f9ded_row14_col3, #T_f9ded_row24_col6, #T_f9ded_row29_col6, #T_f9ded_row34_col6, #T_f9ded_row44_col6, #T_f9ded_row63_col6, #T_f9ded_row112_col6, #T_f9ded_row114_col6, #T_f9ded_row118_col6, #T_f9ded_row120_col6 {\n",
+       "  background-color: #f3f5f6;\n",
+       "  color: #000000;\n",
+       "}\n",
+       "#T_f9ded_row11_col3, #T_f9ded_row21_col3 {\n",
+       "  background-color: #fcdfcf;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row11_col3, #T_bc1a2_row20_col6, #T_bc1a2_row58_col6 {\n",
+       "#T_f9ded_row12_col3, #T_f9ded_row60_col6 {\n",
        "  background-color: #eff3f5;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row11_col6, #T_bc1a2_row21_col6, #T_bc1a2_row52_col6, #T_bc1a2_row60_col6, #T_bc1a2_row87_col6, #T_bc1a2_row89_col6, #T_bc1a2_row121_col6 {\n",
+       "#T_f9ded_row12_col6, #T_f9ded_row13_col6, #T_f9ded_row23_col6, #T_f9ded_row54_col6, #T_f9ded_row62_col6, #T_f9ded_row89_col6, #T_f9ded_row91_col6, #T_f9ded_row123_col6 {\n",
        "  background-color: #f0f4f6;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row12_col3, #T_bc1a2_row22_col6, #T_bc1a2_row27_col6, #T_bc1a2_row32_col6, #T_bc1a2_row42_col6, #T_bc1a2_row61_col6, #T_bc1a2_row110_col6, #T_bc1a2_row112_col6, #T_bc1a2_row116_col6, #T_bc1a2_row118_col6 {\n",
-       "  background-color: #f3f5f6;\n",
+       "#T_f9ded_row13_col3, #T_f9ded_row19_col3, #T_f9ded_row70_col6, #T_f9ded_row98_col6 {\n",
+       "  background-color: #f2f5f6;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row12_col6, #T_bc1a2_row30_col6 {\n",
+       "#T_f9ded_row14_col6, #T_f9ded_row22_col6, #T_f9ded_row32_col6, #T_f9ded_row69_col6, #T_f9ded_row128_col6 {\n",
        "  background-color: #edf2f5;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row14_col3, #T_bc1a2_row18_col3 {\n",
+       "#T_f9ded_row16_col3, #T_f9ded_row20_col3 {\n",
        "  background-color: #fce2d2;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row14_col6, #T_bc1a2_row34_col6, #T_bc1a2_row44_col3, #T_bc1a2_row57_col3, #T_bc1a2_row77_col3, #T_bc1a2_row92_col3, #T_bc1a2_row101_col3, #T_bc1a2_row102_col3, #T_bc1a2_row105_col6, #T_bc1a2_row107_col3, #T_bc1a2_row109_col6, #T_bc1a2_row114_col3, #T_bc1a2_row115_col6, #T_bc1a2_row116_col3, #T_bc1a2_row119_col6, #T_bc1a2_row124_col6 {\n",
+       "#T_f9ded_row16_col6, #T_f9ded_row36_col6, #T_f9ded_row46_col3, #T_f9ded_row59_col3, #T_f9ded_row79_col3, #T_f9ded_row94_col3, #T_f9ded_row103_col3, #T_f9ded_row104_col3, #T_f9ded_row107_col6, #T_f9ded_row109_col3, #T_f9ded_row111_col6, #T_f9ded_row116_col3, #T_f9ded_row117_col6, #T_f9ded_row118_col3, #T_f9ded_row121_col6, #T_f9ded_row126_col6 {\n",
        "  background-color: #f8f2ef;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row15_col3 {\n",
+       "#T_f9ded_row17_col3 {\n",
        "  background-color: #fcdecd;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row15_col6, #T_bc1a2_row30_col3, #T_bc1a2_row42_col3, #T_bc1a2_row52_col3, #T_bc1a2_row68_col3, #T_bc1a2_row73_col6, #T_bc1a2_row76_col3, #T_bc1a2_row87_col3, #T_bc1a2_row91_col6, #T_bc1a2_row103_col6, #T_bc1a2_row108_col3, #T_bc1a2_row115_col3 {\n",
-       "  background-color: #f9eee7;\n",
+       "#T_f9ded_row18_col3, #T_f9ded_row37_col3, #T_f9ded_row45_col6, #T_f9ded_row49_col6, #T_f9ded_row64_col6, #T_f9ded_row78_col6, #T_f9ded_row96_col6, #T_f9ded_row122_col6, #T_f9ded_row124_col6, #T_f9ded_row125_col6, #T_f9ded_row129_col6 {\n",
+       "  background-color: #f5f6f7;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row16_col6, #T_bc1a2_row57_col6, #T_bc1a2_row77_col6, #T_bc1a2_row80_col6, #T_bc1a2_row117_col6 {\n",
+       "#T_f9ded_row18_col6, #T_f9ded_row59_col6, #T_f9ded_row77_col6, #T_f9ded_row79_col6, #T_f9ded_row82_col6, #T_f9ded_row109_col6, #T_f9ded_row119_col6 {\n",
        "  background-color: #e9f0f4;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row17_col3, #T_bc1a2_row68_col6, #T_bc1a2_row96_col6 {\n",
-       "  background-color: #f2f5f6;\n",
-       "  color: #000000;\n",
-       "}\n",
-       "#T_bc1a2_row17_col6, #T_bc1a2_row24_col6, #T_bc1a2_row44_col6, #T_bc1a2_row45_col6, #T_bc1a2_row71_col6, #T_bc1a2_row99_col6, #T_bc1a2_row101_col6 {\n",
-       "  background-color: #e6eff4;\n",
+       "#T_f9ded_row19_col6, #T_f9ded_row56_col6, #T_f9ded_row94_col6 {\n",
+       "  background-color: #e4eef4;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row18_col6, #T_bc1a2_row23_col3, #T_bc1a2_row45_col3, #T_bc1a2_row54_col3, #T_bc1a2_row79_col3, #T_bc1a2_row95_col3, #T_bc1a2_row97_col3, #T_bc1a2_row98_col3, #T_bc1a2_row99_col3, #T_bc1a2_row108_col6, #T_bc1a2_row121_col3 {\n",
+       "#T_f9ded_row20_col6, #T_f9ded_row25_col3, #T_f9ded_row47_col3, #T_f9ded_row56_col3, #T_f9ded_row81_col3, #T_f9ded_row97_col3, #T_f9ded_row99_col3, #T_f9ded_row100_col3, #T_f9ded_row101_col3, #T_f9ded_row110_col6, #T_f9ded_row123_col3 {\n",
        "  background-color: #f8f3f0;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row19_col6, #T_bc1a2_row46_col6, #T_bc1a2_row58_col3, #T_bc1a2_row60_col3, #T_bc1a2_row63_col6, #T_bc1a2_row67_col3, #T_bc1a2_row89_col3, #T_bc1a2_row94_col3, #T_bc1a2_row100_col3, #T_bc1a2_row106_col3, #T_bc1a2_row113_col6, #T_bc1a2_row119_col3, #T_bc1a2_row124_col3 {\n",
+       "#T_f9ded_row21_col6, #T_f9ded_row60_col3, #T_f9ded_row62_col3, #T_f9ded_row69_col3, #T_f9ded_row91_col3, #T_f9ded_row96_col3, #T_f9ded_row102_col3, #T_f9ded_row108_col3, #T_f9ded_row121_col3, #T_f9ded_row126_col3 {\n",
        "  background-color: #f9efe9;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row22_col3, #T_bc1a2_row32_col3, #T_bc1a2_row63_col3, #T_bc1a2_row83_col3, #T_bc1a2_row83_col6, #T_bc1a2_row84_col3, #T_bc1a2_row84_col6 {\n",
+       "#T_f9ded_row24_col3, #T_f9ded_row34_col3, #T_f9ded_row39_col6, #T_f9ded_row65_col3, #T_f9ded_row85_col3, #T_f9ded_row85_col6, #T_f9ded_row86_col3, #T_f9ded_row86_col6 {\n",
        "  background-color: #fae9df;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row23_col6, #T_bc1a2_row41_col6, #T_bc1a2_row51_col6, #T_bc1a2_row56_col6, #T_bc1a2_row59_col6, #T_bc1a2_row114_col6 {\n",
+       "#T_f9ded_row25_col6, #T_f9ded_row43_col6, #T_f9ded_row53_col6, #T_f9ded_row58_col6, #T_f9ded_row61_col6, #T_f9ded_row116_col6 {\n",
        "  background-color: #eaf1f5;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row24_col3, #T_bc1a2_row106_col6, #T_bc1a2_row128_col6 {\n",
+       "#T_f9ded_row26_col3, #T_f9ded_row108_col6, #T_f9ded_row130_col6 {\n",
        "  background-color: #f6f7f7;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row25_col3 {\n",
-       "  background-color: #fdddcb;\n",
-       "  color: #000000;\n",
-       "}\n",
-       "#T_bc1a2_row25_col6, #T_bc1a2_row36_col6, #T_bc1a2_row40_col3, #T_bc1a2_row78_col3, #T_bc1a2_row81_col6, #T_bc1a2_row103_col3, #T_bc1a2_row105_col3, #T_bc1a2_row113_col3 {\n",
-       "  background-color: #f9ebe3;\n",
+       "#T_f9ded_row26_col6, #T_f9ded_row46_col6, #T_f9ded_row47_col6, #T_f9ded_row73_col6, #T_f9ded_row101_col6, #T_f9ded_row103_col6 {\n",
+       "  background-color: #e6eff4;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row28_col3, #T_bc1a2_row29_col6, #T_bc1a2_row70_col6 {\n",
-       "  background-color: #fddcc9;\n",
+       "#T_f9ded_row27_col3, #T_f9ded_row31_col6 {\n",
+       "  background-color: #fdddcb;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row28_col6, #T_bc1a2_row48_col3, #T_bc1a2_row73_col3, #T_bc1a2_row81_col3, #T_bc1a2_row91_col3 {\n",
+       "#T_f9ded_row30_col6, #T_f9ded_row50_col3, #T_f9ded_row75_col3, #T_f9ded_row83_col3, #T_f9ded_row93_col3 {\n",
        "  background-color: #faeae1;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row33_col3, #T_bc1a2_row37_col3, #T_bc1a2_row64_col3, #T_bc1a2_row88_col6 {\n",
+       "#T_f9ded_row35_col3, #T_f9ded_row39_col3, #T_f9ded_row66_col3, #T_f9ded_row90_col6 {\n",
        "  background-color: #fbe3d4;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row38_col6, #T_bc1a2_row79_col6, #T_bc1a2_row98_col6 {\n",
-       "  background-color: #e1edf3;\n",
+       "#T_f9ded_row38_col6, #T_f9ded_row42_col3, #T_f9ded_row80_col3, #T_f9ded_row105_col3, #T_f9ded_row107_col3, #T_f9ded_row115_col3 {\n",
+       "  background-color: #f9ebe3;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row50_col3, #T_bc1a2_row111_col6 {\n",
+       "#T_f9ded_row52_col3 {\n",
        "  background-color: #fac8af;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row50_col6 {\n",
+       "#T_f9ded_row52_col6 {\n",
        "  background-color: #f9c2a7;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row53_col6 {\n",
+       "#T_f9ded_row55_col6 {\n",
        "  background-color: #e0ecf3;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row65_col3, #T_bc1a2_row65_col6 {\n",
+       "#T_f9ded_row58_col3, #T_f9ded_row68_col3, #T_f9ded_row73_col3, #T_f9ded_row77_col3, #T_f9ded_row80_col6, #T_f9ded_row88_col6, #T_f9ded_row114_col3, #T_f9ded_row120_col3 {\n",
+       "  background-color: #f8f1ed;\n",
+       "  color: #000000;\n",
+       "}\n",
+       "#T_f9ded_row67_col3, #T_f9ded_row67_col6 {\n",
        "  background-color: #e48066;\n",
        "  color: #f1f1f1;\n",
        "}\n",
-       "#T_bc1a2_row66_col6, #T_bc1a2_row75_col6, #T_bc1a2_row95_col6, #T_bc1a2_row107_col6 {\n",
+       "#T_f9ded_row68_col6, #T_f9ded_row97_col6 {\n",
        "  background-color: #e7f0f4;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row67_col6, #T_bc1a2_row93_col6, #T_bc1a2_row102_col6, #T_bc1a2_row126_col6 {\n",
-       "  background-color: #ecf2f5;\n",
-       "  color: #000000;\n",
-       "}\n",
-       "#T_bc1a2_row72_col6 {\n",
+       "#T_f9ded_row74_col6 {\n",
        "  background-color: #d5e7f1;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row74_col6 {\n",
+       "#T_f9ded_row76_col6 {\n",
        "  background-color: #d8e9f1;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row82_col6 {\n",
+       "#T_f9ded_row81_col6 {\n",
+       "  background-color: #e1edf3;\n",
+       "  color: #000000;\n",
+       "}\n",
+       "#T_f9ded_row84_col6 {\n",
        "  background-color: #d4e6f1;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_bc1a2_row85_col6 {\n",
+       "#T_f9ded_row87_col6 {\n",
        "  background-color: #fbe4d6;\n",
        "  color: #000000;\n",
        "}\n",
+       "#T_f9ded_row95_col6, #T_f9ded_row104_col6 {\n",
+       "  background-color: #ecf2f5;\n",
+       "  color: #000000;\n",
+       "}\n",
+       "#T_f9ded_row113_col6 {\n",
+       "  background-color: #facab1;\n",
+       "  color: #000000;\n",
+       "}\n",
        "</style>\n",
-       "<table id=\"T_bc1a2\">\n",
+       "<table id=\"T_f9ded\">\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_bc1a2_level0_col0\" class=\"col_heading level0 col0\" >avg_length</th>\n",
-       "      <th id=\"T_bc1a2_level0_col1\" class=\"col_heading level0 col1\" >win_rate</th>\n",
-       "      <th id=\"T_bc1a2_level0_col2\" class=\"col_heading level0 col2\" >new_win_rate</th>\n",
-       "      <th id=\"T_bc1a2_level0_col3\" class=\"col_heading level0 col3\" >delta_win_rate</th>\n",
-       "      <th id=\"T_bc1a2_level0_col4\" class=\"col_heading level0 col4\" >rank_win_rate</th>\n",
-       "      <th id=\"T_bc1a2_level0_col5\" class=\"col_heading level0 col5\" >rank_new_win_rate</th>\n",
-       "      <th id=\"T_bc1a2_level0_col6\" class=\"col_heading level0 col6\" >delta_rank</th>\n",
+       "      <th id=\"T_f9ded_level0_col0\" class=\"col_heading level0 col0\" >avg_length</th>\n",
+       "      <th id=\"T_f9ded_level0_col1\" class=\"col_heading level0 col1\" >win_rate</th>\n",
+       "      <th id=\"T_f9ded_level0_col2\" class=\"col_heading level0 col2\" >new_win_rate</th>\n",
+       "      <th id=\"T_f9ded_level0_col3\" class=\"col_heading level0 col3\" >delta_win_rate</th>\n",
+       "      <th id=\"T_f9ded_level0_col4\" class=\"col_heading level0 col4\" >rank_win_rate</th>\n",
+       "      <th id=\"T_f9ded_level0_col5\" class=\"col_heading level0 col5\" >rank_new_win_rate</th>\n",
+       "      <th id=\"T_f9ded_level0_col6\" class=\"col_heading level0 col6\" >delta_rank</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row0\" class=\"row_heading level0 row0\" >gpt4_1106_preview_verbose</th>\n",
-       "      <td id=\"T_bc1a2_row0_col0\" class=\"data row0 col0\" >2402</td>\n",
-       "      <td id=\"T_bc1a2_row0_col1\" class=\"data row0 col1\" >64.303601</td>\n",
-       "      <td id=\"T_bc1a2_row0_col2\" class=\"data row0 col2\" >55.464179</td>\n",
-       "      <td id=\"T_bc1a2_row0_col3\" class=\"data row0 col3\" >-8.839422</td>\n",
-       "      <td id=\"T_bc1a2_row0_col4\" class=\"data row0 col4\" >0</td>\n",
-       "      <td id=\"T_bc1a2_row0_col5\" class=\"data row0 col5\" >0</td>\n",
-       "      <td id=\"T_bc1a2_row0_col6\" class=\"data row0 col6\" >0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row1\" class=\"row_heading level0 row1\" >gpt4_1106_preview</th>\n",
-       "      <td id=\"T_bc1a2_row1_col0\" class=\"data row1 col0\" >2049</td>\n",
-       "      <td id=\"T_bc1a2_row1_col1\" class=\"data row1 col1\" >50.000000</td>\n",
-       "      <td id=\"T_bc1a2_row1_col2\" class=\"data row1 col2\" >50.000000</td>\n",
-       "      <td id=\"T_bc1a2_row1_col3\" class=\"data row1 col3\" >0.000000</td>\n",
-       "      <td id=\"T_bc1a2_row1_col4\" class=\"data row1 col4\" >1</td>\n",
-       "      <td id=\"T_bc1a2_row1_col5\" class=\"data row1 col5\" >1</td>\n",
-       "      <td id=\"T_bc1a2_row1_col6\" class=\"data row1 col6\" >0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row2\" class=\"row_heading level0 row2\" >gpt4_1106_preview_concise</th>\n",
-       "      <td id=\"T_bc1a2_row2_col0\" class=\"data row2 col0\" >1136</td>\n",
-       "      <td id=\"T_bc1a2_row2_col1\" class=\"data row2 col1\" >22.920194</td>\n",
-       "      <td id=\"T_bc1a2_row2_col2\" class=\"data row2 col2\" >42.476316</td>\n",
-       "      <td id=\"T_bc1a2_row2_col3\" class=\"data row2 col3\" >19.556121</td>\n",
-       "      <td id=\"T_bc1a2_row2_col4\" class=\"data row2 col4\" >13</td>\n",
-       "      <td id=\"T_bc1a2_row2_col5\" class=\"data row2 col5\" >3</td>\n",
-       "      <td id=\"T_bc1a2_row2_col6\" class=\"data row2 col6\" >10</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row3\" class=\"row_heading level0 row3\" >claude-3-opus-20240229</th>\n",
-       "      <td id=\"T_bc1a2_row3_col0\" class=\"data row3 col0\" >1388</td>\n",
-       "      <td id=\"T_bc1a2_row3_col1\" class=\"data row3 col1\" >29.041764</td>\n",
-       "      <td id=\"T_bc1a2_row3_col2\" class=\"data row3 col2\" >39.494379</td>\n",
-       "      <td id=\"T_bc1a2_row3_col3\" class=\"data row3 col3\" >10.452615</td>\n",
-       "      <td id=\"T_bc1a2_row3_col4\" class=\"data row3 col4\" >6</td>\n",
-       "      <td id=\"T_bc1a2_row3_col5\" class=\"data row3 col5\" >4</td>\n",
-       "      <td id=\"T_bc1a2_row3_col6\" class=\"data row3 col6\" >2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row4\" class=\"row_heading level0 row4\" >gpt4</th>\n",
-       "      <td id=\"T_bc1a2_row4_col0\" class=\"data row4 col0\" >1365</td>\n",
-       "      <td id=\"T_bc1a2_row4_col1\" class=\"data row4 col1\" >23.576789</td>\n",
-       "      <td id=\"T_bc1a2_row4_col2\" class=\"data row4 col2\" >36.503486</td>\n",
-       "      <td id=\"T_bc1a2_row4_col3\" class=\"data row4 col3\" >12.926697</td>\n",
-       "      <td id=\"T_bc1a2_row4_col4\" class=\"data row4 col4\" >11</td>\n",
-       "      <td id=\"T_bc1a2_row4_col5\" class=\"data row4 col5\" >6</td>\n",
-       "      <td id=\"T_bc1a2_row4_col6\" class=\"data row4 col6\" >5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row5\" class=\"row_heading level0 row5\" >Qwen1.5-72B-Chat</th>\n",
-       "      <td id=\"T_bc1a2_row5_col0\" class=\"data row5 col0\" >1549</td>\n",
-       "      <td id=\"T_bc1a2_row5_col1\" class=\"data row5 col1\" >26.498283</td>\n",
-       "      <td id=\"T_bc1a2_row5_col2\" class=\"data row5 col2\" >37.072419</td>\n",
-       "      <td id=\"T_bc1a2_row5_col3\" class=\"data row5 col3\" >10.574135</td>\n",
-       "      <td id=\"T_bc1a2_row5_col4\" class=\"data row5 col4\" >7</td>\n",
-       "      <td id=\"T_bc1a2_row5_col5\" class=\"data row5 col5\" >5</td>\n",
-       "      <td id=\"T_bc1a2_row5_col6\" class=\"data row5 col6\" >2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row6\" class=\"row_heading level0 row6\" >gpt4_0314</th>\n",
-       "      <td id=\"T_bc1a2_row6_col0\" class=\"data row6 col0\" >1371</td>\n",
-       "      <td id=\"T_bc1a2_row6_col1\" class=\"data row6 col1\" >22.073259</td>\n",
-       "      <td id=\"T_bc1a2_row6_col2\" class=\"data row6 col2\" >30.972772</td>\n",
-       "      <td id=\"T_bc1a2_row6_col3\" class=\"data row6 col3\" >8.899513</td>\n",
-       "      <td id=\"T_bc1a2_row6_col4\" class=\"data row6 col4\" >14</td>\n",
-       "      <td id=\"T_bc1a2_row6_col5\" class=\"data row6 col5\" >11</td>\n",
-       "      <td id=\"T_bc1a2_row6_col6\" class=\"data row6 col6\" >3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row7\" class=\"row_heading level0 row7\" >claude-3-sonnet-20240229</th>\n",
-       "      <td id=\"T_bc1a2_row7_col0\" class=\"data row7 col0\" >1420</td>\n",
-       "      <td id=\"T_bc1a2_row7_col1\" class=\"data row7 col1\" >25.556325</td>\n",
-       "      <td id=\"T_bc1a2_row7_col2\" class=\"data row7 col2\" >35.516836</td>\n",
-       "      <td id=\"T_bc1a2_row7_col3\" class=\"data row7 col3\" >9.960510</td>\n",
-       "      <td id=\"T_bc1a2_row7_col4\" class=\"data row7 col4\" >8</td>\n",
-       "      <td id=\"T_bc1a2_row7_col5\" class=\"data row7 col5\" >7</td>\n",
-       "      <td id=\"T_bc1a2_row7_col6\" class=\"data row7 col6\" >1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row8\" class=\"row_heading level0 row8\" >gpt4_0613_verbose</th>\n",
-       "      <td id=\"T_bc1a2_row8_col0\" class=\"data row8 col0\" >1473</td>\n",
-       "      <td id=\"T_bc1a2_row8_col1\" class=\"data row8 col1\" >23.237360</td>\n",
-       "      <td id=\"T_bc1a2_row8_col2\" class=\"data row8 col2\" >32.752569</td>\n",
-       "      <td id=\"T_bc1a2_row8_col3\" class=\"data row8 col3\" >9.515209</td>\n",
-       "      <td id=\"T_bc1a2_row8_col4\" class=\"data row8 col4\" >12</td>\n",
-       "      <td id=\"T_bc1a2_row8_col5\" class=\"data row8 col5\" >8</td>\n",
-       "      <td id=\"T_bc1a2_row8_col6\" class=\"data row8 col6\" >4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row9\" class=\"row_heading level0 row9\" >claude-2.1_verbose</th>\n",
-       "      <td id=\"T_bc1a2_row9_col0\" class=\"data row9 col0\" >1414</td>\n",
-       "      <td id=\"T_bc1a2_row9_col1\" class=\"data row9 col1\" >24.354071</td>\n",
-       "      <td id=\"T_bc1a2_row9_col2\" class=\"data row9 col2\" >30.614862</td>\n",
-       "      <td id=\"T_bc1a2_row9_col3\" class=\"data row9 col3\" >6.260791</td>\n",
-       "      <td id=\"T_bc1a2_row9_col4\" class=\"data row9 col4\" >10</td>\n",
-       "      <td id=\"T_bc1a2_row9_col5\" class=\"data row9 col5\" >13</td>\n",
-       "      <td id=\"T_bc1a2_row9_col6\" class=\"data row9 col6\" >-3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row10\" class=\"row_heading level0 row10\" >gpt4_0613</th>\n",
-       "      <td id=\"T_bc1a2_row10_col0\" class=\"data row10 col0\" >1140</td>\n",
-       "      <td id=\"T_bc1a2_row10_col1\" class=\"data row10 col1\" >15.755038</td>\n",
-       "      <td id=\"T_bc1a2_row10_col2\" class=\"data row10 col2\" >29.528662</td>\n",
-       "      <td id=\"T_bc1a2_row10_col3\" class=\"data row10 col3\" >13.773624</td>\n",
-       "      <td id=\"T_bc1a2_row10_col4\" class=\"data row10 col4\" >28</td>\n",
-       "      <td id=\"T_bc1a2_row10_col5\" class=\"data row10 col5\" >17</td>\n",
-       "      <td id=\"T_bc1a2_row10_col6\" class=\"data row10 col6\" >11</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row11\" class=\"row_heading level0 row11\" >Snorkel-Mistral-PairRM-DPO-best-of-16</th>\n",
-       "      <td id=\"T_bc1a2_row11_col0\" class=\"data row11 col0\" >2616</td>\n",
-       "      <td id=\"T_bc1a2_row11_col1\" class=\"data row11 col1\" >34.860133</td>\n",
-       "      <td id=\"T_bc1a2_row11_col2\" class=\"data row11 col2\" >31.504510</td>\n",
-       "      <td id=\"T_bc1a2_row11_col3\" class=\"data row11 col3\" >-3.355623</td>\n",
-       "      <td id=\"T_bc1a2_row11_col4\" class=\"data row11 col4\" >2</td>\n",
-       "      <td id=\"T_bc1a2_row11_col5\" class=\"data row11 col5\" >9</td>\n",
-       "      <td id=\"T_bc1a2_row11_col6\" class=\"data row11 col6\" >-7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row12\" class=\"row_heading level0 row12\" >pairrm-Yi-34B-Chat</th>\n",
-       "      <td id=\"T_bc1a2_row12_col0\" class=\"data row12 col0\" >2195</td>\n",
-       "      <td id=\"T_bc1a2_row12_col1\" class=\"data row12 col1\" >31.241283</td>\n",
-       "      <td id=\"T_bc1a2_row12_col2\" class=\"data row12 col2\" >29.895164</td>\n",
-       "      <td id=\"T_bc1a2_row12_col3\" class=\"data row12 col3\" >-1.346119</td>\n",
-       "      <td id=\"T_bc1a2_row12_col4\" class=\"data row12 col4\" >3</td>\n",
-       "      <td id=\"T_bc1a2_row12_col5\" class=\"data row12 col5\" >14</td>\n",
-       "      <td id=\"T_bc1a2_row12_col6\" class=\"data row12 col6\" >-11</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row13\" class=\"row_heading level0 row13\" >mistral-medium</th>\n",
-       "      <td id=\"T_bc1a2_row13_col0\" class=\"data row13 col0\" >1500</td>\n",
-       "      <td id=\"T_bc1a2_row13_col1\" class=\"data row13 col1\" >21.855773</td>\n",
-       "      <td id=\"T_bc1a2_row13_col2\" class=\"data row13 col2\" >30.845477</td>\n",
-       "      <td id=\"T_bc1a2_row13_col3\" class=\"data row13 col3\" >8.989704</td>\n",
-       "      <td id=\"T_bc1a2_row13_col4\" class=\"data row13 col4\" >15</td>\n",
-       "      <td id=\"T_bc1a2_row13_col5\" class=\"data row13 col5\" >12</td>\n",
-       "      <td id=\"T_bc1a2_row13_col6\" class=\"data row13 col6\" >3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row14\" class=\"row_heading level0 row14\" >claude-2</th>\n",
-       "      <td id=\"T_bc1a2_row14_col0\" class=\"data row14 col0\" >1069</td>\n",
-       "      <td id=\"T_bc1a2_row14_col1\" class=\"data row14 col1\" >17.188240</td>\n",
-       "      <td id=\"T_bc1a2_row14_col2\" class=\"data row14 col2\" >29.813958</td>\n",
-       "      <td id=\"T_bc1a2_row14_col3\" class=\"data row14 col3\" >12.625718</td>\n",
-       "      <td id=\"T_bc1a2_row14_col4\" class=\"data row14 col4\" >23</td>\n",
-       "      <td id=\"T_bc1a2_row14_col5\" class=\"data row14 col5\" >15</td>\n",
-       "      <td id=\"T_bc1a2_row14_col6\" class=\"data row14 col6\" >8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row15\" class=\"row_heading level0 row15\" >claude</th>\n",
-       "      <td id=\"T_bc1a2_row15_col0\" class=\"data row15 col0\" >1082</td>\n",
-       "      <td id=\"T_bc1a2_row15_col1\" class=\"data row15 col1\" >16.985344</td>\n",
-       "      <td id=\"T_bc1a2_row15_col2\" class=\"data row15 col2\" >31.090175</td>\n",
-       "      <td id=\"T_bc1a2_row15_col3\" class=\"data row15 col3\" >14.104832</td>\n",
-       "      <td id=\"T_bc1a2_row15_col4\" class=\"data row15 col4\" >24</td>\n",
-       "      <td id=\"T_bc1a2_row15_col5\" class=\"data row15 col5\" >10</td>\n",
-       "      <td id=\"T_bc1a2_row15_col6\" class=\"data row15 col6\" >14</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row16\" class=\"row_heading level0 row16\" >Yi-34B-Chat</th>\n",
-       "      <td id=\"T_bc1a2_row16_col0\" class=\"data row16 col0\" >2123</td>\n",
-       "      <td id=\"T_bc1a2_row16_col1\" class=\"data row16 col1\" >29.659947</td>\n",
-       "      <td id=\"T_bc1a2_row16_col2\" class=\"data row16 col2\" >28.477128</td>\n",
-       "      <td id=\"T_bc1a2_row16_col3\" class=\"data row16 col3\" >-1.182818</td>\n",
-       "      <td id=\"T_bc1a2_row16_col4\" class=\"data row16 col4\" >5</td>\n",
-       "      <td id=\"T_bc1a2_row16_col5\" class=\"data row16 col5\" >21</td>\n",
-       "      <td id=\"T_bc1a2_row16_col6\" class=\"data row16 col6\" >-16</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row17\" class=\"row_heading level0 row17\" >Snorkel-Mistral-PairRM-DPO</th>\n",
-       "      <td id=\"T_bc1a2_row17_col0\" class=\"data row17 col0\" >2736</td>\n",
-       "      <td id=\"T_bc1a2_row17_col1\" class=\"data row17 col1\" >30.220053</td>\n",
-       "      <td id=\"T_bc1a2_row17_col2\" class=\"data row17 col2\" >27.673988</td>\n",
-       "      <td id=\"T_bc1a2_row17_col3\" class=\"data row17 col3\" >-2.546065</td>\n",
-       "      <td id=\"T_bc1a2_row17_col4\" class=\"data row17 col4\" >4</td>\n",
-       "      <td id=\"T_bc1a2_row17_col5\" class=\"data row17 col5\" >24</td>\n",
-       "      <td id=\"T_bc1a2_row17_col6\" class=\"data row17 col6\" >-20</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row18\" class=\"row_heading level0 row18\" >claude-instant-1.2</th>\n",
-       "      <td id=\"T_bc1a2_row18_col0\" class=\"data row18 col0\" >1112</td>\n",
-       "      <td id=\"T_bc1a2_row18_col1\" class=\"data row18 col1\" >16.127400</td>\n",
-       "      <td id=\"T_bc1a2_row18_col2\" class=\"data row18 col2\" >28.730484</td>\n",
-       "      <td id=\"T_bc1a2_row18_col3\" class=\"data row18 col3\" >12.603085</td>\n",
-       "      <td id=\"T_bc1a2_row18_col4\" class=\"data row18 col4\" >25</td>\n",
-       "      <td id=\"T_bc1a2_row18_col5\" class=\"data row18 col5\" >19</td>\n",
-       "      <td id=\"T_bc1a2_row18_col6\" class=\"data row18 col6\" >6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row19\" class=\"row_heading level0 row19\" >claude-2.1</th>\n",
-       "      <td id=\"T_bc1a2_row19_col0\" class=\"data row19 col0\" >1096</td>\n",
-       "      <td id=\"T_bc1a2_row19_col1\" class=\"data row19 col1\" >15.733507</td>\n",
-       "      <td id=\"T_bc1a2_row19_col2\" class=\"data row19 col2\" >29.562828</td>\n",
-       "      <td id=\"T_bc1a2_row19_col3\" class=\"data row19 col3\" >13.829321</td>\n",
-       "      <td id=\"T_bc1a2_row19_col4\" class=\"data row19 col4\" >29</td>\n",
-       "      <td id=\"T_bc1a2_row19_col5\" class=\"data row19 col5\" >16</td>\n",
-       "      <td id=\"T_bc1a2_row19_col6\" class=\"data row19 col6\" >13</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row20\" class=\"row_heading level0 row20\" >xwinlm-70b-v0.1</th>\n",
-       "      <td id=\"T_bc1a2_row20_col0\" class=\"data row20 col0\" >1775</td>\n",
-       "      <td id=\"T_bc1a2_row20_col1\" class=\"data row20 col1\" >21.812957</td>\n",
-       "      <td id=\"T_bc1a2_row20_col2\" class=\"data row20 col2\" >25.825081</td>\n",
-       "      <td id=\"T_bc1a2_row20_col3\" class=\"data row20 col3\" >4.012124</td>\n",
-       "      <td id=\"T_bc1a2_row20_col4\" class=\"data row20 col4\" >16</td>\n",
-       "      <td id=\"T_bc1a2_row20_col5\" class=\"data row20 col5\" >26</td>\n",
-       "      <td id=\"T_bc1a2_row20_col6\" class=\"data row20 col6\" >-10</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row21\" class=\"row_heading level0 row21\" >gemini-pro</th>\n",
-       "      <td id=\"T_bc1a2_row21_col0\" class=\"data row21 col0\" >1456</td>\n",
-       "      <td id=\"T_bc1a2_row21_col1\" class=\"data row21 col1\" >18.177645</td>\n",
-       "      <td id=\"T_bc1a2_row21_col2\" class=\"data row21 col2\" >24.449134</td>\n",
-       "      <td id=\"T_bc1a2_row21_col3\" class=\"data row21 col3\" >6.271490</td>\n",
-       "      <td id=\"T_bc1a2_row21_col4\" class=\"data row21 col4\" >21</td>\n",
-       "      <td id=\"T_bc1a2_row21_col5\" class=\"data row21 col5\" >29</td>\n",
-       "      <td id=\"T_bc1a2_row21_col6\" class=\"data row21 col6\" >-8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row22\" class=\"row_heading level0 row22\" >Mixtral-8x7B-Instruct-v0.1</th>\n",
-       "      <td id=\"T_bc1a2_row22_col0\" class=\"data row22 col0\" >1465</td>\n",
-       "      <td id=\"T_bc1a2_row22_col1\" class=\"data row22 col1\" >18.255318</td>\n",
-       "      <td id=\"T_bc1a2_row22_col2\" class=\"data row22 col2\" >26.083414</td>\n",
-       "      <td id=\"T_bc1a2_row22_col3\" class=\"data row22 col3\" >7.828096</td>\n",
-       "      <td id=\"T_bc1a2_row22_col4\" class=\"data row22 col4\" >20</td>\n",
-       "      <td id=\"T_bc1a2_row22_col5\" class=\"data row22 col5\" >25</td>\n",
-       "      <td id=\"T_bc1a2_row22_col6\" class=\"data row22 col6\" >-5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row23\" class=\"row_heading level0 row23\" >evo-v2-7b</th>\n",
-       "      <td id=\"T_bc1a2_row23_col0\" class=\"data row23 col0\" >1754</td>\n",
-       "      <td id=\"T_bc1a2_row23_col1\" class=\"data row23 col1\" >20.834113</td>\n",
-       "      <td id=\"T_bc1a2_row23_col2\" class=\"data row23 col2\" >22.778849</td>\n",
-       "      <td id=\"T_bc1a2_row23_col3\" class=\"data row23 col3\" >1.944736</td>\n",
-       "      <td id=\"T_bc1a2_row23_col4\" class=\"data row23 col4\" >18</td>\n",
-       "      <td id=\"T_bc1a2_row23_col5\" class=\"data row23 col5\" >32</td>\n",
-       "      <td id=\"T_bc1a2_row23_col6\" class=\"data row23 col6\" >-14</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row24\" class=\"row_heading level0 row24\" >Mixtral-8x7B-Instruct-v0.1_verbose</th>\n",
-       "      <td id=\"T_bc1a2_row24_col0\" class=\"data row24 col0\" >2083</td>\n",
-       "      <td id=\"T_bc1a2_row24_col1\" class=\"data row24 col1\" >24.614063</td>\n",
-       "      <td id=\"T_bc1a2_row24_col2\" class=\"data row24 col2\" >24.503900</td>\n",
-       "      <td id=\"T_bc1a2_row24_col3\" class=\"data row24 col3\" >-0.110163</td>\n",
-       "      <td id=\"T_bc1a2_row24_col4\" class=\"data row24 col4\" >9</td>\n",
-       "      <td id=\"T_bc1a2_row24_col5\" class=\"data row24 col5\" >28</td>\n",
-       "      <td id=\"T_bc1a2_row24_col6\" class=\"data row24 col6\" >-19</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row25\" class=\"row_heading level0 row25\" >Mixtral-8x7B-Instruct-v0.1_concise</th>\n",
-       "      <td id=\"T_bc1a2_row25_col0\" class=\"data row25 col0\" >910</td>\n",
-       "      <td id=\"T_bc1a2_row25_col1\" class=\"data row25 col1\" >13.744040</td>\n",
-       "      <td id=\"T_bc1a2_row25_col2\" class=\"data row25 col2\" >28.436687</td>\n",
-       "      <td id=\"T_bc1a2_row25_col3\" class=\"data row25 col3\" >14.692646</td>\n",
-       "      <td id=\"T_bc1a2_row25_col4\" class=\"data row25 col4\" >39</td>\n",
-       "      <td id=\"T_bc1a2_row25_col5\" class=\"data row25 col5\" >22</td>\n",
-       "      <td id=\"T_bc1a2_row25_col6\" class=\"data row25 col6\" >17</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row26\" class=\"row_heading level0 row26\" >gpt-3.5-turbo-16k-0613</th>\n",
-       "      <td id=\"T_bc1a2_row26_col0\" class=\"data row26 col0\" >1328</td>\n",
-       "      <td id=\"T_bc1a2_row26_col1\" class=\"data row26 col1\" >14.132391</td>\n",
-       "      <td id=\"T_bc1a2_row26_col2\" class=\"data row26 col2\" >22.695292</td>\n",
-       "      <td id=\"T_bc1a2_row26_col3\" class=\"data row26 col3\" >8.562902</td>\n",
-       "      <td id=\"T_bc1a2_row26_col4\" class=\"data row26 col4\" >34</td>\n",
-       "      <td id=\"T_bc1a2_row26_col5\" class=\"data row26 col5\" >34</td>\n",
-       "      <td id=\"T_bc1a2_row26_col6\" class=\"data row26 col6\" >0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row27\" class=\"row_heading level0 row27\" >gpt-3.5-turbo-0613</th>\n",
-       "      <td id=\"T_bc1a2_row27_col0\" class=\"data row27 col0\" >1331</td>\n",
-       "      <td id=\"T_bc1a2_row27_col1\" class=\"data row27 col1\" >14.095799</td>\n",
-       "      <td id=\"T_bc1a2_row27_col2\" class=\"data row27 col2\" >20.421657</td>\n",
-       "      <td id=\"T_bc1a2_row27_col3\" class=\"data row27 col3\" >6.325858</td>\n",
-       "      <td id=\"T_bc1a2_row27_col4\" class=\"data row27 col4\" >35</td>\n",
-       "      <td id=\"T_bc1a2_row27_col5\" class=\"data row27 col5\" >40</td>\n",
-       "      <td id=\"T_bc1a2_row27_col6\" class=\"data row27 col6\" >-5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row28\" class=\"row_heading level0 row28\" >gpt-3.5-turbo-1106_verbose</th>\n",
-       "      <td id=\"T_bc1a2_row28_col0\" class=\"data row28 col0\" >1058</td>\n",
-       "      <td id=\"T_bc1a2_row28_col1\" class=\"data row28 col1\" >12.763170</td>\n",
-       "      <td id=\"T_bc1a2_row28_col2\" class=\"data row28 col2\" >28.251113</td>\n",
-       "      <td id=\"T_bc1a2_row28_col3\" class=\"data row28 col3\" >15.487943</td>\n",
-       "      <td id=\"T_bc1a2_row28_col4\" class=\"data row28 col4\" >43</td>\n",
-       "      <td id=\"T_bc1a2_row28_col5\" class=\"data row28 col5\" >23</td>\n",
-       "      <td id=\"T_bc1a2_row28_col6\" class=\"data row28 col6\" >20</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row29\" class=\"row_heading level0 row29\" >gpt4_0613_concise</th>\n",
-       "      <td id=\"T_bc1a2_row29_col0\" class=\"data row29 col0\" >627</td>\n",
-       "      <td id=\"T_bc1a2_row29_col1\" class=\"data row29 col1\" >9.400321</td>\n",
-       "      <td id=\"T_bc1a2_row29_col2\" class=\"data row29 col2\" >28.602992</td>\n",
-       "      <td id=\"T_bc1a2_row29_col3\" class=\"data row29 col3\" >19.202671</td>\n",
-       "      <td id=\"T_bc1a2_row29_col4\" class=\"data row29 col4\" >61</td>\n",
-       "      <td id=\"T_bc1a2_row29_col5\" class=\"data row29 col5\" >20</td>\n",
-       "      <td id=\"T_bc1a2_row29_col6\" class=\"data row29 col6\" >41</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row30\" class=\"row_heading level0 row30\" >pairrm-tulu-2-70b</th>\n",
-       "      <td id=\"T_bc1a2_row30_col0\" class=\"data row30 col0\" >1607</td>\n",
-       "      <td id=\"T_bc1a2_row30_col1\" class=\"data row30 col1\" >18.638963</td>\n",
-       "      <td id=\"T_bc1a2_row30_col2\" class=\"data row30 col2\" >23.943414</td>\n",
-       "      <td id=\"T_bc1a2_row30_col3\" class=\"data row30 col3\" >5.304451</td>\n",
-       "      <td id=\"T_bc1a2_row30_col4\" class=\"data row30 col4\" >19</td>\n",
-       "      <td id=\"T_bc1a2_row30_col5\" class=\"data row30 col5\" >30</td>\n",
-       "      <td id=\"T_bc1a2_row30_col6\" class=\"data row30 col6\" >-11</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row31\" class=\"row_heading level0 row31\" >tulu-2-dpo-70b</th>\n",
-       "      <td id=\"T_bc1a2_row31_col0\" class=\"data row31 col0\" >1418</td>\n",
-       "      <td id=\"T_bc1a2_row31_col1\" class=\"data row31 col1\" >15.982854</td>\n",
-       "      <td id=\"T_bc1a2_row31_col2\" class=\"data row31 col2\" >24.924799</td>\n",
-       "      <td id=\"T_bc1a2_row31_col3\" class=\"data row31 col3\" >8.941945</td>\n",
-       "      <td id=\"T_bc1a2_row31_col4\" class=\"data row31 col4\" >27</td>\n",
-       "      <td id=\"T_bc1a2_row31_col5\" class=\"data row31 col5\" >27</td>\n",
-       "      <td id=\"T_bc1a2_row31_col6\" class=\"data row31 col6\" >0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row32\" class=\"row_heading level0 row32\" >Mistral-7B-ReMax-v0.1</th>\n",
-       "      <td id=\"T_bc1a2_row32_col0\" class=\"data row32 col0\" >1478</td>\n",
-       "      <td id=\"T_bc1a2_row32_col1\" class=\"data row32 col1\" >15.999331</td>\n",
-       "      <td id=\"T_bc1a2_row32_col2\" class=\"data row32 col2\" >23.779278</td>\n",
-       "      <td id=\"T_bc1a2_row32_col3\" class=\"data row32 col3\" >7.779946</td>\n",
-       "      <td id=\"T_bc1a2_row32_col4\" class=\"data row32 col4\" >26</td>\n",
-       "      <td id=\"T_bc1a2_row32_col5\" class=\"data row32 col5\" >31</td>\n",
-       "      <td id=\"T_bc1a2_row32_col6\" class=\"data row32 col6\" >-5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row33\" class=\"row_heading level0 row33\" >gpt-3.5-turbo-1106</th>\n",
-       "      <td id=\"T_bc1a2_row33_col0\" class=\"data row33 col0\" >796</td>\n",
-       "      <td id=\"T_bc1a2_row33_col1\" class=\"data row33 col1\" >9.177965</td>\n",
-       "      <td id=\"T_bc1a2_row33_col2\" class=\"data row33 col2\" >21.197910</td>\n",
-       "      <td id=\"T_bc1a2_row33_col3\" class=\"data row33 col3\" >12.019945</td>\n",
-       "      <td id=\"T_bc1a2_row33_col4\" class=\"data row33 col4\" >64</td>\n",
-       "      <td id=\"T_bc1a2_row33_col5\" class=\"data row33 col5\" >37</td>\n",
-       "      <td id=\"T_bc1a2_row33_col6\" class=\"data row33 col6\" >27</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row34\" class=\"row_heading level0 row34\" >LMCocktail-10.7B-v1</th>\n",
-       "      <td id=\"T_bc1a2_row34_col0\" class=\"data row34 col0\" >1203</td>\n",
-       "      <td id=\"T_bc1a2_row34_col1\" class=\"data row34 col1\" >13.153431</td>\n",
-       "      <td id=\"T_bc1a2_row34_col2\" class=\"data row34 col2\" >22.716773</td>\n",
-       "      <td id=\"T_bc1a2_row34_col3\" class=\"data row34 col3\" >9.563342</td>\n",
-       "      <td id=\"T_bc1a2_row34_col4\" class=\"data row34 col4\" >40</td>\n",
-       "      <td id=\"T_bc1a2_row34_col5\" class=\"data row34 col5\" >33</td>\n",
-       "      <td id=\"T_bc1a2_row34_col6\" class=\"data row34 col6\" >7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row35\" class=\"row_heading level0 row35\" >internlm2-chat-20b-ppo</th>\n",
-       "      <td id=\"T_bc1a2_row35_col0\" class=\"data row35 col0\" >2373</td>\n",
-       "      <td id=\"T_bc1a2_row35_col1\" class=\"data row35 col1\" >21.749155</td>\n",
-       "      <td id=\"T_bc1a2_row35_col2\" class=\"data row35 col2\" >20.927878</td>\n",
-       "      <td id=\"T_bc1a2_row35_col3\" class=\"data row35 col3\" >-0.821277</td>\n",
-       "      <td id=\"T_bc1a2_row35_col4\" class=\"data row35 col4\" >17</td>\n",
-       "      <td id=\"T_bc1a2_row35_col5\" class=\"data row35 col5\" >39</td>\n",
-       "      <td id=\"T_bc1a2_row35_col6\" class=\"data row35 col6\" >-22</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row36\" class=\"row_heading level0 row36\" >claude-2.1_concise</th>\n",
-       "      <td id=\"T_bc1a2_row36_col0\" class=\"data row36 col0\" >573</td>\n",
-       "      <td id=\"T_bc1a2_row36_col1\" class=\"data row36 col1\" >9.227125</td>\n",
-       "      <td id=\"T_bc1a2_row36_col2\" class=\"data row36 col2\" >19.030658</td>\n",
-       "      <td id=\"T_bc1a2_row36_col3\" class=\"data row36 col3\" >9.803532</td>\n",
-       "      <td id=\"T_bc1a2_row36_col4\" class=\"data row36 col4\" >63</td>\n",
-       "      <td id=\"T_bc1a2_row36_col5\" class=\"data row36 col5\" >45</td>\n",
-       "      <td id=\"T_bc1a2_row36_col6\" class=\"data row36 col6\" >18</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row37\" class=\"row_heading level0 row37\" >gpt-3.5-turbo-0301</th>\n",
-       "      <td id=\"T_bc1a2_row37_col0\" class=\"data row37 col0\" >827</td>\n",
-       "      <td id=\"T_bc1a2_row37_col1\" class=\"data row37 col1\" >9.622453</td>\n",
-       "      <td id=\"T_bc1a2_row37_col2\" class=\"data row37 col2\" >21.634439</td>\n",
-       "      <td id=\"T_bc1a2_row37_col3\" class=\"data row37 col3\" >12.011986</td>\n",
-       "      <td id=\"T_bc1a2_row37_col4\" class=\"data row37 col4\" >58</td>\n",
-       "      <td id=\"T_bc1a2_row37_col5\" class=\"data row37 col5\" >36</td>\n",
-       "      <td id=\"T_bc1a2_row37_col6\" class=\"data row37 col6\" >22</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row38\" class=\"row_heading level0 row38\" >xwinlm-13b-v0.1</th>\n",
-       "      <td id=\"T_bc1a2_row38_col0\" class=\"data row38 col0\" >1894</td>\n",
-       "      <td id=\"T_bc1a2_row38_col1\" class=\"data row38 col1\" >17.427935</td>\n",
-       "      <td id=\"T_bc1a2_row38_col2\" class=\"data row38 col2\" >18.845262</td>\n",
-       "      <td id=\"T_bc1a2_row38_col3\" class=\"data row38 col3\" >1.417327</td>\n",
-       "      <td id=\"T_bc1a2_row38_col4\" class=\"data row38 col4\" >22</td>\n",
-       "      <td id=\"T_bc1a2_row38_col5\" class=\"data row38 col5\" >46</td>\n",
-       "      <td id=\"T_bc1a2_row38_col6\" class=\"data row38 col6\" >-24</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row39\" class=\"row_heading level0 row39\" >deepseek-llm-67b-chat</th>\n",
-       "      <td id=\"T_bc1a2_row39_col0\" class=\"data row39 col0\" >1151</td>\n",
-       "      <td id=\"T_bc1a2_row39_col1\" class=\"data row39 col1\" >12.093422</td>\n",
-       "      <td id=\"T_bc1a2_row39_col2\" class=\"data row39 col2\" >21.888822</td>\n",
-       "      <td id=\"T_bc1a2_row39_col3\" class=\"data row39 col3\" >9.795400</td>\n",
-       "      <td id=\"T_bc1a2_row39_col4\" class=\"data row39 col4\" >46</td>\n",
-       "      <td id=\"T_bc1a2_row39_col5\" class=\"data row39 col5\" >35</td>\n",
-       "      <td id=\"T_bc1a2_row39_col6\" class=\"data row39 col6\" >11</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row40\" class=\"row_heading level0 row40\" >gpt35_turbo_instruct</th>\n",
-       "      <td id=\"T_bc1a2_row40_col0\" class=\"data row40 col0\" >1018</td>\n",
-       "      <td id=\"T_bc1a2_row40_col1\" class=\"data row40 col1\" >8.462447</td>\n",
-       "      <td id=\"T_bc1a2_row40_col2\" class=\"data row40 col2\" >14.933606</td>\n",
-       "      <td id=\"T_bc1a2_row40_col3\" class=\"data row40 col3\" >6.471160</td>\n",
-       "      <td id=\"T_bc1a2_row40_col4\" class=\"data row40 col4\" >68</td>\n",
-       "      <td id=\"T_bc1a2_row40_col5\" class=\"data row40 col5\" >67</td>\n",
-       "      <td id=\"T_bc1a2_row40_col6\" class=\"data row40 col6\" >1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row41\" class=\"row_heading level0 row41\" >wizardlm-70b</th>\n",
-       "      <td id=\"T_bc1a2_row41_col0\" class=\"data row41 col0\" >1545</td>\n",
-       "      <td id=\"T_bc1a2_row41_col1\" class=\"data row41 col1\" >14.383896</td>\n",
-       "      <td id=\"T_bc1a2_row41_col2\" class=\"data row41 col2\" >18.441779</td>\n",
-       "      <td id=\"T_bc1a2_row41_col3\" class=\"data row41 col3\" >4.057883</td>\n",
-       "      <td id=\"T_bc1a2_row41_col4\" class=\"data row41 col4\" >32</td>\n",
-       "      <td id=\"T_bc1a2_row41_col5\" class=\"data row41 col5\" >47</td>\n",
-       "      <td id=\"T_bc1a2_row41_col6\" class=\"data row41 col6\" >-15</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row42\" class=\"row_heading level0 row42\" >vicuna-33b-v1.3</th>\n",
-       "      <td id=\"T_bc1a2_row42_col0\" class=\"data row42 col0\" >1479</td>\n",
-       "      <td id=\"T_bc1a2_row42_col1\" class=\"data row42 col1\" >12.705948</td>\n",
-       "      <td id=\"T_bc1a2_row42_col2\" class=\"data row42 col2\" >18.269349</td>\n",
-       "      <td id=\"T_bc1a2_row42_col3\" class=\"data row42 col3\" >5.563401</td>\n",
-       "      <td id=\"T_bc1a2_row42_col4\" class=\"data row42 col4\" >44</td>\n",
-       "      <td id=\"T_bc1a2_row42_col5\" class=\"data row42 col5\" >48</td>\n",
-       "      <td id=\"T_bc1a2_row42_col6\" class=\"data row42 col6\" >-4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row43\" class=\"row_heading level0 row43\" >pairrm-tulu-2-13b</th>\n",
-       "      <td id=\"T_bc1a2_row43_col0\" class=\"data row43 col0\" >1454</td>\n",
-       "      <td id=\"T_bc1a2_row43_col1\" class=\"data row43 col1\" >13.831901</td>\n",
-       "      <td id=\"T_bc1a2_row43_col2\" class=\"data row43 col2\" >20.187366</td>\n",
-       "      <td id=\"T_bc1a2_row43_col3\" class=\"data row43 col3\" >6.355465</td>\n",
-       "      <td id=\"T_bc1a2_row43_col4\" class=\"data row43 col4\" >38</td>\n",
-       "      <td id=\"T_bc1a2_row43_col5\" class=\"data row43 col5\" >41</td>\n",
-       "      <td id=\"T_bc1a2_row43_col6\" class=\"data row43 col6\" >-3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row44\" class=\"row_heading level0 row44\" >Mistral-7B-Instruct-v0.2</th>\n",
-       "      <td id=\"T_bc1a2_row44_col0\" class=\"data row44 col0\" >1676</td>\n",
-       "      <td id=\"T_bc1a2_row44_col1\" class=\"data row44 col1\" >14.722773</td>\n",
-       "      <td id=\"T_bc1a2_row44_col2\" class=\"data row44 col2\" >17.503610</td>\n",
-       "      <td id=\"T_bc1a2_row44_col3\" class=\"data row44 col3\" >2.780837</td>\n",
-       "      <td id=\"T_bc1a2_row44_col4\" class=\"data row44 col4\" >31</td>\n",
-       "      <td id=\"T_bc1a2_row44_col5\" class=\"data row44 col5\" >51</td>\n",
-       "      <td id=\"T_bc1a2_row44_col6\" class=\"data row44 col6\" >-20</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row45\" class=\"row_heading level0 row45\" >evo-7b</th>\n",
-       "      <td id=\"T_bc1a2_row45_col0\" class=\"data row45 col0\" >1774</td>\n",
-       "      <td id=\"T_bc1a2_row45_col1\" class=\"data row45 col1\" >15.577437</td>\n",
-       "      <td id=\"T_bc1a2_row45_col2\" class=\"data row45 col2\" >17.702745</td>\n",
-       "      <td id=\"T_bc1a2_row45_col3\" class=\"data row45 col3\" >2.125307</td>\n",
-       "      <td id=\"T_bc1a2_row45_col4\" class=\"data row45 col4\" >30</td>\n",
-       "      <td id=\"T_bc1a2_row45_col5\" class=\"data row45 col5\" >50</td>\n",
-       "      <td id=\"T_bc1a2_row45_col6\" class=\"data row45 col6\" >-20</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row46\" class=\"row_heading level0 row46\" >humpback-llama2-70b</th>\n",
-       "      <td id=\"T_bc1a2_row46_col0\" class=\"data row46 col0\" >1107</td>\n",
-       "      <td id=\"T_bc1a2_row46_col1\" class=\"data row46 col1\" >10.121772</td>\n",
-       "      <td id=\"T_bc1a2_row46_col2\" class=\"data row46 col2\" >19.416493</td>\n",
-       "      <td id=\"T_bc1a2_row46_col3\" class=\"data row46 col3\" >9.294722</td>\n",
-       "      <td id=\"T_bc1a2_row46_col4\" class=\"data row46 col4\" >56</td>\n",
-       "      <td id=\"T_bc1a2_row46_col5\" class=\"data row46 col5\" >44</td>\n",
-       "      <td id=\"T_bc1a2_row46_col6\" class=\"data row46 col6\" >12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row47\" class=\"row_heading level0 row47\" >OpenHermes-2.5-Mistral-7B</th>\n",
-       "      <td id=\"T_bc1a2_row47_col0\" class=\"data row47 col0\" >1107</td>\n",
-       "      <td id=\"T_bc1a2_row47_col1\" class=\"data row47 col1\" >10.340416</td>\n",
-       "      <td id=\"T_bc1a2_row47_col2\" class=\"data row47 col2\" >16.352879</td>\n",
-       "      <td id=\"T_bc1a2_row47_col3\" class=\"data row47 col3\" >6.012464</td>\n",
-       "      <td id=\"T_bc1a2_row47_col4\" class=\"data row47 col4\" >55</td>\n",
-       "      <td id=\"T_bc1a2_row47_col5\" class=\"data row47 col5\" >57</td>\n",
-       "      <td id=\"T_bc1a2_row47_col6\" class=\"data row47 col6\" >-2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row48\" class=\"row_heading level0 row48\" >deita-7b-v1.0</th>\n",
-       "      <td id=\"T_bc1a2_row48_col0\" class=\"data row48 col0\" >1417</td>\n",
-       "      <td id=\"T_bc1a2_row48_col1\" class=\"data row48 col1\" >12.646639</td>\n",
-       "      <td id=\"T_bc1a2_row48_col2\" class=\"data row48 col2\" >19.855339</td>\n",
-       "      <td id=\"T_bc1a2_row48_col3\" class=\"data row48 col3\" >7.208699</td>\n",
-       "      <td id=\"T_bc1a2_row48_col4\" class=\"data row48 col4\" >45</td>\n",
-       "      <td id=\"T_bc1a2_row48_col5\" class=\"data row48 col5\" >42</td>\n",
-       "      <td id=\"T_bc1a2_row48_col6\" class=\"data row48 col6\" >3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row49\" class=\"row_heading level0 row49\" >jina-chat</th>\n",
-       "      <td id=\"T_bc1a2_row49_col0\" class=\"data row49 col0\" >676</td>\n",
-       "      <td id=\"T_bc1a2_row49_col1\" class=\"data row49 col1\" >7.786130</td>\n",
-       "      <td id=\"T_bc1a2_row49_col2\" class=\"data row49 col2\" >21.063020</td>\n",
-       "      <td id=\"T_bc1a2_row49_col3\" class=\"data row49 col3\" >13.276889</td>\n",
-       "      <td id=\"T_bc1a2_row49_col4\" class=\"data row49 col4\" >74</td>\n",
-       "      <td id=\"T_bc1a2_row49_col5\" class=\"data row49 col5\" >38</td>\n",
-       "      <td id=\"T_bc1a2_row49_col6\" class=\"data row49 col6\" >36</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row50\" class=\"row_heading level0 row50\" >gpt-3.5-turbo-1106_concise</th>\n",
-       "      <td id=\"T_bc1a2_row50_col0\" class=\"data row50 col0\" >431</td>\n",
-       "      <td id=\"T_bc1a2_row50_col1\" class=\"data row50 col1\" >7.415865</td>\n",
-       "      <td id=\"T_bc1a2_row50_col2\" class=\"data row50 col2\" >29.490736</td>\n",
-       "      <td id=\"T_bc1a2_row50_col3\" class=\"data row50 col3\" >22.074871</td>\n",
-       "      <td id=\"T_bc1a2_row50_col4\" class=\"data row50 col4\" >82</td>\n",
-       "      <td id=\"T_bc1a2_row50_col5\" class=\"data row50 col5\" >18</td>\n",
-       "      <td id=\"T_bc1a2_row50_col6\" class=\"data row50 col6\" >64</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row51\" class=\"row_heading level0 row51\" >causallm-14b</th>\n",
-       "      <td id=\"T_bc1a2_row51_col0\" class=\"data row51 col0\" >1391</td>\n",
-       "      <td id=\"T_bc1a2_row51_col1\" class=\"data row51 col1\" >11.146161</td>\n",
-       "      <td id=\"T_bc1a2_row51_col2\" class=\"data row51 col2\" >15.225911</td>\n",
-       "      <td id=\"T_bc1a2_row51_col3\" class=\"data row51 col3\" >4.079750</td>\n",
-       "      <td id=\"T_bc1a2_row51_col4\" class=\"data row51 col4\" >51</td>\n",
-       "      <td id=\"T_bc1a2_row51_col5\" class=\"data row51 col5\" >66</td>\n",
-       "      <td id=\"T_bc1a2_row51_col6\" class=\"data row51 col6\" >-15</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row52\" class=\"row_heading level0 row52\" >pairrm-zephyr-7b-beta</th>\n",
-       "      <td id=\"T_bc1a2_row52_col0\" class=\"data row52 col0\" >1487</td>\n",
-       "      <td id=\"T_bc1a2_row52_col1\" class=\"data row52 col1\" >12.841278</td>\n",
-       "      <td id=\"T_bc1a2_row52_col2\" class=\"data row52 col2\" >18.046105</td>\n",
-       "      <td id=\"T_bc1a2_row52_col3\" class=\"data row52 col3\" >5.204827</td>\n",
-       "      <td id=\"T_bc1a2_row52_col4\" class=\"data row52 col4\" >42</td>\n",
-       "      <td id=\"T_bc1a2_row52_col5\" class=\"data row52 col5\" >49</td>\n",
-       "      <td id=\"T_bc1a2_row52_col6\" class=\"data row52 col6\" >-7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row53\" class=\"row_heading level0 row53\" >Starling-LM-7B-alpha</th>\n",
-       "      <td id=\"T_bc1a2_row53_col0\" class=\"data row53 col0\" >1895</td>\n",
-       "      <td id=\"T_bc1a2_row53_col1\" class=\"data row53 col1\" >14.245924</td>\n",
-       "      <td id=\"T_bc1a2_row53_col2\" class=\"data row53 col2\" >15.838749</td>\n",
-       "      <td id=\"T_bc1a2_row53_col3\" class=\"data row53 col3\" >1.592826</td>\n",
-       "      <td id=\"T_bc1a2_row53_col4\" class=\"data row53 col4\" >33</td>\n",
-       "      <td id=\"T_bc1a2_row53_col5\" class=\"data row53 col5\" >59</td>\n",
-       "      <td id=\"T_bc1a2_row53_col6\" class=\"data row53 col6\" >-26</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row54\" class=\"row_heading level0 row54\" >llama-2-70b-chat-hf</th>\n",
-       "      <td id=\"T_bc1a2_row54_col0\" class=\"data row54 col0\" >1790</td>\n",
-       "      <td id=\"T_bc1a2_row54_col1\" class=\"data row54 col1\" >13.888258</td>\n",
-       "      <td id=\"T_bc1a2_row54_col2\" class=\"data row54 col2\" >16.317284</td>\n",
-       "      <td id=\"T_bc1a2_row54_col3\" class=\"data row54 col3\" >2.429026</td>\n",
-       "      <td id=\"T_bc1a2_row54_col4\" class=\"data row54 col4\" >36</td>\n",
-       "      <td id=\"T_bc1a2_row54_col5\" class=\"data row54 col5\" >58</td>\n",
-       "      <td id=\"T_bc1a2_row54_col6\" class=\"data row54 col6\" >-22</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row55\" class=\"row_heading level0 row55\" >openchat-v3.1-13b</th>\n",
-       "      <td id=\"T_bc1a2_row55_col0\" class=\"data row55 col0\" >1484</td>\n",
-       "      <td id=\"T_bc1a2_row55_col1\" class=\"data row55 col1\" >11.082230</td>\n",
-       "      <td id=\"T_bc1a2_row55_col2\" class=\"data row55 col2\" >16.885199</td>\n",
-       "      <td id=\"T_bc1a2_row55_col3\" class=\"data row55 col3\" >5.802969</td>\n",
-       "      <td id=\"T_bc1a2_row55_col4\" class=\"data row55 col4\" >52</td>\n",
-       "      <td id=\"T_bc1a2_row55_col5\" class=\"data row55 col5\" >52</td>\n",
-       "      <td id=\"T_bc1a2_row55_col6\" class=\"data row55 col6\" >0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row56\" class=\"row_heading level0 row56\" >wizardlm-13b-v1.2</th>\n",
-       "      <td id=\"T_bc1a2_row56_col0\" class=\"data row56 col0\" >1635</td>\n",
-       "      <td id=\"T_bc1a2_row56_col1\" class=\"data row56 col1\" >12.027480</td>\n",
-       "      <td id=\"T_bc1a2_row56_col2\" class=\"data row56 col2\" >15.578715</td>\n",
-       "      <td id=\"T_bc1a2_row56_col3\" class=\"data row56 col3\" >3.551234</td>\n",
-       "      <td id=\"T_bc1a2_row56_col4\" class=\"data row56 col4\" >47</td>\n",
-       "      <td id=\"T_bc1a2_row56_col5\" class=\"data row56 col5\" >62</td>\n",
-       "      <td id=\"T_bc1a2_row56_col6\" class=\"data row56 col6\" >-15</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row57\" class=\"row_heading level0 row57\" >ultralm-13b-v2.0-best-of-16</th>\n",
-       "      <td id=\"T_bc1a2_row57_col0\" class=\"data row57 col0\" >1720</td>\n",
-       "      <td id=\"T_bc1a2_row57_col1\" class=\"data row57 col1\" >13.853373</td>\n",
-       "      <td id=\"T_bc1a2_row57_col2\" class=\"data row57 col2\" >16.749030</td>\n",
-       "      <td id=\"T_bc1a2_row57_col3\" class=\"data row57 col3\" >2.895657</td>\n",
-       "      <td id=\"T_bc1a2_row57_col4\" class=\"data row57 col4\" >37</td>\n",
-       "      <td id=\"T_bc1a2_row57_col5\" class=\"data row57 col5\" >53</td>\n",
-       "      <td id=\"T_bc1a2_row57_col6\" class=\"data row57 col6\" >-16</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row58\" class=\"row_heading level0 row58\" >wizardlm-13b-v1.1</th>\n",
-       "      <td id=\"T_bc1a2_row58_col0\" class=\"data row58 col0\" >1525</td>\n",
-       "      <td id=\"T_bc1a2_row58_col1\" class=\"data row58 col1\" >11.233910</td>\n",
-       "      <td id=\"T_bc1a2_row58_col2\" class=\"data row58 col2\" >15.777430</td>\n",
-       "      <td id=\"T_bc1a2_row58_col3\" class=\"data row58 col3\" >4.543520</td>\n",
-       "      <td id=\"T_bc1a2_row58_col4\" class=\"data row58 col4\" >50</td>\n",
-       "      <td id=\"T_bc1a2_row58_col5\" class=\"data row58 col5\" >60</td>\n",
-       "      <td id=\"T_bc1a2_row58_col6\" class=\"data row58 col6\" >-10</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row59\" class=\"row_heading level0 row59\" >zephyr-7b-beta</th>\n",
-       "      <td id=\"T_bc1a2_row59_col0\" class=\"data row59 col0\" >1444</td>\n",
-       "      <td id=\"T_bc1a2_row59_col1\" class=\"data row59 col1\" >10.992886</td>\n",
-       "      <td id=\"T_bc1a2_row59_col2\" class=\"data row59 col2\" >14.824691</td>\n",
-       "      <td id=\"T_bc1a2_row59_col3\" class=\"data row59 col3\" >3.831805</td>\n",
-       "      <td id=\"T_bc1a2_row59_col4\" class=\"data row59 col4\" >53</td>\n",
-       "      <td id=\"T_bc1a2_row59_col5\" class=\"data row59 col5\" >68</td>\n",
-       "      <td id=\"T_bc1a2_row59_col6\" class=\"data row59 col6\" >-15</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row60\" class=\"row_heading level0 row60\" >dolphin-2.2.1-mistral-7b</th>\n",
-       "      <td id=\"T_bc1a2_row60_col0\" class=\"data row60 col0\" >1130</td>\n",
-       "      <td id=\"T_bc1a2_row60_col1\" class=\"data row60 col1\" >9.039800</td>\n",
-       "      <td id=\"T_bc1a2_row60_col2\" class=\"data row60 col2\" >13.974427</td>\n",
-       "      <td id=\"T_bc1a2_row60_col3\" class=\"data row60 col3\" >4.934628</td>\n",
-       "      <td id=\"T_bc1a2_row60_col4\" class=\"data row60 col4\" >66</td>\n",
-       "      <td id=\"T_bc1a2_row60_col5\" class=\"data row60 col5\" >73</td>\n",
-       "      <td id=\"T_bc1a2_row60_col6\" class=\"data row60 col6\" >-7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row61\" class=\"row_heading level0 row61\" >humpback-llama-65b</th>\n",
-       "      <td id=\"T_bc1a2_row61_col0\" class=\"data row61 col0\" >1232</td>\n",
-       "      <td id=\"T_bc1a2_row61_col1\" class=\"data row61 col1\" >9.425139</td>\n",
-       "      <td id=\"T_bc1a2_row61_col2\" class=\"data row61 col2\" >15.277149</td>\n",
-       "      <td id=\"T_bc1a2_row61_col3\" class=\"data row61 col3\" >5.852010</td>\n",
-       "      <td id=\"T_bc1a2_row61_col4\" class=\"data row61 col4\" >60</td>\n",
-       "      <td id=\"T_bc1a2_row61_col5\" class=\"data row61 col5\" >65</td>\n",
-       "      <td id=\"T_bc1a2_row61_col6\" class=\"data row61 col6\" >-5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row62\" class=\"row_heading level0 row62\" >openbuddy-llama2-70b-v10.1</th>\n",
-       "      <td id=\"T_bc1a2_row62_col0\" class=\"data row62 col0\" >1077</td>\n",
-       "      <td id=\"T_bc1a2_row62_col1\" class=\"data row62 col1\" >8.096422</td>\n",
-       "      <td id=\"T_bc1a2_row62_col2\" class=\"data row62 col2\" >13.879050</td>\n",
-       "      <td id=\"T_bc1a2_row62_col3\" class=\"data row62 col3\" >5.782628</td>\n",
-       "      <td id=\"T_bc1a2_row62_col4\" class=\"data row62 col4\" >72</td>\n",
-       "      <td id=\"T_bc1a2_row62_col5\" class=\"data row62 col5\" >74</td>\n",
-       "      <td id=\"T_bc1a2_row62_col6\" class=\"data row62 col6\" >-2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row63\" class=\"row_heading level0 row63\" >openbuddy-llama-65b-v8</th>\n",
-       "      <td id=\"T_bc1a2_row63_col0\" class=\"data row63 col0\" >1162</td>\n",
-       "      <td id=\"T_bc1a2_row63_col1\" class=\"data row63 col1\" >8.770650</td>\n",
-       "      <td id=\"T_bc1a2_row63_col2\" class=\"data row63 col2\" >16.487347</td>\n",
-       "      <td id=\"T_bc1a2_row63_col3\" class=\"data row63 col3\" >7.716697</td>\n",
-       "      <td id=\"T_bc1a2_row63_col4\" class=\"data row63 col4\" >67</td>\n",
-       "      <td id=\"T_bc1a2_row63_col5\" class=\"data row63 col5\" >55</td>\n",
-       "      <td id=\"T_bc1a2_row63_col6\" class=\"data row63 col6\" >12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row64\" class=\"row_heading level0 row64\" >Qwen-14B-Chat</th>\n",
-       "      <td id=\"T_bc1a2_row64_col0\" class=\"data row64 col0\" >1013</td>\n",
-       "      <td id=\"T_bc1a2_row64_col1\" class=\"data row64 col1\" >7.502333</td>\n",
-       "      <td id=\"T_bc1a2_row64_col2\" class=\"data row64 col2\" >19.464203</td>\n",
-       "      <td id=\"T_bc1a2_row64_col3\" class=\"data row64 col3\" >11.961870</td>\n",
-       "      <td id=\"T_bc1a2_row64_col4\" class=\"data row64 col4\" >79</td>\n",
-       "      <td id=\"T_bc1a2_row64_col5\" class=\"data row64 col5\" >43</td>\n",
-       "      <td id=\"T_bc1a2_row64_col6\" class=\"data row64 col6\" >36</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row65\" class=\"row_heading level0 row65\" >gpt4_gamed</th>\n",
-       "      <td id=\"T_bc1a2_row65_col0\" class=\"data row65 col0\" >68</td>\n",
-       "      <td id=\"T_bc1a2_row65_col1\" class=\"data row65 col1\" >3.738337</td>\n",
-       "      <td id=\"T_bc1a2_row65_col2\" class=\"data row65 col2\" >44.532377</td>\n",
-       "      <td id=\"T_bc1a2_row65_col3\" class=\"data row65 col3\" >40.794040</td>\n",
-       "      <td id=\"T_bc1a2_row65_col4\" class=\"data row65 col4\" >110</td>\n",
-       "      <td id=\"T_bc1a2_row65_col5\" class=\"data row65 col5\" >2</td>\n",
-       "      <td id=\"T_bc1a2_row65_col6\" class=\"data row65 col6\" >108</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row66\" class=\"row_heading level0 row66\" >cut-13b</th>\n",
-       "      <td id=\"T_bc1a2_row66_col0\" class=\"data row66 col0\" >1637</td>\n",
-       "      <td id=\"T_bc1a2_row66_col1\" class=\"data row66 col1\" >10.779089</td>\n",
-       "      <td id=\"T_bc1a2_row66_col2\" class=\"data row66 col2\" >14.074431</td>\n",
-       "      <td id=\"T_bc1a2_row66_col3\" class=\"data row66 col3\" >3.295342</td>\n",
-       "      <td id=\"T_bc1a2_row66_col4\" class=\"data row66 col4\" >54</td>\n",
-       "      <td id=\"T_bc1a2_row66_col5\" class=\"data row66 col5\" >72</td>\n",
-       "      <td id=\"T_bc1a2_row66_col6\" class=\"data row66 col6\" >-18</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row67\" class=\"row_heading level0 row67\" >openchat-v2-w-13b</th>\n",
-       "      <td id=\"T_bc1a2_row67_col0\" class=\"data row67 col0\" >1566</td>\n",
-       "      <td id=\"T_bc1a2_row67_col1\" class=\"data row67 col1\" >9.615344</td>\n",
-       "      <td id=\"T_bc1a2_row67_col2\" class=\"data row67 col2\" >14.106426</td>\n",
-       "      <td id=\"T_bc1a2_row67_col3\" class=\"data row67 col3\" >4.491082</td>\n",
-       "      <td id=\"T_bc1a2_row67_col4\" class=\"data row67 col4\" >59</td>\n",
-       "      <td id=\"T_bc1a2_row67_col5\" class=\"data row67 col5\" >71</td>\n",
-       "      <td id=\"T_bc1a2_row67_col6\" class=\"data row67 col6\" >-12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row68\" class=\"row_heading level0 row68\" >tulu-2-dpo-13b</th>\n",
-       "      <td id=\"T_bc1a2_row68_col0\" class=\"data row68 col0\" >1614</td>\n",
-       "      <td id=\"T_bc1a2_row68_col1\" class=\"data row68 col1\" >10.119788</td>\n",
-       "      <td id=\"T_bc1a2_row68_col2\" class=\"data row68 col2\" >15.521773</td>\n",
-       "      <td id=\"T_bc1a2_row68_col3\" class=\"data row68 col3\" >5.401985</td>\n",
-       "      <td id=\"T_bc1a2_row68_col4\" class=\"data row68 col4\" >57</td>\n",
-       "      <td id=\"T_bc1a2_row68_col5\" class=\"data row68 col5\" >63</td>\n",
-       "      <td id=\"T_bc1a2_row68_col6\" class=\"data row68 col6\" >-6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row69\" class=\"row_heading level0 row69\" >claude2-alpaca-13b</th>\n",
-       "      <td id=\"T_bc1a2_row69_col0\" class=\"data row69 col0\" >1127</td>\n",
-       "      <td id=\"T_bc1a2_row69_col1\" class=\"data row69 col1\" >7.437351</td>\n",
-       "      <td id=\"T_bc1a2_row69_col2\" class=\"data row69 col2\" >16.733107</td>\n",
-       "      <td id=\"T_bc1a2_row69_col3\" class=\"data row69 col3\" >9.295755</td>\n",
-       "      <td id=\"T_bc1a2_row69_col4\" class=\"data row69 col4\" >81</td>\n",
-       "      <td id=\"T_bc1a2_row69_col5\" class=\"data row69 col5\" >54</td>\n",
-       "      <td id=\"T_bc1a2_row69_col6\" class=\"data row69 col6\" >27</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row70\" class=\"row_heading level0 row70\" >minotaur-13b</th>\n",
-       "      <td id=\"T_bc1a2_row70_col0\" class=\"data row70 col0\" >881</td>\n",
-       "      <td id=\"T_bc1a2_row70_col1\" class=\"data row70 col1\" >5.738964</td>\n",
-       "      <td id=\"T_bc1a2_row70_col2\" class=\"data row70 col2\" >16.471708</td>\n",
-       "      <td id=\"T_bc1a2_row70_col3\" class=\"data row70 col3\" >10.732744</td>\n",
-       "      <td id=\"T_bc1a2_row70_col4\" class=\"data row70 col4\" >98</td>\n",
-       "      <td id=\"T_bc1a2_row70_col5\" class=\"data row70 col5\" >56</td>\n",
-       "      <td id=\"T_bc1a2_row70_col6\" class=\"data row70 col6\" >42</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row71\" class=\"row_heading level0 row71\" >airoboros-65b</th>\n",
-       "      <td id=\"T_bc1a2_row71_col0\" class=\"data row71 col0\" >1512</td>\n",
-       "      <td id=\"T_bc1a2_row71_col1\" class=\"data row71 col1\" >9.388950</td>\n",
-       "      <td id=\"T_bc1a2_row71_col2\" class=\"data row71 col2\" >13.035846</td>\n",
-       "      <td id=\"T_bc1a2_row71_col3\" class=\"data row71 col3\" >3.646896</td>\n",
-       "      <td id=\"T_bc1a2_row71_col4\" class=\"data row71 col4\" >62</td>\n",
-       "      <td id=\"T_bc1a2_row71_col5\" class=\"data row71 col5\" >81</td>\n",
-       "      <td id=\"T_bc1a2_row71_col6\" class=\"data row71 col6\" >-19</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row72\" class=\"row_heading level0 row72\" >cohere</th>\n",
-       "      <td id=\"T_bc1a2_row72_col0\" class=\"data row72 col0\" >1983</td>\n",
-       "      <td id=\"T_bc1a2_row72_col1\" class=\"data row72 col1\" >12.901455</td>\n",
-       "      <td id=\"T_bc1a2_row72_col2\" class=\"data row72 col2\" >13.147459</td>\n",
-       "      <td id=\"T_bc1a2_row72_col3\" class=\"data row72 col3\" >0.246004</td>\n",
-       "      <td id=\"T_bc1a2_row72_col4\" class=\"data row72 col4\" >41</td>\n",
-       "      <td id=\"T_bc1a2_row72_col5\" class=\"data row72 col5\" >79</td>\n",
-       "      <td id=\"T_bc1a2_row72_col6\" class=\"data row72 col6\" >-38</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row73\" class=\"row_heading level0 row73\" >vicuna-13b-v1.3</th>\n",
-       "      <td id=\"T_bc1a2_row73_col0\" class=\"data row73 col0\" >1132</td>\n",
-       "      <td id=\"T_bc1a2_row73_col1\" class=\"data row73 col1\" >7.137240</td>\n",
-       "      <td id=\"T_bc1a2_row73_col2\" class=\"data row73 col2\" >14.467847</td>\n",
-       "      <td id=\"T_bc1a2_row73_col3\" class=\"data row73 col3\" >7.330607</td>\n",
-       "      <td id=\"T_bc1a2_row73_col4\" class=\"data row73 col4\" >85</td>\n",
-       "      <td id=\"T_bc1a2_row73_col5\" class=\"data row73 col5\" >70</td>\n",
-       "      <td id=\"T_bc1a2_row73_col6\" class=\"data row73 col6\" >15</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row74\" class=\"row_heading level0 row74\" >xwinlm-7b-v0.1</th>\n",
-       "      <td id=\"T_bc1a2_row74_col0\" class=\"data row74 col0\" >1894</td>\n",
-       "      <td id=\"T_bc1a2_row74_col1\" class=\"data row74 col1\" >11.245652</td>\n",
-       "      <td id=\"T_bc1a2_row74_col2\" class=\"data row74 col2\" >12.644308</td>\n",
-       "      <td id=\"T_bc1a2_row74_col3\" class=\"data row74 col3\" >1.398656</td>\n",
-       "      <td id=\"T_bc1a2_row74_col4\" class=\"data row74 col4\" >49</td>\n",
-       "      <td id=\"T_bc1a2_row74_col5\" class=\"data row74 col5\" >84</td>\n",
-       "      <td id=\"T_bc1a2_row74_col6\" class=\"data row74 col6\" >-35</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row75\" class=\"row_heading level0 row75\" >airoboros-33b</th>\n",
-       "      <td id=\"T_bc1a2_row75_col0\" class=\"data row75 col0\" >1514</td>\n",
-       "      <td id=\"T_bc1a2_row75_col1\" class=\"data row75 col1\" >9.053160</td>\n",
-       "      <td id=\"T_bc1a2_row75_col2\" class=\"data row75 col2\" >12.840199</td>\n",
-       "      <td id=\"T_bc1a2_row75_col3\" class=\"data row75 col3\" >3.787039</td>\n",
-       "      <td id=\"T_bc1a2_row75_col4\" class=\"data row75 col4\" >65</td>\n",
-       "      <td id=\"T_bc1a2_row75_col5\" class=\"data row75 col5\" >82</td>\n",
-       "      <td id=\"T_bc1a2_row75_col6\" class=\"data row75 col6\" >-17</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row76\" class=\"row_heading level0 row76\" >platolm-7b</th>\n",
-       "      <td id=\"T_bc1a2_row76_col0\" class=\"data row76 col0\" >1344</td>\n",
-       "      <td id=\"T_bc1a2_row76_col1\" class=\"data row76 col1\" >6.320828</td>\n",
-       "      <td id=\"T_bc1a2_row76_col2\" class=\"data row76 col2\" >11.443269</td>\n",
-       "      <td id=\"T_bc1a2_row76_col3\" class=\"data row76 col3\" >5.122441</td>\n",
-       "      <td id=\"T_bc1a2_row76_col4\" class=\"data row76 col4\" >91</td>\n",
-       "      <td id=\"T_bc1a2_row76_col5\" class=\"data row76 col5\" >93</td>\n",
-       "      <td id=\"T_bc1a2_row76_col6\" class=\"data row76 col6\" >-2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row77\" class=\"row_heading level0 row77\" >vicuna-13b-v1.5</th>\n",
-       "      <td id=\"T_bc1a2_row77_col0\" class=\"data row77 col0\" >1061</td>\n",
-       "      <td id=\"T_bc1a2_row77_col1\" class=\"data row77 col1\" >6.722122</td>\n",
-       "      <td id=\"T_bc1a2_row77_col2\" class=\"data row77 col2\" >9.559231</td>\n",
-       "      <td id=\"T_bc1a2_row77_col3\" class=\"data row77 col3\" >2.837109</td>\n",
-       "      <td id=\"T_bc1a2_row77_col4\" class=\"data row77 col4\" >88</td>\n",
-       "      <td id=\"T_bc1a2_row77_col5\" class=\"data row77 col5\" >104</td>\n",
-       "      <td id=\"T_bc1a2_row77_col6\" class=\"data row77 col6\" >-16</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row78\" class=\"row_heading level0 row78\" >gemma-7b-it</th>\n",
-       "      <td id=\"T_bc1a2_row78_col0\" class=\"data row78 col0\" >1115</td>\n",
-       "      <td id=\"T_bc1a2_row78_col1\" class=\"data row78 col1\" >6.937294</td>\n",
-       "      <td id=\"T_bc1a2_row78_col2\" class=\"data row78 col2\" >13.780013</td>\n",
-       "      <td id=\"T_bc1a2_row78_col3\" class=\"data row78 col3\" >6.842719</td>\n",
-       "      <td id=\"T_bc1a2_row78_col4\" class=\"data row78 col4\" >86</td>\n",
-       "      <td id=\"T_bc1a2_row78_col5\" class=\"data row78 col5\" >76</td>\n",
-       "      <td id=\"T_bc1a2_row78_col6\" class=\"data row78 col6\" >10</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row79\" class=\"row_heading level0 row79\" >openchat-v2-13b</th>\n",
-       "      <td id=\"T_bc1a2_row79_col0\" class=\"data row79 col0\" >1564</td>\n",
-       "      <td id=\"T_bc1a2_row79_col1\" class=\"data row79 col1\" >8.435076</td>\n",
-       "      <td id=\"T_bc1a2_row79_col2\" class=\"data row79 col2\" >10.921402</td>\n",
-       "      <td id=\"T_bc1a2_row79_col3\" class=\"data row79 col3\" >2.486326</td>\n",
-       "      <td id=\"T_bc1a2_row79_col4\" class=\"data row79 col4\" >69</td>\n",
-       "      <td id=\"T_bc1a2_row79_col5\" class=\"data row79 col5\" >94</td>\n",
-       "      <td id=\"T_bc1a2_row79_col6\" class=\"data row79 col6\" >-25</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row80\" class=\"row_heading level0 row80\" >zephyr-7b-alpha</th>\n",
-       "      <td id=\"T_bc1a2_row80_col0\" class=\"data row80 col0\" >1302</td>\n",
-       "      <td id=\"T_bc1a2_row80_col1\" class=\"data row80 col1\" >8.352664</td>\n",
-       "      <td id=\"T_bc1a2_row80_col2\" class=\"data row80 col2\" >12.315627</td>\n",
-       "      <td id=\"T_bc1a2_row80_col3\" class=\"data row80 col3\" >3.962963</td>\n",
-       "      <td id=\"T_bc1a2_row80_col4\" class=\"data row80 col4\" >70</td>\n",
-       "      <td id=\"T_bc1a2_row80_col5\" class=\"data row80 col5\" >86</td>\n",
-       "      <td id=\"T_bc1a2_row80_col6\" class=\"data row80 col6\" >-16</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row81\" class=\"row_heading level0 row81\" >openbuddy-llama-30b-v7.1</th>\n",
-       "      <td id=\"T_bc1a2_row81_col0\" class=\"data row81 col0\" >968</td>\n",
-       "      <td id=\"T_bc1a2_row81_col1\" class=\"data row81 col1\" >6.130015</td>\n",
-       "      <td id=\"T_bc1a2_row81_col2\" class=\"data row81 col2\" >13.506367</td>\n",
-       "      <td id=\"T_bc1a2_row81_col3\" class=\"data row81 col3\" >7.376352</td>\n",
-       "      <td id=\"T_bc1a2_row81_col4\" class=\"data row81 col4\" >94</td>\n",
-       "      <td id=\"T_bc1a2_row81_col5\" class=\"data row81 col5\" >77</td>\n",
-       "      <td id=\"T_bc1a2_row81_col6\" class=\"data row81 col6\" >17</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row82\" class=\"row_heading level0 row82\" >ultralm-13b-best-of-16</th>\n",
-       "      <td id=\"T_bc1a2_row82_col0\" class=\"data row82 col0\" >1980</td>\n",
-       "      <td id=\"T_bc1a2_row82_col1\" class=\"data row82 col1\" >11.307315</td>\n",
-       "      <td id=\"T_bc1a2_row82_col2\" class=\"data row82 col2\" >12.037139</td>\n",
-       "      <td id=\"T_bc1a2_row82_col3\" class=\"data row82 col3\" >0.729824</td>\n",
-       "      <td id=\"T_bc1a2_row82_col4\" class=\"data row82 col4\" >48</td>\n",
-       "      <td id=\"T_bc1a2_row82_col5\" class=\"data row82 col5\" >88</td>\n",
-       "      <td id=\"T_bc1a2_row82_col6\" class=\"data row82 col6\" >-40</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row83\" class=\"row_heading level0 row83\" >oasst-sft-llama-33b</th>\n",
-       "      <td id=\"T_bc1a2_row83_col0\" class=\"data row83 col0\" >748</td>\n",
-       "      <td id=\"T_bc1a2_row83_col1\" class=\"data row83 col1\" >4.770391</td>\n",
-       "      <td id=\"T_bc1a2_row83_col2\" class=\"data row83 col2\" >12.742207</td>\n",
-       "      <td id=\"T_bc1a2_row83_col3\" class=\"data row83 col3\" >7.971816</td>\n",
-       "      <td id=\"T_bc1a2_row83_col4\" class=\"data row83 col4\" >104</td>\n",
-       "      <td id=\"T_bc1a2_row83_col5\" class=\"data row83 col5\" >83</td>\n",
-       "      <td id=\"T_bc1a2_row83_col6\" class=\"data row83 col6\" >21</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row84\" class=\"row_heading level0 row84\" >wizardlm-13b</th>\n",
-       "      <td id=\"T_bc1a2_row84_col0\" class=\"data row84 col0\" >985</td>\n",
-       "      <td id=\"T_bc1a2_row84_col1\" class=\"data row84 col1\" >5.878153</td>\n",
-       "      <td id=\"T_bc1a2_row84_col2\" class=\"data row84 col2\" >13.845511</td>\n",
-       "      <td id=\"T_bc1a2_row84_col3\" class=\"data row84 col3\" >7.967358</td>\n",
-       "      <td id=\"T_bc1a2_row84_col4\" class=\"data row84 col4\" >96</td>\n",
-       "      <td id=\"T_bc1a2_row84_col5\" class=\"data row84 col5\" >75</td>\n",
-       "      <td id=\"T_bc1a2_row84_col6\" class=\"data row84 col6\" >21</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row85\" class=\"row_heading level0 row85\" >nous-hermes-13b</th>\n",
-       "      <td id=\"T_bc1a2_row85_col0\" class=\"data row85 col0\" >844</td>\n",
-       "      <td id=\"T_bc1a2_row85_col1\" class=\"data row85 col1\" >5.411879</td>\n",
-       "      <td id=\"T_bc1a2_row85_col2\" class=\"data row85 col2\" >14.553850</td>\n",
-       "      <td id=\"T_bc1a2_row85_col3\" class=\"data row85 col3\" >9.141971</td>\n",
-       "      <td id=\"T_bc1a2_row85_col4\" class=\"data row85 col4\" >99</td>\n",
-       "      <td id=\"T_bc1a2_row85_col5\" class=\"data row85 col5\" >69</td>\n",
-       "      <td id=\"T_bc1a2_row85_col6\" class=\"data row85 col6\" >30</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row86\" class=\"row_heading level0 row86\" >vicuna-13b</th>\n",
-       "      <td id=\"T_bc1a2_row86_col0\" class=\"data row86 col0\" >1037</td>\n",
-       "      <td id=\"T_bc1a2_row86_col1\" class=\"data row86 col1\" >5.831103</td>\n",
-       "      <td id=\"T_bc1a2_row86_col2\" class=\"data row86 col2\" >12.121340</td>\n",
-       "      <td id=\"T_bc1a2_row86_col3\" class=\"data row86 col3\" >6.290237</td>\n",
-       "      <td id=\"T_bc1a2_row86_col4\" class=\"data row86 col4\" >97</td>\n",
-       "      <td id=\"T_bc1a2_row86_col5\" class=\"data row86 col5\" >87</td>\n",
-       "      <td id=\"T_bc1a2_row86_col6\" class=\"data row86 col6\" >10</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row87\" class=\"row_heading level0 row87\" >tulu-2-dpo-7b</th>\n",
-       "      <td id=\"T_bc1a2_row87_col0\" class=\"data row87 col0\" >1663</td>\n",
-       "      <td id=\"T_bc1a2_row87_col1\" class=\"data row87 col1\" >8.197515</td>\n",
-       "      <td id=\"T_bc1a2_row87_col2\" class=\"data row87 col2\" >13.475569</td>\n",
-       "      <td id=\"T_bc1a2_row87_col3\" class=\"data row87 col3\" >5.278053</td>\n",
-       "      <td id=\"T_bc1a2_row87_col4\" class=\"data row87 col4\" >71</td>\n",
-       "      <td id=\"T_bc1a2_row87_col5\" class=\"data row87 col5\" >78</td>\n",
-       "      <td id=\"T_bc1a2_row87_col6\" class=\"data row87 col6\" >-7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row88\" class=\"row_heading level0 row88\" >openbuddy-llama2-13b-v11.1</th>\n",
-       "      <td id=\"T_bc1a2_row88_col0\" class=\"data row88 col0\" >1057</td>\n",
-       "      <td id=\"T_bc1a2_row88_col1\" class=\"data row88 col1\" >6.174716</td>\n",
-       "      <td id=\"T_bc1a2_row88_col2\" class=\"data row88 col2\" >15.665046</td>\n",
-       "      <td id=\"T_bc1a2_row88_col3\" class=\"data row88 col3\" >9.490330</td>\n",
-       "      <td id=\"T_bc1a2_row88_col4\" class=\"data row88 col4\" >93</td>\n",
-       "      <td id=\"T_bc1a2_row88_col5\" class=\"data row88 col5\" >61</td>\n",
-       "      <td id=\"T_bc1a2_row88_col6\" class=\"data row88 col6\" >32</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row89\" class=\"row_heading level0 row89\" >ultralm-13b-v2.0</th>\n",
-       "      <td id=\"T_bc1a2_row89_col0\" class=\"data row89 col0\" >1399</td>\n",
-       "      <td id=\"T_bc1a2_row89_col1\" class=\"data row89 col1\" >7.504623</td>\n",
-       "      <td id=\"T_bc1a2_row89_col2\" class=\"data row89 col2\" >12.353613</td>\n",
-       "      <td id=\"T_bc1a2_row89_col3\" class=\"data row89 col3\" >4.848990</td>\n",
-       "      <td id=\"T_bc1a2_row89_col4\" class=\"data row89 col4\" >78</td>\n",
-       "      <td id=\"T_bc1a2_row89_col5\" class=\"data row89 col5\" >85</td>\n",
-       "      <td id=\"T_bc1a2_row89_col6\" class=\"data row89 col6\" >-7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row90\" class=\"row_heading level0 row90\" >text_davinci_001</th>\n",
-       "      <td id=\"T_bc1a2_row90_col0\" class=\"data row90 col0\" >296</td>\n",
-       "      <td id=\"T_bc1a2_row90_col1\" class=\"data row90 col1\" >2.764005</td>\n",
-       "      <td id=\"T_bc1a2_row90_col2\" class=\"data row90 col2\" >8.565768</td>\n",
-       "      <td id=\"T_bc1a2_row90_col3\" class=\"data row90 col3\" >5.801762</td>\n",
-       "      <td id=\"T_bc1a2_row90_col4\" class=\"data row90 col4\" >120</td>\n",
-       "      <td id=\"T_bc1a2_row90_col5\" class=\"data row90 col5\" >109</td>\n",
-       "      <td id=\"T_bc1a2_row90_col6\" class=\"data row90 col6\" >11</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row91\" class=\"row_heading level0 row91\" >openbuddy-falcon-40b-v9</th>\n",
-       "      <td id=\"T_bc1a2_row91_col0\" class=\"data row91 col0\" >1089</td>\n",
-       "      <td id=\"T_bc1a2_row91_col1\" class=\"data row91 col1\" >5.955743</td>\n",
-       "      <td id=\"T_bc1a2_row91_col2\" class=\"data row91 col2\" >13.140887</td>\n",
-       "      <td id=\"T_bc1a2_row91_col3\" class=\"data row91 col3\" >7.185144</td>\n",
-       "      <td id=\"T_bc1a2_row91_col4\" class=\"data row91 col4\" >95</td>\n",
-       "      <td id=\"T_bc1a2_row91_col5\" class=\"data row91 col5\" >80</td>\n",
-       "      <td id=\"T_bc1a2_row91_col6\" class=\"data row91 col6\" >15</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row92\" class=\"row_heading level0 row92\" >openchat-13b</th>\n",
-       "      <td id=\"T_bc1a2_row92_col0\" class=\"data row92 col0\" >1632</td>\n",
-       "      <td id=\"T_bc1a2_row92_col1\" class=\"data row92 col1\" >8.022386</td>\n",
-       "      <td id=\"T_bc1a2_row92_col2\" class=\"data row92 col2\" >10.899403</td>\n",
-       "      <td id=\"T_bc1a2_row92_col3\" class=\"data row92 col3\" >2.877017</td>\n",
-       "      <td id=\"T_bc1a2_row92_col4\" class=\"data row92 col4\" >73</td>\n",
-       "      <td id=\"T_bc1a2_row92_col5\" class=\"data row92 col5\" >95</td>\n",
-       "      <td id=\"T_bc1a2_row92_col6\" class=\"data row92 col6\" >-22</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row93\" class=\"row_heading level0 row93\" >llama-2-13b-chat-hf</th>\n",
-       "      <td id=\"T_bc1a2_row93_col0\" class=\"data row93 col0\" >1513</td>\n",
-       "      <td id=\"T_bc1a2_row93_col1\" class=\"data row93 col1\" >7.702310</td>\n",
-       "      <td id=\"T_bc1a2_row93_col2\" class=\"data row93 col2\" >11.844717</td>\n",
-       "      <td id=\"T_bc1a2_row93_col3\" class=\"data row93 col3\" >4.142407</td>\n",
-       "      <td id=\"T_bc1a2_row93_col4\" class=\"data row93 col4\" >76</td>\n",
-       "      <td id=\"T_bc1a2_row93_col5\" class=\"data row93 col5\" >89</td>\n",
-       "      <td id=\"T_bc1a2_row93_col6\" class=\"data row93 col6\" >-13</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row94\" class=\"row_heading level0 row94\" >guanaco-65b</th>\n",
-       "      <td id=\"T_bc1a2_row94_col0\" class=\"data row94 col0\" >1249</td>\n",
-       "      <td id=\"T_bc1a2_row94_col1\" class=\"data row94 col1\" >6.858495</td>\n",
-       "      <td id=\"T_bc1a2_row94_col2\" class=\"data row94 col2\" >11.653236</td>\n",
-       "      <td id=\"T_bc1a2_row94_col3\" class=\"data row94 col3\" >4.794742</td>\n",
-       "      <td id=\"T_bc1a2_row94_col4\" class=\"data row94 col4\" >87</td>\n",
-       "      <td id=\"T_bc1a2_row94_col5\" class=\"data row94 col5\" >90</td>\n",
-       "      <td id=\"T_bc1a2_row94_col6\" class=\"data row94 col6\" >-3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row95\" class=\"row_heading level0 row95\" >opencoderplus-15b</th>\n",
-       "      <td id=\"T_bc1a2_row95_col0\" class=\"data row95 col0\" >1628</td>\n",
-       "      <td id=\"T_bc1a2_row95_col1\" class=\"data row95 col1\" >7.406222</td>\n",
-       "      <td id=\"T_bc1a2_row95_col2\" class=\"data row95 col2\" >9.927700</td>\n",
-       "      <td id=\"T_bc1a2_row95_col3\" class=\"data row95 col3\" >2.521477</td>\n",
-       "      <td id=\"T_bc1a2_row95_col4\" class=\"data row95 col4\" >83</td>\n",
-       "      <td id=\"T_bc1a2_row95_col5\" class=\"data row95 col5\" >101</td>\n",
-       "      <td id=\"T_bc1a2_row95_col6\" class=\"data row95 col6\" >-18</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row96\" class=\"row_heading level0 row96\" >oasst-rlhf-llama-33b</th>\n",
-       "      <td id=\"T_bc1a2_row96_col0\" class=\"data row96 col0\" >1079</td>\n",
-       "      <td id=\"T_bc1a2_row96_col1\" class=\"data row96 col1\" >6.296435</td>\n",
-       "      <td id=\"T_bc1a2_row96_col2\" class=\"data row96 col2\" >10.199504</td>\n",
-       "      <td id=\"T_bc1a2_row96_col3\" class=\"data row96 col3\" >3.903069</td>\n",
-       "      <td id=\"T_bc1a2_row96_col4\" class=\"data row96 col4\" >92</td>\n",
-       "      <td id=\"T_bc1a2_row96_col5\" class=\"data row96 col5\" >98</td>\n",
-       "      <td id=\"T_bc1a2_row96_col6\" class=\"data row96 col6\" >-6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row97\" class=\"row_heading level0 row97\" >openchat8192-13b</th>\n",
-       "      <td id=\"T_bc1a2_row97_col0\" class=\"data row97 col0\" >1664</td>\n",
-       "      <td id=\"T_bc1a2_row97_col1\" class=\"data row97 col1\" >7.472767</td>\n",
-       "      <td id=\"T_bc1a2_row97_col2\" class=\"data row97 col2\" >9.674293</td>\n",
-       "      <td id=\"T_bc1a2_row97_col3\" class=\"data row97 col3\" >2.201526</td>\n",
-       "      <td id=\"T_bc1a2_row97_col4\" class=\"data row97 col4\" >80</td>\n",
-       "      <td id=\"T_bc1a2_row97_col5\" class=\"data row97 col5\" >103</td>\n",
-       "      <td id=\"T_bc1a2_row97_col6\" class=\"data row97 col6\" >-23</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row98\" class=\"row_heading level0 row98\" >phi-2-dpo</th>\n",
-       "      <td id=\"T_bc1a2_row98_col0\" class=\"data row98 col0\" >1687</td>\n",
-       "      <td id=\"T_bc1a2_row98_col1\" class=\"data row98 col1\" >7.757096</td>\n",
-       "      <td id=\"T_bc1a2_row98_col2\" class=\"data row98 col2\" >10.102981</td>\n",
-       "      <td id=\"T_bc1a2_row98_col3\" class=\"data row98 col3\" >2.345885</td>\n",
-       "      <td id=\"T_bc1a2_row98_col4\" class=\"data row98 col4\" >75</td>\n",
-       "      <td id=\"T_bc1a2_row98_col5\" class=\"data row98 col5\" >99</td>\n",
-       "      <td id=\"T_bc1a2_row98_col6\" class=\"data row98 col6\" >-24</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row99\" class=\"row_heading level0 row99\" >minichat-1.5-3b</th>\n",
-       "      <td id=\"T_bc1a2_row99_col0\" class=\"data row99 col0\" >1545</td>\n",
-       "      <td id=\"T_bc1a2_row99_col1\" class=\"data row99 col1\" >6.553443</td>\n",
-       "      <td id=\"T_bc1a2_row99_col2\" class=\"data row99 col2\" >8.493973</td>\n",
-       "      <td id=\"T_bc1a2_row99_col3\" class=\"data row99 col3\" >1.940530</td>\n",
-       "      <td id=\"T_bc1a2_row99_col4\" class=\"data row99 col4\" >90</td>\n",
-       "      <td id=\"T_bc1a2_row99_col5\" class=\"data row99 col5\" >110</td>\n",
-       "      <td id=\"T_bc1a2_row99_col6\" class=\"data row99 col6\" >-20</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row100\" class=\"row_heading level0 row100\" >vicuna-7b-v1.5</th>\n",
-       "      <td id=\"T_bc1a2_row100_col0\" class=\"data row100 col0\" >1083</td>\n",
-       "      <td id=\"T_bc1a2_row100_col1\" class=\"data row100 col1\" >4.797494</td>\n",
-       "      <td id=\"T_bc1a2_row100_col2\" class=\"data row100 col2\" >9.831513</td>\n",
-       "      <td id=\"T_bc1a2_row100_col3\" class=\"data row100 col3\" >5.034019</td>\n",
-       "      <td id=\"T_bc1a2_row100_col4\" class=\"data row100 col4\" >103</td>\n",
-       "      <td id=\"T_bc1a2_row100_col5\" class=\"data row100 col5\" >102</td>\n",
-       "      <td id=\"T_bc1a2_row100_col6\" class=\"data row100 col6\" >1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row101\" class=\"row_heading level0 row101\" >llama-2-chat-7b-evol70k-neft</th>\n",
-       "      <td id=\"T_bc1a2_row101_col0\" class=\"data row101 col0\" >1612</td>\n",
-       "      <td id=\"T_bc1a2_row101_col1\" class=\"data row101 col1\" >7.602384</td>\n",
-       "      <td id=\"T_bc1a2_row101_col2\" class=\"data row101 col2\" >10.530830</td>\n",
-       "      <td id=\"T_bc1a2_row101_col3\" class=\"data row101 col3\" >2.928447</td>\n",
-       "      <td id=\"T_bc1a2_row101_col4\" class=\"data row101 col4\" >77</td>\n",
-       "      <td id=\"T_bc1a2_row101_col5\" class=\"data row101 col5\" >96</td>\n",
-       "      <td id=\"T_bc1a2_row101_col6\" class=\"data row101 col6\" >-19</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row102\" class=\"row_heading level0 row102\" >recycled-wizardlm-7b-v2.0</th>\n",
-       "      <td id=\"T_bc1a2_row102_col0\" class=\"data row102 col0\" >1583</td>\n",
-       "      <td id=\"T_bc1a2_row102_col1\" class=\"data row102 col1\" >7.337129</td>\n",
-       "      <td id=\"T_bc1a2_row102_col2\" class=\"data row102 col2\" >10.438112</td>\n",
-       "      <td id=\"T_bc1a2_row102_col3\" class=\"data row102 col3\" >3.100983</td>\n",
-       "      <td id=\"T_bc1a2_row102_col4\" class=\"data row102 col4\" >84</td>\n",
-       "      <td id=\"T_bc1a2_row102_col5\" class=\"data row102 col5\" >97</td>\n",
-       "      <td id=\"T_bc1a2_row102_col6\" class=\"data row102 col6\" >-13</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row103\" class=\"row_heading level0 row103\" >vicuna-7b-v1.3</th>\n",
-       "      <td id=\"T_bc1a2_row103_col0\" class=\"data row103 col0\" >1110</td>\n",
-       "      <td id=\"T_bc1a2_row103_col1\" class=\"data row103 col1\" >4.642512</td>\n",
-       "      <td id=\"T_bc1a2_row103_col2\" class=\"data row103 col2\" >11.599864</td>\n",
-       "      <td id=\"T_bc1a2_row103_col3\" class=\"data row103 col3\" >6.957352</td>\n",
-       "      <td id=\"T_bc1a2_row103_col4\" class=\"data row103 col4\" >105</td>\n",
-       "      <td id=\"T_bc1a2_row103_col5\" class=\"data row103 col5\" >91</td>\n",
-       "      <td id=\"T_bc1a2_row103_col6\" class=\"data row103 col6\" >14</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row104\" class=\"row_heading level0 row104\" >alpaca-farm-ppo-sim-gpt4-20k</th>\n",
-       "      <td id=\"T_bc1a2_row104_col0\" class=\"data row104 col0\" >511</td>\n",
-       "      <td id=\"T_bc1a2_row104_col1\" class=\"data row104 col1\" >3.450342</td>\n",
-       "      <td id=\"T_bc1a2_row104_col2\" class=\"data row104 col2\" >7.809135</td>\n",
-       "      <td id=\"T_bc1a2_row104_col3\" class=\"data row104 col3\" >4.358793</td>\n",
-       "      <td id=\"T_bc1a2_row104_col4\" class=\"data row104 col4\" >113</td>\n",
-       "      <td id=\"T_bc1a2_row104_col5\" class=\"data row104 col5\" >113</td>\n",
-       "      <td id=\"T_bc1a2_row104_col6\" class=\"data row104 col6\" >0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row105\" class=\"row_heading level0 row105\" >ultralm-13b</th>\n",
-       "      <td id=\"T_bc1a2_row105_col0\" class=\"data row105 col0\" >1087</td>\n",
-       "      <td id=\"T_bc1a2_row105_col1\" class=\"data row105 col1\" >5.074590</td>\n",
-       "      <td id=\"T_bc1a2_row105_col2\" class=\"data row105 col2\" >11.539285</td>\n",
-       "      <td id=\"T_bc1a2_row105_col3\" class=\"data row105 col3\" >6.464695</td>\n",
-       "      <td id=\"T_bc1a2_row105_col4\" class=\"data row105 col4\" >100</td>\n",
-       "      <td id=\"T_bc1a2_row105_col5\" class=\"data row105 col5\" >92</td>\n",
-       "      <td id=\"T_bc1a2_row105_col6\" class=\"data row105 col6\" >8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row106\" class=\"row_heading level0 row106\" >baize-v2-13b</th>\n",
-       "      <td id=\"T_bc1a2_row106_col0\" class=\"data row106 col0\" >930</td>\n",
-       "      <td id=\"T_bc1a2_row106_col1\" class=\"data row106 col1\" >4.590545</td>\n",
-       "      <td id=\"T_bc1a2_row106_col2\" class=\"data row106 col2\" >9.054781</td>\n",
-       "      <td id=\"T_bc1a2_row106_col3\" class=\"data row106 col3\" >4.464236</td>\n",
-       "      <td id=\"T_bc1a2_row106_col4\" class=\"data row106 col4\" >106</td>\n",
-       "      <td id=\"T_bc1a2_row106_col5\" class=\"data row106 col5\" >107</td>\n",
-       "      <td id=\"T_bc1a2_row106_col6\" class=\"data row106 col6\" >-1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row107\" class=\"row_heading level0 row107\" >recycled-wizardlm-7b-v1.0</th>\n",
-       "      <td id=\"T_bc1a2_row107_col0\" class=\"data row107 col0\" >1494</td>\n",
-       "      <td id=\"T_bc1a2_row107_col1\" class=\"data row107 col1\" >6.632750</td>\n",
-       "      <td id=\"T_bc1a2_row107_col2\" class=\"data row107 col2\" >9.200354</td>\n",
-       "      <td id=\"T_bc1a2_row107_col3\" class=\"data row107 col3\" >2.567604</td>\n",
-       "      <td id=\"T_bc1a2_row107_col4\" class=\"data row107 col4\" >89</td>\n",
-       "      <td id=\"T_bc1a2_row107_col5\" class=\"data row107 col5\" >106</td>\n",
-       "      <td id=\"T_bc1a2_row107_col6\" class=\"data row107 col6\" >-17</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row108\" class=\"row_heading level0 row108\" >alpaca-7b_verbose</th>\n",
-       "      <td id=\"T_bc1a2_row108_col0\" class=\"data row108 col0\" >537</td>\n",
-       "      <td id=\"T_bc1a2_row108_col1\" class=\"data row108 col1\" >2.933102</td>\n",
-       "      <td id=\"T_bc1a2_row108_col2\" class=\"data row108 col2\" >8.155702</td>\n",
-       "      <td id=\"T_bc1a2_row108_col3\" class=\"data row108 col3\" >5.222601</td>\n",
-       "      <td id=\"T_bc1a2_row108_col4\" class=\"data row108 col4\" >118</td>\n",
-       "      <td id=\"T_bc1a2_row108_col5\" class=\"data row108 col5\" >112</td>\n",
-       "      <td id=\"T_bc1a2_row108_col6\" class=\"data row108 col6\" >6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row109\" class=\"row_heading level0 row109\" >alpaca-farm-ppo-human</th>\n",
-       "      <td id=\"T_bc1a2_row109_col0\" class=\"data row109 col0\" >803</td>\n",
-       "      <td id=\"T_bc1a2_row109_col1\" class=\"data row109 col1\" >4.100427</td>\n",
-       "      <td id=\"T_bc1a2_row109_col2\" class=\"data row109 col2\" >9.954076</td>\n",
-       "      <td id=\"T_bc1a2_row109_col3\" class=\"data row109 col3\" >5.853649</td>\n",
-       "      <td id=\"T_bc1a2_row109_col4\" class=\"data row109 col4\" >108</td>\n",
-       "      <td id=\"T_bc1a2_row109_col5\" class=\"data row109 col5\" >100</td>\n",
-       "      <td id=\"T_bc1a2_row109_col6\" class=\"data row109 col6\" >8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row110\" class=\"row_heading level0 row110\" >vicuna-7b</th>\n",
-       "      <td id=\"T_bc1a2_row110_col0\" class=\"data row110 col0\" >1044</td>\n",
-       "      <td id=\"T_bc1a2_row110_col1\" class=\"data row110 col1\" >4.162611</td>\n",
-       "      <td id=\"T_bc1a2_row110_col2\" class=\"data row110 col2\" >8.263311</td>\n",
-       "      <td id=\"T_bc1a2_row110_col3\" class=\"data row110 col3\" >4.100700</td>\n",
-       "      <td id=\"T_bc1a2_row110_col4\" class=\"data row110 col4\" >107</td>\n",
-       "      <td id=\"T_bc1a2_row110_col5\" class=\"data row110 col5\" >111</td>\n",
-       "      <td id=\"T_bc1a2_row110_col6\" class=\"data row110 col6\" >-4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row111\" class=\"row_heading level0 row111\" >alpaca-7b</th>\n",
-       "      <td id=\"T_bc1a2_row111_col0\" class=\"data row111 col0\" >396</td>\n",
-       "      <td id=\"T_bc1a2_row111_col1\" class=\"data row111 col1\" >2.591451</td>\n",
-       "      <td id=\"T_bc1a2_row111_col2\" class=\"data row111 col2\" >15.393406</td>\n",
-       "      <td id=\"T_bc1a2_row111_col3\" class=\"data row111 col3\" >12.801955</td>\n",
-       "      <td id=\"T_bc1a2_row111_col4\" class=\"data row111 col4\" >122</td>\n",
-       "      <td id=\"T_bc1a2_row111_col5\" class=\"data row111 col5\" >64</td>\n",
-       "      <td id=\"T_bc1a2_row111_col6\" class=\"data row111 col6\" >58</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row112\" class=\"row_heading level0 row112\" >phi-2-sft</th>\n",
-       "      <td id=\"T_bc1a2_row112_col0\" class=\"data row112 col0\" >1068</td>\n",
-       "      <td id=\"T_bc1a2_row112_col1\" class=\"data row112 col1\" >3.977568</td>\n",
-       "      <td id=\"T_bc1a2_row112_col2\" class=\"data row112 col2\" >7.608799</td>\n",
-       "      <td id=\"T_bc1a2_row112_col3\" class=\"data row112 col3\" >3.631231</td>\n",
-       "      <td id=\"T_bc1a2_row112_col4\" class=\"data row112 col4\" >109</td>\n",
-       "      <td id=\"T_bc1a2_row112_col5\" class=\"data row112 col5\" >114</td>\n",
-       "      <td id=\"T_bc1a2_row112_col6\" class=\"data row112 col6\" >-5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row113\" class=\"row_heading level0 row113\" >minichat-3b</th>\n",
-       "      <td id=\"T_bc1a2_row113_col0\" class=\"data row113 col0\" >868</td>\n",
-       "      <td id=\"T_bc1a2_row113_col1\" class=\"data row113 col1\" >3.007151</td>\n",
-       "      <td id=\"T_bc1a2_row113_col2\" class=\"data row113 col2\" >9.394740</td>\n",
-       "      <td id=\"T_bc1a2_row113_col3\" class=\"data row113 col3\" >6.387589</td>\n",
-       "      <td id=\"T_bc1a2_row113_col4\" class=\"data row113 col4\" >117</td>\n",
-       "      <td id=\"T_bc1a2_row113_col5\" class=\"data row113 col5\" >105</td>\n",
-       "      <td id=\"T_bc1a2_row113_col6\" class=\"data row113 col6\" >12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row114\" class=\"row_heading level0 row114\" >guanaco-33b</th>\n",
-       "      <td id=\"T_bc1a2_row114_col0\" class=\"data row114 col0\" >1311</td>\n",
-       "      <td id=\"T_bc1a2_row114_col1\" class=\"data row114 col1\" >5.002494</td>\n",
-       "      <td id=\"T_bc1a2_row114_col2\" class=\"data row114 col2\" >7.568960</td>\n",
-       "      <td id=\"T_bc1a2_row114_col3\" class=\"data row114 col3\" >2.566467</td>\n",
-       "      <td id=\"T_bc1a2_row114_col4\" class=\"data row114 col4\" >101</td>\n",
-       "      <td id=\"T_bc1a2_row114_col5\" class=\"data row114 col5\" >115</td>\n",
-       "      <td id=\"T_bc1a2_row114_col6\" class=\"data row114 col6\" >-14</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row115\" class=\"row_heading level0 row115\" >falcon-40b-instruct</th>\n",
-       "      <td id=\"T_bc1a2_row115_col0\" class=\"data row115 col0\" >662</td>\n",
-       "      <td id=\"T_bc1a2_row115_col1\" class=\"data row115 col1\" >3.342919</td>\n",
-       "      <td id=\"T_bc1a2_row115_col2\" class=\"data row115 col2\" >8.765865</td>\n",
-       "      <td id=\"T_bc1a2_row115_col3\" class=\"data row115 col3\" >5.422946</td>\n",
-       "      <td id=\"T_bc1a2_row115_col4\" class=\"data row115 col4\" >116</td>\n",
-       "      <td id=\"T_bc1a2_row115_col5\" class=\"data row115 col5\" >108</td>\n",
-       "      <td id=\"T_bc1a2_row115_col6\" class=\"data row115 col6\" >8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row116\" class=\"row_heading level0 row116\" >gemma-2b-it</th>\n",
-       "      <td id=\"T_bc1a2_row116_col0\" class=\"data row116 col0\" >1041</td>\n",
-       "      <td id=\"T_bc1a2_row116_col1\" class=\"data row116 col1\" >3.401971</td>\n",
-       "      <td id=\"T_bc1a2_row116_col2\" class=\"data row116 col2\" >6.002278</td>\n",
-       "      <td id=\"T_bc1a2_row116_col3\" class=\"data row116 col3\" >2.600306</td>\n",
-       "      <td id=\"T_bc1a2_row116_col4\" class=\"data row116 col4\" >115</td>\n",
-       "      <td id=\"T_bc1a2_row116_col5\" class=\"data row116 col5\" >120</td>\n",
-       "      <td id=\"T_bc1a2_row116_col6\" class=\"data row116 col6\" >-5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row117\" class=\"row_heading level0 row117\" >llama-2-7b-chat-hf</th>\n",
-       "      <td id=\"T_bc1a2_row117_col0\" class=\"data row117 col0\" >1479</td>\n",
-       "      <td id=\"T_bc1a2_row117_col1\" class=\"data row117 col1\" >4.961340</td>\n",
-       "      <td id=\"T_bc1a2_row117_col2\" class=\"data row117 col2\" >6.711881</td>\n",
-       "      <td id=\"T_bc1a2_row117_col3\" class=\"data row117 col3\" >1.750541</td>\n",
-       "      <td id=\"T_bc1a2_row117_col4\" class=\"data row117 col4\" >102</td>\n",
-       "      <td id=\"T_bc1a2_row117_col5\" class=\"data row117 col5\" >118</td>\n",
-       "      <td id=\"T_bc1a2_row117_col6\" class=\"data row117 col6\" >-16</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row118\" class=\"row_heading level0 row118\" >openbuddy-falcon-7b-v6</th>\n",
-       "      <td id=\"T_bc1a2_row118_col0\" class=\"data row118 col0\" >1152</td>\n",
-       "      <td id=\"T_bc1a2_row118_col1\" class=\"data row118 col1\" >3.521174</td>\n",
-       "      <td id=\"T_bc1a2_row118_col2\" class=\"data row118 col2\" >6.978847</td>\n",
-       "      <td id=\"T_bc1a2_row118_col3\" class=\"data row118 col3\" >3.457673</td>\n",
-       "      <td id=\"T_bc1a2_row118_col4\" class=\"data row118 col4\" >111</td>\n",
-       "      <td id=\"T_bc1a2_row118_col5\" class=\"data row118 col5\" >116</td>\n",
-       "      <td id=\"T_bc1a2_row118_col6\" class=\"data row118 col6\" >-5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row119\" class=\"row_heading level0 row119\" >alpaca-7b_concise</th>\n",
-       "      <td id=\"T_bc1a2_row119_col0\" class=\"data row119 col0\" >351</td>\n",
-       "      <td id=\"T_bc1a2_row119_col1\" class=\"data row119 col1\" >1.991176</td>\n",
-       "      <td id=\"T_bc1a2_row119_col2\" class=\"data row119 col2\" >6.673438</td>\n",
-       "      <td id=\"T_bc1a2_row119_col3\" class=\"data row119 col3\" >4.682261</td>\n",
-       "      <td id=\"T_bc1a2_row119_col4\" class=\"data row119 col4\" >127</td>\n",
-       "      <td id=\"T_bc1a2_row119_col5\" class=\"data row119 col5\" >119</td>\n",
-       "      <td id=\"T_bc1a2_row119_col6\" class=\"data row119 col6\" >8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row120\" class=\"row_heading level0 row120\" >phi-2</th>\n",
-       "      <td id=\"T_bc1a2_row120_col0\" class=\"data row120 col0\" >626</td>\n",
-       "      <td id=\"T_bc1a2_row120_col1\" class=\"data row120 col1\" >2.350210</td>\n",
-       "      <td id=\"T_bc1a2_row120_col2\" class=\"data row120 col2\" >3.105325</td>\n",
-       "      <td id=\"T_bc1a2_row120_col3\" class=\"data row120 col3\" >0.755115</td>\n",
-       "      <td id=\"T_bc1a2_row120_col4\" class=\"data row120 col4\" >124</td>\n",
-       "      <td id=\"T_bc1a2_row120_col5\" class=\"data row120 col5\" >126</td>\n",
-       "      <td id=\"T_bc1a2_row120_col6\" class=\"data row120 col6\" >-2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row121\" class=\"row_heading level0 row121\" >baize-v2-7b</th>\n",
-       "      <td id=\"T_bc1a2_row121_col0\" class=\"data row121 col0\" >1127</td>\n",
-       "      <td id=\"T_bc1a2_row121_col1\" class=\"data row121 col1\" >3.404815</td>\n",
-       "      <td id=\"T_bc1a2_row121_col2\" class=\"data row121 col2\" >5.322234</td>\n",
-       "      <td id=\"T_bc1a2_row121_col3\" class=\"data row121 col3\" >1.917420</td>\n",
-       "      <td id=\"T_bc1a2_row121_col4\" class=\"data row121 col4\" >114</td>\n",
-       "      <td id=\"T_bc1a2_row121_col5\" class=\"data row121 col5\" >121</td>\n",
-       "      <td id=\"T_bc1a2_row121_col6\" class=\"data row121 col6\" >-7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row122\" class=\"row_heading level0 row122\" >chatglm2-6b</th>\n",
-       "      <td id=\"T_bc1a2_row122_col0\" class=\"data row122 col0\" >1027</td>\n",
-       "      <td id=\"T_bc1a2_row122_col1\" class=\"data row122 col1\" >2.762185</td>\n",
-       "      <td id=\"T_bc1a2_row122_col2\" class=\"data row122 col2\" >4.570916</td>\n",
-       "      <td id=\"T_bc1a2_row122_col3\" class=\"data row122 col3\" >1.808732</td>\n",
-       "      <td id=\"T_bc1a2_row122_col4\" class=\"data row122 col4\" >121</td>\n",
-       "      <td id=\"T_bc1a2_row122_col5\" class=\"data row122 col5\" >123</td>\n",
-       "      <td id=\"T_bc1a2_row122_col6\" class=\"data row122 col6\" >-2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row123\" class=\"row_heading level0 row123\" >pythia-12b-mix-sft</th>\n",
-       "      <td id=\"T_bc1a2_row123_col0\" class=\"data row123 col0\" >913</td>\n",
-       "      <td id=\"T_bc1a2_row123_col1\" class=\"data row123 col1\" >2.578090</td>\n",
-       "      <td id=\"T_bc1a2_row123_col2\" class=\"data row123 col2\" >3.344637</td>\n",
-       "      <td id=\"T_bc1a2_row123_col3\" class=\"data row123 col3\" >0.766547</td>\n",
-       "      <td id=\"T_bc1a2_row123_col4\" class=\"data row123 col4\" >123</td>\n",
-       "      <td id=\"T_bc1a2_row123_col5\" class=\"data row123 col5\" >125</td>\n",
-       "      <td id=\"T_bc1a2_row123_col6\" class=\"data row123 col6\" >-2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row124\" class=\"row_heading level0 row124\" >falcon-7b-instruct</th>\n",
-       "      <td id=\"T_bc1a2_row124_col0\" class=\"data row124 col0\" >478</td>\n",
-       "      <td id=\"T_bc1a2_row124_col1\" class=\"data row124 col1\" >2.146618</td>\n",
-       "      <td id=\"T_bc1a2_row124_col2\" class=\"data row124 col2\" >6.787961</td>\n",
-       "      <td id=\"T_bc1a2_row124_col3\" class=\"data row124 col3\" >4.641344</td>\n",
-       "      <td id=\"T_bc1a2_row124_col4\" class=\"data row124 col4\" >125</td>\n",
-       "      <td id=\"T_bc1a2_row124_col5\" class=\"data row124 col5\" >117</td>\n",
-       "      <td id=\"T_bc1a2_row124_col6\" class=\"data row124 col6\" >8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row125\" class=\"row_heading level0 row125\" >oasst-sft-pythia-12b</th>\n",
-       "      <td id=\"T_bc1a2_row125_col0\" class=\"data row125 col0\" >726</td>\n",
-       "      <td id=\"T_bc1a2_row125_col1\" class=\"data row125 col1\" >1.790114</td>\n",
-       "      <td id=\"T_bc1a2_row125_col2\" class=\"data row125 col2\" >2.274166</td>\n",
-       "      <td id=\"T_bc1a2_row125_col3\" class=\"data row125 col3\" >0.484052</td>\n",
-       "      <td id=\"T_bc1a2_row125_col4\" class=\"data row125 col4\" >128</td>\n",
-       "      <td id=\"T_bc1a2_row125_col5\" class=\"data row125 col5\" >128</td>\n",
-       "      <td id=\"T_bc1a2_row125_col6\" class=\"data row125 col6\" >0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row126\" class=\"row_heading level0 row126\" >guanaco-13b</th>\n",
-       "      <td id=\"T_bc1a2_row126_col0\" class=\"data row126 col0\" >1774</td>\n",
-       "      <td id=\"T_bc1a2_row126_col1\" class=\"data row126 col1\" >3.469597</td>\n",
-       "      <td id=\"T_bc1a2_row126_col2\" class=\"data row126 col2\" >4.103434</td>\n",
-       "      <td id=\"T_bc1a2_row126_col3\" class=\"data row126 col3\" >0.633838</td>\n",
-       "      <td id=\"T_bc1a2_row126_col4\" class=\"data row126 col4\" >112</td>\n",
-       "      <td id=\"T_bc1a2_row126_col5\" class=\"data row126 col5\" >124</td>\n",
-       "      <td id=\"T_bc1a2_row126_col6\" class=\"data row126 col6\" >-12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row127\" class=\"row_heading level0 row127\" >guanaco-7b</th>\n",
-       "      <td id=\"T_bc1a2_row127_col0\" class=\"data row127 col0\" >1364</td>\n",
-       "      <td id=\"T_bc1a2_row127_col1\" class=\"data row127 col1\" >2.880002</td>\n",
-       "      <td id=\"T_bc1a2_row127_col2\" class=\"data row127 col2\" >4.644985</td>\n",
-       "      <td id=\"T_bc1a2_row127_col3\" class=\"data row127 col3\" >1.764983</td>\n",
-       "      <td id=\"T_bc1a2_row127_col4\" class=\"data row127 col4\" >119</td>\n",
-       "      <td id=\"T_bc1a2_row127_col5\" class=\"data row127 col5\" >122</td>\n",
-       "      <td id=\"T_bc1a2_row127_col6\" class=\"data row127 col6\" >-3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_bc1a2_level0_row128\" class=\"row_heading level0 row128\" >baichuan-13b-chat</th>\n",
-       "      <td id=\"T_bc1a2_row128_col0\" class=\"data row128 col0\" >1727</td>\n",
-       "      <td id=\"T_bc1a2_row128_col1\" class=\"data row128 col1\" >1.992146</td>\n",
-       "      <td id=\"T_bc1a2_row128_col2\" class=\"data row128 col2\" >2.464749</td>\n",
-       "      <td id=\"T_bc1a2_row128_col3\" class=\"data row128 col3\" >0.472603</td>\n",
-       "      <td id=\"T_bc1a2_row128_col4\" class=\"data row128 col4\" >126</td>\n",
-       "      <td id=\"T_bc1a2_row128_col5\" class=\"data row128 col5\" >127</td>\n",
-       "      <td id=\"T_bc1a2_row128_col6\" class=\"data row128 col6\" >-1</td>\n",
+       "      <th id=\"T_f9ded_level0_row0\" class=\"row_heading level0 row0\" >gpt4_1106_preview_verbose</th>\n",
+       "      <td id=\"T_f9ded_row0_col0\" class=\"data row0 col0\" >2402</td>\n",
+       "      <td id=\"T_f9ded_row0_col1\" class=\"data row0 col1\" >64.303601</td>\n",
+       "      <td id=\"T_f9ded_row0_col2\" class=\"data row0 col2\" >55.464179</td>\n",
+       "      <td id=\"T_f9ded_row0_col3\" class=\"data row0 col3\" >-8.839422</td>\n",
+       "      <td id=\"T_f9ded_row0_col4\" class=\"data row0 col4\" >0</td>\n",
+       "      <td id=\"T_f9ded_row0_col5\" class=\"data row0 col5\" >0</td>\n",
+       "      <td id=\"T_f9ded_row0_col6\" class=\"data row0 col6\" >0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row1\" class=\"row_heading level0 row1\" >gpt4_1106_preview</th>\n",
+       "      <td id=\"T_f9ded_row1_col0\" class=\"data row1 col0\" >2049</td>\n",
+       "      <td id=\"T_f9ded_row1_col1\" class=\"data row1 col1\" >50.000000</td>\n",
+       "      <td id=\"T_f9ded_row1_col2\" class=\"data row1 col2\" >50.000000</td>\n",
+       "      <td id=\"T_f9ded_row1_col3\" class=\"data row1 col3\" >0.000000</td>\n",
+       "      <td id=\"T_f9ded_row1_col4\" class=\"data row1 col4\" >1</td>\n",
+       "      <td id=\"T_f9ded_row1_col5\" class=\"data row1 col5\" >1</td>\n",
+       "      <td id=\"T_f9ded_row1_col6\" class=\"data row1 col6\" >0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row2\" class=\"row_heading level0 row2\" >gpt4_1106_preview_concise</th>\n",
+       "      <td id=\"T_f9ded_row2_col0\" class=\"data row2 col0\" >1136</td>\n",
+       "      <td id=\"T_f9ded_row2_col1\" class=\"data row2 col1\" >22.920194</td>\n",
+       "      <td id=\"T_f9ded_row2_col2\" class=\"data row2 col2\" >42.476316</td>\n",
+       "      <td id=\"T_f9ded_row2_col3\" class=\"data row2 col3\" >19.556121</td>\n",
+       "      <td id=\"T_f9ded_row2_col4\" class=\"data row2 col4\" >14</td>\n",
+       "      <td id=\"T_f9ded_row2_col5\" class=\"data row2 col5\" >3</td>\n",
+       "      <td id=\"T_f9ded_row2_col6\" class=\"data row2 col6\" >11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row3\" class=\"row_heading level0 row3\" >claude-3-opus-20240229</th>\n",
+       "      <td id=\"T_f9ded_row3_col0\" class=\"data row3 col0\" >1388</td>\n",
+       "      <td id=\"T_f9ded_row3_col1\" class=\"data row3 col1\" >29.041764</td>\n",
+       "      <td id=\"T_f9ded_row3_col2\" class=\"data row3 col2\" >39.494379</td>\n",
+       "      <td id=\"T_f9ded_row3_col3\" class=\"data row3 col3\" >10.452615</td>\n",
+       "      <td id=\"T_f9ded_row3_col4\" class=\"data row3 col4\" >7</td>\n",
+       "      <td id=\"T_f9ded_row3_col5\" class=\"data row3 col5\" >4</td>\n",
+       "      <td id=\"T_f9ded_row3_col6\" class=\"data row3 col6\" >3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row4\" class=\"row_heading level0 row4\" >gpt4</th>\n",
+       "      <td id=\"T_f9ded_row4_col0\" class=\"data row4 col0\" >1365</td>\n",
+       "      <td id=\"T_f9ded_row4_col1\" class=\"data row4 col1\" >23.576789</td>\n",
+       "      <td id=\"T_f9ded_row4_col2\" class=\"data row4 col2\" >36.503486</td>\n",
+       "      <td id=\"T_f9ded_row4_col3\" class=\"data row4 col3\" >12.926697</td>\n",
+       "      <td id=\"T_f9ded_row4_col4\" class=\"data row4 col4\" >12</td>\n",
+       "      <td id=\"T_f9ded_row4_col5\" class=\"data row4 col5\" >7</td>\n",
+       "      <td id=\"T_f9ded_row4_col6\" class=\"data row4 col6\" >5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row5\" class=\"row_heading level0 row5\" >Qwen1.5-72B-Chat</th>\n",
+       "      <td id=\"T_f9ded_row5_col0\" class=\"data row5 col0\" >1549</td>\n",
+       "      <td id=\"T_f9ded_row5_col1\" class=\"data row5 col1\" >26.498283</td>\n",
+       "      <td id=\"T_f9ded_row5_col2\" class=\"data row5 col2\" >37.072419</td>\n",
+       "      <td id=\"T_f9ded_row5_col3\" class=\"data row5 col3\" >10.574135</td>\n",
+       "      <td id=\"T_f9ded_row5_col4\" class=\"data row5 col4\" >8</td>\n",
+       "      <td id=\"T_f9ded_row5_col5\" class=\"data row5 col5\" >6</td>\n",
+       "      <td id=\"T_f9ded_row5_col6\" class=\"data row5 col6\" >2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row6\" class=\"row_heading level0 row6\" >gpt4_0314</th>\n",
+       "      <td id=\"T_f9ded_row6_col0\" class=\"data row6 col0\" >1371</td>\n",
+       "      <td id=\"T_f9ded_row6_col1\" class=\"data row6 col1\" >22.073259</td>\n",
+       "      <td id=\"T_f9ded_row6_col2\" class=\"data row6 col2\" >30.972772</td>\n",
+       "      <td id=\"T_f9ded_row6_col3\" class=\"data row6 col3\" >8.899513</td>\n",
+       "      <td id=\"T_f9ded_row6_col4\" class=\"data row6 col4\" >15</td>\n",
+       "      <td id=\"T_f9ded_row6_col5\" class=\"data row6 col5\" >13</td>\n",
+       "      <td id=\"T_f9ded_row6_col6\" class=\"data row6 col6\" >2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row7\" class=\"row_heading level0 row7\" >claude-3-sonnet-20240229</th>\n",
+       "      <td id=\"T_f9ded_row7_col0\" class=\"data row7 col0\" >1420</td>\n",
+       "      <td id=\"T_f9ded_row7_col1\" class=\"data row7 col1\" >25.556325</td>\n",
+       "      <td id=\"T_f9ded_row7_col2\" class=\"data row7 col2\" >35.516836</td>\n",
+       "      <td id=\"T_f9ded_row7_col3\" class=\"data row7 col3\" >9.960510</td>\n",
+       "      <td id=\"T_f9ded_row7_col4\" class=\"data row7 col4\" >9</td>\n",
+       "      <td id=\"T_f9ded_row7_col5\" class=\"data row7 col5\" >8</td>\n",
+       "      <td id=\"T_f9ded_row7_col6\" class=\"data row7 col6\" >1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row8\" class=\"row_heading level0 row8\" >gpt4_0613_verbose</th>\n",
+       "      <td id=\"T_f9ded_row8_col0\" class=\"data row8 col0\" >1473</td>\n",
+       "      <td id=\"T_f9ded_row8_col1\" class=\"data row8 col1\" >23.237360</td>\n",
+       "      <td id=\"T_f9ded_row8_col2\" class=\"data row8 col2\" >32.752569</td>\n",
+       "      <td id=\"T_f9ded_row8_col3\" class=\"data row8 col3\" >9.515209</td>\n",
+       "      <td id=\"T_f9ded_row8_col4\" class=\"data row8 col4\" >13</td>\n",
+       "      <td id=\"T_f9ded_row8_col5\" class=\"data row8 col5\" >9</td>\n",
+       "      <td id=\"T_f9ded_row8_col6\" class=\"data row8 col6\" >4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row9\" class=\"row_heading level0 row9\" >mistral-large-2402</th>\n",
+       "      <td id=\"T_f9ded_row9_col0\" class=\"data row9 col0\" >1362</td>\n",
+       "      <td id=\"T_f9ded_row9_col1\" class=\"data row9 col1\" >21.438776</td>\n",
+       "      <td id=\"T_f9ded_row9_col2\" class=\"data row9 col2\" >37.141506</td>\n",
+       "      <td id=\"T_f9ded_row9_col3\" class=\"data row9 col3\" >15.702730</td>\n",
+       "      <td id=\"T_f9ded_row9_col4\" class=\"data row9 col4\" >19</td>\n",
+       "      <td id=\"T_f9ded_row9_col5\" class=\"data row9 col5\" >5</td>\n",
+       "      <td id=\"T_f9ded_row9_col6\" class=\"data row9 col6\" >14</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row10\" class=\"row_heading level0 row10\" >claude-2.1_verbose</th>\n",
+       "      <td id=\"T_f9ded_row10_col0\" class=\"data row10 col0\" >1414</td>\n",
+       "      <td id=\"T_f9ded_row10_col1\" class=\"data row10 col1\" >24.354071</td>\n",
+       "      <td id=\"T_f9ded_row10_col2\" class=\"data row10 col2\" >30.614862</td>\n",
+       "      <td id=\"T_f9ded_row10_col3\" class=\"data row10 col3\" >6.260791</td>\n",
+       "      <td id=\"T_f9ded_row10_col4\" class=\"data row10 col4\" >11</td>\n",
+       "      <td id=\"T_f9ded_row10_col5\" class=\"data row10 col5\" >15</td>\n",
+       "      <td id=\"T_f9ded_row10_col6\" class=\"data row10 col6\" >-4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row11\" class=\"row_heading level0 row11\" >gpt4_0613</th>\n",
+       "      <td id=\"T_f9ded_row11_col0\" class=\"data row11 col0\" >1140</td>\n",
+       "      <td id=\"T_f9ded_row11_col1\" class=\"data row11 col1\" >15.755038</td>\n",
+       "      <td id=\"T_f9ded_row11_col2\" class=\"data row11 col2\" >29.528662</td>\n",
+       "      <td id=\"T_f9ded_row11_col3\" class=\"data row11 col3\" >13.773624</td>\n",
+       "      <td id=\"T_f9ded_row11_col4\" class=\"data row11 col4\" >30</td>\n",
+       "      <td id=\"T_f9ded_row11_col5\" class=\"data row11 col5\" >19</td>\n",
+       "      <td id=\"T_f9ded_row11_col6\" class=\"data row11 col6\" >11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row12\" class=\"row_heading level0 row12\" >Snorkel-Mistral-PairRM-DPO-best-of-16</th>\n",
+       "      <td id=\"T_f9ded_row12_col0\" class=\"data row12 col0\" >2616</td>\n",
+       "      <td id=\"T_f9ded_row12_col1\" class=\"data row12 col1\" >34.860133</td>\n",
+       "      <td id=\"T_f9ded_row12_col2\" class=\"data row12 col2\" >31.504510</td>\n",
+       "      <td id=\"T_f9ded_row12_col3\" class=\"data row12 col3\" >-3.355623</td>\n",
+       "      <td id=\"T_f9ded_row12_col4\" class=\"data row12 col4\" >2</td>\n",
+       "      <td id=\"T_f9ded_row12_col5\" class=\"data row12 col5\" >10</td>\n",
+       "      <td id=\"T_f9ded_row12_col6\" class=\"data row12 col6\" >-8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row13\" class=\"row_heading level0 row13\" >Contextual-KTO-Mistral-PairRM</th>\n",
+       "      <td id=\"T_f9ded_row13_col0\" class=\"data row13 col0\" >2521</td>\n",
+       "      <td id=\"T_f9ded_row13_col1\" class=\"data row13 col1\" >33.227355</td>\n",
+       "      <td id=\"T_f9ded_row13_col2\" class=\"data row13 col2\" >31.198200</td>\n",
+       "      <td id=\"T_f9ded_row13_col3\" class=\"data row13 col3\" >-2.029155</td>\n",
+       "      <td id=\"T_f9ded_row13_col4\" class=\"data row13 col4\" >3</td>\n",
+       "      <td id=\"T_f9ded_row13_col5\" class=\"data row13 col5\" >11</td>\n",
+       "      <td id=\"T_f9ded_row13_col6\" class=\"data row13 col6\" >-8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row14\" class=\"row_heading level0 row14\" >pairrm-Yi-34B-Chat</th>\n",
+       "      <td id=\"T_f9ded_row14_col0\" class=\"data row14 col0\" >2195</td>\n",
+       "      <td id=\"T_f9ded_row14_col1\" class=\"data row14 col1\" >31.241283</td>\n",
+       "      <td id=\"T_f9ded_row14_col2\" class=\"data row14 col2\" >29.895164</td>\n",
+       "      <td id=\"T_f9ded_row14_col3\" class=\"data row14 col3\" >-1.346119</td>\n",
+       "      <td id=\"T_f9ded_row14_col4\" class=\"data row14 col4\" >4</td>\n",
+       "      <td id=\"T_f9ded_row14_col5\" class=\"data row14 col5\" >16</td>\n",
+       "      <td id=\"T_f9ded_row14_col6\" class=\"data row14 col6\" >-12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row15\" class=\"row_heading level0 row15\" >mistral-medium</th>\n",
+       "      <td id=\"T_f9ded_row15_col0\" class=\"data row15 col0\" >1500</td>\n",
+       "      <td id=\"T_f9ded_row15_col1\" class=\"data row15 col1\" >21.855773</td>\n",
+       "      <td id=\"T_f9ded_row15_col2\" class=\"data row15 col2\" >30.845477</td>\n",
+       "      <td id=\"T_f9ded_row15_col3\" class=\"data row15 col3\" >8.989704</td>\n",
+       "      <td id=\"T_f9ded_row15_col4\" class=\"data row15 col4\" >16</td>\n",
+       "      <td id=\"T_f9ded_row15_col5\" class=\"data row15 col5\" >14</td>\n",
+       "      <td id=\"T_f9ded_row15_col6\" class=\"data row15 col6\" >2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row16\" class=\"row_heading level0 row16\" >claude-2</th>\n",
+       "      <td id=\"T_f9ded_row16_col0\" class=\"data row16 col0\" >1069</td>\n",
+       "      <td id=\"T_f9ded_row16_col1\" class=\"data row16 col1\" >17.188240</td>\n",
+       "      <td id=\"T_f9ded_row16_col2\" class=\"data row16 col2\" >29.813958</td>\n",
+       "      <td id=\"T_f9ded_row16_col3\" class=\"data row16 col3\" >12.625718</td>\n",
+       "      <td id=\"T_f9ded_row16_col4\" class=\"data row16 col4\" >25</td>\n",
+       "      <td id=\"T_f9ded_row16_col5\" class=\"data row16 col5\" >17</td>\n",
+       "      <td id=\"T_f9ded_row16_col6\" class=\"data row16 col6\" >8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row17\" class=\"row_heading level0 row17\" >claude</th>\n",
+       "      <td id=\"T_f9ded_row17_col0\" class=\"data row17 col0\" >1082</td>\n",
+       "      <td id=\"T_f9ded_row17_col1\" class=\"data row17 col1\" >16.985344</td>\n",
+       "      <td id=\"T_f9ded_row17_col2\" class=\"data row17 col2\" >31.090175</td>\n",
+       "      <td id=\"T_f9ded_row17_col3\" class=\"data row17 col3\" >14.104832</td>\n",
+       "      <td id=\"T_f9ded_row17_col4\" class=\"data row17 col4\" >26</td>\n",
+       "      <td id=\"T_f9ded_row17_col5\" class=\"data row17 col5\" >12</td>\n",
+       "      <td id=\"T_f9ded_row17_col6\" class=\"data row17 col6\" >14</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row18\" class=\"row_heading level0 row18\" >Yi-34B-Chat</th>\n",
+       "      <td id=\"T_f9ded_row18_col0\" class=\"data row18 col0\" >2123</td>\n",
+       "      <td id=\"T_f9ded_row18_col1\" class=\"data row18 col1\" >29.659947</td>\n",
+       "      <td id=\"T_f9ded_row18_col2\" class=\"data row18 col2\" >28.477128</td>\n",
+       "      <td id=\"T_f9ded_row18_col3\" class=\"data row18 col3\" >-1.182818</td>\n",
+       "      <td id=\"T_f9ded_row18_col4\" class=\"data row18 col4\" >6</td>\n",
+       "      <td id=\"T_f9ded_row18_col5\" class=\"data row18 col5\" >23</td>\n",
+       "      <td id=\"T_f9ded_row18_col6\" class=\"data row18 col6\" >-17</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row19\" class=\"row_heading level0 row19\" >Snorkel-Mistral-PairRM-DPO</th>\n",
+       "      <td id=\"T_f9ded_row19_col0\" class=\"data row19 col0\" >2736</td>\n",
+       "      <td id=\"T_f9ded_row19_col1\" class=\"data row19 col1\" >30.220053</td>\n",
+       "      <td id=\"T_f9ded_row19_col2\" class=\"data row19 col2\" >27.673988</td>\n",
+       "      <td id=\"T_f9ded_row19_col3\" class=\"data row19 col3\" >-2.546065</td>\n",
+       "      <td id=\"T_f9ded_row19_col4\" class=\"data row19 col4\" >5</td>\n",
+       "      <td id=\"T_f9ded_row19_col5\" class=\"data row19 col5\" >26</td>\n",
+       "      <td id=\"T_f9ded_row19_col6\" class=\"data row19 col6\" >-21</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row20\" class=\"row_heading level0 row20\" >claude-instant-1.2</th>\n",
+       "      <td id=\"T_f9ded_row20_col0\" class=\"data row20 col0\" >1112</td>\n",
+       "      <td id=\"T_f9ded_row20_col1\" class=\"data row20 col1\" >16.127400</td>\n",
+       "      <td id=\"T_f9ded_row20_col2\" class=\"data row20 col2\" >28.730484</td>\n",
+       "      <td id=\"T_f9ded_row20_col3\" class=\"data row20 col3\" >12.603085</td>\n",
+       "      <td id=\"T_f9ded_row20_col4\" class=\"data row20 col4\" >27</td>\n",
+       "      <td id=\"T_f9ded_row20_col5\" class=\"data row20 col5\" >21</td>\n",
+       "      <td id=\"T_f9ded_row20_col6\" class=\"data row20 col6\" >6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row21\" class=\"row_heading level0 row21\" >claude-2.1</th>\n",
+       "      <td id=\"T_f9ded_row21_col0\" class=\"data row21 col0\" >1096</td>\n",
+       "      <td id=\"T_f9ded_row21_col1\" class=\"data row21 col1\" >15.733507</td>\n",
+       "      <td id=\"T_f9ded_row21_col2\" class=\"data row21 col2\" >29.562828</td>\n",
+       "      <td id=\"T_f9ded_row21_col3\" class=\"data row21 col3\" >13.829321</td>\n",
+       "      <td id=\"T_f9ded_row21_col4\" class=\"data row21 col4\" >31</td>\n",
+       "      <td id=\"T_f9ded_row21_col5\" class=\"data row21 col5\" >18</td>\n",
+       "      <td id=\"T_f9ded_row21_col6\" class=\"data row21 col6\" >13</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row22\" class=\"row_heading level0 row22\" >xwinlm-70b-v0.1</th>\n",
+       "      <td id=\"T_f9ded_row22_col0\" class=\"data row22 col0\" >1775</td>\n",
+       "      <td id=\"T_f9ded_row22_col1\" class=\"data row22 col1\" >21.812957</td>\n",
+       "      <td id=\"T_f9ded_row22_col2\" class=\"data row22 col2\" >25.825081</td>\n",
+       "      <td id=\"T_f9ded_row22_col3\" class=\"data row22 col3\" >4.012124</td>\n",
+       "      <td id=\"T_f9ded_row22_col4\" class=\"data row22 col4\" >17</td>\n",
+       "      <td id=\"T_f9ded_row22_col5\" class=\"data row22 col5\" >28</td>\n",
+       "      <td id=\"T_f9ded_row22_col6\" class=\"data row22 col6\" >-11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row23\" class=\"row_heading level0 row23\" >gemini-pro</th>\n",
+       "      <td id=\"T_f9ded_row23_col0\" class=\"data row23 col0\" >1456</td>\n",
+       "      <td id=\"T_f9ded_row23_col1\" class=\"data row23 col1\" >18.177645</td>\n",
+       "      <td id=\"T_f9ded_row23_col2\" class=\"data row23 col2\" >24.449134</td>\n",
+       "      <td id=\"T_f9ded_row23_col3\" class=\"data row23 col3\" >6.271490</td>\n",
+       "      <td id=\"T_f9ded_row23_col4\" class=\"data row23 col4\" >23</td>\n",
+       "      <td id=\"T_f9ded_row23_col5\" class=\"data row23 col5\" >31</td>\n",
+       "      <td id=\"T_f9ded_row23_col6\" class=\"data row23 col6\" >-8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row24\" class=\"row_heading level0 row24\" >Mixtral-8x7B-Instruct-v0.1</th>\n",
+       "      <td id=\"T_f9ded_row24_col0\" class=\"data row24 col0\" >1465</td>\n",
+       "      <td id=\"T_f9ded_row24_col1\" class=\"data row24 col1\" >18.255318</td>\n",
+       "      <td id=\"T_f9ded_row24_col2\" class=\"data row24 col2\" >26.083414</td>\n",
+       "      <td id=\"T_f9ded_row24_col3\" class=\"data row24 col3\" >7.828096</td>\n",
+       "      <td id=\"T_f9ded_row24_col4\" class=\"data row24 col4\" >22</td>\n",
+       "      <td id=\"T_f9ded_row24_col5\" class=\"data row24 col5\" >27</td>\n",
+       "      <td id=\"T_f9ded_row24_col6\" class=\"data row24 col6\" >-5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row25\" class=\"row_heading level0 row25\" >evo-v2-7b</th>\n",
+       "      <td id=\"T_f9ded_row25_col0\" class=\"data row25 col0\" >1754</td>\n",
+       "      <td id=\"T_f9ded_row25_col1\" class=\"data row25 col1\" >20.834113</td>\n",
+       "      <td id=\"T_f9ded_row25_col2\" class=\"data row25 col2\" >22.778849</td>\n",
+       "      <td id=\"T_f9ded_row25_col3\" class=\"data row25 col3\" >1.944736</td>\n",
+       "      <td id=\"T_f9ded_row25_col4\" class=\"data row25 col4\" >20</td>\n",
+       "      <td id=\"T_f9ded_row25_col5\" class=\"data row25 col5\" >34</td>\n",
+       "      <td id=\"T_f9ded_row25_col6\" class=\"data row25 col6\" >-14</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row26\" class=\"row_heading level0 row26\" >Mixtral-8x7B-Instruct-v0.1_verbose</th>\n",
+       "      <td id=\"T_f9ded_row26_col0\" class=\"data row26 col0\" >2083</td>\n",
+       "      <td id=\"T_f9ded_row26_col1\" class=\"data row26 col1\" >24.614063</td>\n",
+       "      <td id=\"T_f9ded_row26_col2\" class=\"data row26 col2\" >24.503900</td>\n",
+       "      <td id=\"T_f9ded_row26_col3\" class=\"data row26 col3\" >-0.110163</td>\n",
+       "      <td id=\"T_f9ded_row26_col4\" class=\"data row26 col4\" >10</td>\n",
+       "      <td id=\"T_f9ded_row26_col5\" class=\"data row26 col5\" >30</td>\n",
+       "      <td id=\"T_f9ded_row26_col6\" class=\"data row26 col6\" >-20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row27\" class=\"row_heading level0 row27\" >Mixtral-8x7B-Instruct-v0.1_concise</th>\n",
+       "      <td id=\"T_f9ded_row27_col0\" class=\"data row27 col0\" >910</td>\n",
+       "      <td id=\"T_f9ded_row27_col1\" class=\"data row27 col1\" >13.744040</td>\n",
+       "      <td id=\"T_f9ded_row27_col2\" class=\"data row27 col2\" >28.436687</td>\n",
+       "      <td id=\"T_f9ded_row27_col3\" class=\"data row27 col3\" >14.692646</td>\n",
+       "      <td id=\"T_f9ded_row27_col4\" class=\"data row27 col4\" >41</td>\n",
+       "      <td id=\"T_f9ded_row27_col5\" class=\"data row27 col5\" >24</td>\n",
+       "      <td id=\"T_f9ded_row27_col6\" class=\"data row27 col6\" >17</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row28\" class=\"row_heading level0 row28\" >gpt-3.5-turbo-16k-0613</th>\n",
+       "      <td id=\"T_f9ded_row28_col0\" class=\"data row28 col0\" >1328</td>\n",
+       "      <td id=\"T_f9ded_row28_col1\" class=\"data row28 col1\" >14.132391</td>\n",
+       "      <td id=\"T_f9ded_row28_col2\" class=\"data row28 col2\" >22.695292</td>\n",
+       "      <td id=\"T_f9ded_row28_col3\" class=\"data row28 col3\" >8.562902</td>\n",
+       "      <td id=\"T_f9ded_row28_col4\" class=\"data row28 col4\" >36</td>\n",
+       "      <td id=\"T_f9ded_row28_col5\" class=\"data row28 col5\" >36</td>\n",
+       "      <td id=\"T_f9ded_row28_col6\" class=\"data row28 col6\" >0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row29\" class=\"row_heading level0 row29\" >gpt-3.5-turbo-0613</th>\n",
+       "      <td id=\"T_f9ded_row29_col0\" class=\"data row29 col0\" >1331</td>\n",
+       "      <td id=\"T_f9ded_row29_col1\" class=\"data row29 col1\" >14.095799</td>\n",
+       "      <td id=\"T_f9ded_row29_col2\" class=\"data row29 col2\" >20.421657</td>\n",
+       "      <td id=\"T_f9ded_row29_col3\" class=\"data row29 col3\" >6.325858</td>\n",
+       "      <td id=\"T_f9ded_row29_col4\" class=\"data row29 col4\" >37</td>\n",
+       "      <td id=\"T_f9ded_row29_col5\" class=\"data row29 col5\" >42</td>\n",
+       "      <td id=\"T_f9ded_row29_col6\" class=\"data row29 col6\" >-5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row30\" class=\"row_heading level0 row30\" >gpt-3.5-turbo-1106_verbose</th>\n",
+       "      <td id=\"T_f9ded_row30_col0\" class=\"data row30 col0\" >1058</td>\n",
+       "      <td id=\"T_f9ded_row30_col1\" class=\"data row30 col1\" >12.763170</td>\n",
+       "      <td id=\"T_f9ded_row30_col2\" class=\"data row30 col2\" >28.251113</td>\n",
+       "      <td id=\"T_f9ded_row30_col3\" class=\"data row30 col3\" >15.487943</td>\n",
+       "      <td id=\"T_f9ded_row30_col4\" class=\"data row30 col4\" >45</td>\n",
+       "      <td id=\"T_f9ded_row30_col5\" class=\"data row30 col5\" >25</td>\n",
+       "      <td id=\"T_f9ded_row30_col6\" class=\"data row30 col6\" >20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row31\" class=\"row_heading level0 row31\" >gpt4_0613_concise</th>\n",
+       "      <td id=\"T_f9ded_row31_col0\" class=\"data row31 col0\" >627</td>\n",
+       "      <td id=\"T_f9ded_row31_col1\" class=\"data row31 col1\" >9.400321</td>\n",
+       "      <td id=\"T_f9ded_row31_col2\" class=\"data row31 col2\" >28.602992</td>\n",
+       "      <td id=\"T_f9ded_row31_col3\" class=\"data row31 col3\" >19.202671</td>\n",
+       "      <td id=\"T_f9ded_row31_col4\" class=\"data row31 col4\" >63</td>\n",
+       "      <td id=\"T_f9ded_row31_col5\" class=\"data row31 col5\" >22</td>\n",
+       "      <td id=\"T_f9ded_row31_col6\" class=\"data row31 col6\" >41</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row32\" class=\"row_heading level0 row32\" >pairrm-tulu-2-70b</th>\n",
+       "      <td id=\"T_f9ded_row32_col0\" class=\"data row32 col0\" >1607</td>\n",
+       "      <td id=\"T_f9ded_row32_col1\" class=\"data row32 col1\" >18.638963</td>\n",
+       "      <td id=\"T_f9ded_row32_col2\" class=\"data row32 col2\" >23.943414</td>\n",
+       "      <td id=\"T_f9ded_row32_col3\" class=\"data row32 col3\" >5.304451</td>\n",
+       "      <td id=\"T_f9ded_row32_col4\" class=\"data row32 col4\" >21</td>\n",
+       "      <td id=\"T_f9ded_row32_col5\" class=\"data row32 col5\" >32</td>\n",
+       "      <td id=\"T_f9ded_row32_col6\" class=\"data row32 col6\" >-11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row33\" class=\"row_heading level0 row33\" >tulu-2-dpo-70b</th>\n",
+       "      <td id=\"T_f9ded_row33_col0\" class=\"data row33 col0\" >1418</td>\n",
+       "      <td id=\"T_f9ded_row33_col1\" class=\"data row33 col1\" >15.982854</td>\n",
+       "      <td id=\"T_f9ded_row33_col2\" class=\"data row33 col2\" >24.924799</td>\n",
+       "      <td id=\"T_f9ded_row33_col3\" class=\"data row33 col3\" >8.941945</td>\n",
+       "      <td id=\"T_f9ded_row33_col4\" class=\"data row33 col4\" >29</td>\n",
+       "      <td id=\"T_f9ded_row33_col5\" class=\"data row33 col5\" >29</td>\n",
+       "      <td id=\"T_f9ded_row33_col6\" class=\"data row33 col6\" >0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row34\" class=\"row_heading level0 row34\" >Mistral-7B-ReMax-v0.1</th>\n",
+       "      <td id=\"T_f9ded_row34_col0\" class=\"data row34 col0\" >1478</td>\n",
+       "      <td id=\"T_f9ded_row34_col1\" class=\"data row34 col1\" >15.999331</td>\n",
+       "      <td id=\"T_f9ded_row34_col2\" class=\"data row34 col2\" >23.779278</td>\n",
+       "      <td id=\"T_f9ded_row34_col3\" class=\"data row34 col3\" >7.779946</td>\n",
+       "      <td id=\"T_f9ded_row34_col4\" class=\"data row34 col4\" >28</td>\n",
+       "      <td id=\"T_f9ded_row34_col5\" class=\"data row34 col5\" >33</td>\n",
+       "      <td id=\"T_f9ded_row34_col6\" class=\"data row34 col6\" >-5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row35\" class=\"row_heading level0 row35\" >gpt-3.5-turbo-1106</th>\n",
+       "      <td id=\"T_f9ded_row35_col0\" class=\"data row35 col0\" >796</td>\n",
+       "      <td id=\"T_f9ded_row35_col1\" class=\"data row35 col1\" >9.177965</td>\n",
+       "      <td id=\"T_f9ded_row35_col2\" class=\"data row35 col2\" >21.197910</td>\n",
+       "      <td id=\"T_f9ded_row35_col3\" class=\"data row35 col3\" >12.019945</td>\n",
+       "      <td id=\"T_f9ded_row35_col4\" class=\"data row35 col4\" >66</td>\n",
+       "      <td id=\"T_f9ded_row35_col5\" class=\"data row35 col5\" >39</td>\n",
+       "      <td id=\"T_f9ded_row35_col6\" class=\"data row35 col6\" >27</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row36\" class=\"row_heading level0 row36\" >LMCocktail-10.7B-v1</th>\n",
+       "      <td id=\"T_f9ded_row36_col0\" class=\"data row36 col0\" >1203</td>\n",
+       "      <td id=\"T_f9ded_row36_col1\" class=\"data row36 col1\" >13.153431</td>\n",
+       "      <td id=\"T_f9ded_row36_col2\" class=\"data row36 col2\" >22.716773</td>\n",
+       "      <td id=\"T_f9ded_row36_col3\" class=\"data row36 col3\" >9.563342</td>\n",
+       "      <td id=\"T_f9ded_row36_col4\" class=\"data row36 col4\" >42</td>\n",
+       "      <td id=\"T_f9ded_row36_col5\" class=\"data row36 col5\" >35</td>\n",
+       "      <td id=\"T_f9ded_row36_col6\" class=\"data row36 col6\" >7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row37\" class=\"row_heading level0 row37\" >internlm2-chat-20b-ppo</th>\n",
+       "      <td id=\"T_f9ded_row37_col0\" class=\"data row37 col0\" >2373</td>\n",
+       "      <td id=\"T_f9ded_row37_col1\" class=\"data row37 col1\" >21.749155</td>\n",
+       "      <td id=\"T_f9ded_row37_col2\" class=\"data row37 col2\" >20.927878</td>\n",
+       "      <td id=\"T_f9ded_row37_col3\" class=\"data row37 col3\" >-0.821277</td>\n",
+       "      <td id=\"T_f9ded_row37_col4\" class=\"data row37 col4\" >18</td>\n",
+       "      <td id=\"T_f9ded_row37_col5\" class=\"data row37 col5\" >41</td>\n",
+       "      <td id=\"T_f9ded_row37_col6\" class=\"data row37 col6\" >-23</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row38\" class=\"row_heading level0 row38\" >claude-2.1_concise</th>\n",
+       "      <td id=\"T_f9ded_row38_col0\" class=\"data row38 col0\" >573</td>\n",
+       "      <td id=\"T_f9ded_row38_col1\" class=\"data row38 col1\" >9.227125</td>\n",
+       "      <td id=\"T_f9ded_row38_col2\" class=\"data row38 col2\" >19.030658</td>\n",
+       "      <td id=\"T_f9ded_row38_col3\" class=\"data row38 col3\" >9.803532</td>\n",
+       "      <td id=\"T_f9ded_row38_col4\" class=\"data row38 col4\" >65</td>\n",
+       "      <td id=\"T_f9ded_row38_col5\" class=\"data row38 col5\" >47</td>\n",
+       "      <td id=\"T_f9ded_row38_col6\" class=\"data row38 col6\" >18</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row39\" class=\"row_heading level0 row39\" >gpt-3.5-turbo-0301</th>\n",
+       "      <td id=\"T_f9ded_row39_col0\" class=\"data row39 col0\" >827</td>\n",
+       "      <td id=\"T_f9ded_row39_col1\" class=\"data row39 col1\" >9.622453</td>\n",
+       "      <td id=\"T_f9ded_row39_col2\" class=\"data row39 col2\" >21.634439</td>\n",
+       "      <td id=\"T_f9ded_row39_col3\" class=\"data row39 col3\" >12.011986</td>\n",
+       "      <td id=\"T_f9ded_row39_col4\" class=\"data row39 col4\" >60</td>\n",
+       "      <td id=\"T_f9ded_row39_col5\" class=\"data row39 col5\" >38</td>\n",
+       "      <td id=\"T_f9ded_row39_col6\" class=\"data row39 col6\" >22</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row40\" class=\"row_heading level0 row40\" >xwinlm-13b-v0.1</th>\n",
+       "      <td id=\"T_f9ded_row40_col0\" class=\"data row40 col0\" >1894</td>\n",
+       "      <td id=\"T_f9ded_row40_col1\" class=\"data row40 col1\" >17.427935</td>\n",
+       "      <td id=\"T_f9ded_row40_col2\" class=\"data row40 col2\" >18.845262</td>\n",
+       "      <td id=\"T_f9ded_row40_col3\" class=\"data row40 col3\" >1.417327</td>\n",
+       "      <td id=\"T_f9ded_row40_col4\" class=\"data row40 col4\" >24</td>\n",
+       "      <td id=\"T_f9ded_row40_col5\" class=\"data row40 col5\" >48</td>\n",
+       "      <td id=\"T_f9ded_row40_col6\" class=\"data row40 col6\" >-24</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row41\" class=\"row_heading level0 row41\" >deepseek-llm-67b-chat</th>\n",
+       "      <td id=\"T_f9ded_row41_col0\" class=\"data row41 col0\" >1151</td>\n",
+       "      <td id=\"T_f9ded_row41_col1\" class=\"data row41 col1\" >12.093422</td>\n",
+       "      <td id=\"T_f9ded_row41_col2\" class=\"data row41 col2\" >21.888822</td>\n",
+       "      <td id=\"T_f9ded_row41_col3\" class=\"data row41 col3\" >9.795400</td>\n",
+       "      <td id=\"T_f9ded_row41_col4\" class=\"data row41 col4\" >48</td>\n",
+       "      <td id=\"T_f9ded_row41_col5\" class=\"data row41 col5\" >37</td>\n",
+       "      <td id=\"T_f9ded_row41_col6\" class=\"data row41 col6\" >11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row42\" class=\"row_heading level0 row42\" >gpt35_turbo_instruct</th>\n",
+       "      <td id=\"T_f9ded_row42_col0\" class=\"data row42 col0\" >1018</td>\n",
+       "      <td id=\"T_f9ded_row42_col1\" class=\"data row42 col1\" >8.462447</td>\n",
+       "      <td id=\"T_f9ded_row42_col2\" class=\"data row42 col2\" >14.933606</td>\n",
+       "      <td id=\"T_f9ded_row42_col3\" class=\"data row42 col3\" >6.471160</td>\n",
+       "      <td id=\"T_f9ded_row42_col4\" class=\"data row42 col4\" >70</td>\n",
+       "      <td id=\"T_f9ded_row42_col5\" class=\"data row42 col5\" >69</td>\n",
+       "      <td id=\"T_f9ded_row42_col6\" class=\"data row42 col6\" >1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row43\" class=\"row_heading level0 row43\" >wizardlm-70b</th>\n",
+       "      <td id=\"T_f9ded_row43_col0\" class=\"data row43 col0\" >1545</td>\n",
+       "      <td id=\"T_f9ded_row43_col1\" class=\"data row43 col1\" >14.383896</td>\n",
+       "      <td id=\"T_f9ded_row43_col2\" class=\"data row43 col2\" >18.441779</td>\n",
+       "      <td id=\"T_f9ded_row43_col3\" class=\"data row43 col3\" >4.057883</td>\n",
+       "      <td id=\"T_f9ded_row43_col4\" class=\"data row43 col4\" >34</td>\n",
+       "      <td id=\"T_f9ded_row43_col5\" class=\"data row43 col5\" >49</td>\n",
+       "      <td id=\"T_f9ded_row43_col6\" class=\"data row43 col6\" >-15</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row44\" class=\"row_heading level0 row44\" >vicuna-33b-v1.3</th>\n",
+       "      <td id=\"T_f9ded_row44_col0\" class=\"data row44 col0\" >1479</td>\n",
+       "      <td id=\"T_f9ded_row44_col1\" class=\"data row44 col1\" >12.705948</td>\n",
+       "      <td id=\"T_f9ded_row44_col2\" class=\"data row44 col2\" >18.269349</td>\n",
+       "      <td id=\"T_f9ded_row44_col3\" class=\"data row44 col3\" >5.563401</td>\n",
+       "      <td id=\"T_f9ded_row44_col4\" class=\"data row44 col4\" >46</td>\n",
+       "      <td id=\"T_f9ded_row44_col5\" class=\"data row44 col5\" >50</td>\n",
+       "      <td id=\"T_f9ded_row44_col6\" class=\"data row44 col6\" >-4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row45\" class=\"row_heading level0 row45\" >pairrm-tulu-2-13b</th>\n",
+       "      <td id=\"T_f9ded_row45_col0\" class=\"data row45 col0\" >1454</td>\n",
+       "      <td id=\"T_f9ded_row45_col1\" class=\"data row45 col1\" >13.831901</td>\n",
+       "      <td id=\"T_f9ded_row45_col2\" class=\"data row45 col2\" >20.187366</td>\n",
+       "      <td id=\"T_f9ded_row45_col3\" class=\"data row45 col3\" >6.355465</td>\n",
+       "      <td id=\"T_f9ded_row45_col4\" class=\"data row45 col4\" >40</td>\n",
+       "      <td id=\"T_f9ded_row45_col5\" class=\"data row45 col5\" >43</td>\n",
+       "      <td id=\"T_f9ded_row45_col6\" class=\"data row45 col6\" >-3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row46\" class=\"row_heading level0 row46\" >Mistral-7B-Instruct-v0.2</th>\n",
+       "      <td id=\"T_f9ded_row46_col0\" class=\"data row46 col0\" >1676</td>\n",
+       "      <td id=\"T_f9ded_row46_col1\" class=\"data row46 col1\" >14.722773</td>\n",
+       "      <td id=\"T_f9ded_row46_col2\" class=\"data row46 col2\" >17.503610</td>\n",
+       "      <td id=\"T_f9ded_row46_col3\" class=\"data row46 col3\" >2.780837</td>\n",
+       "      <td id=\"T_f9ded_row46_col4\" class=\"data row46 col4\" >33</td>\n",
+       "      <td id=\"T_f9ded_row46_col5\" class=\"data row46 col5\" >53</td>\n",
+       "      <td id=\"T_f9ded_row46_col6\" class=\"data row46 col6\" >-20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row47\" class=\"row_heading level0 row47\" >evo-7b</th>\n",
+       "      <td id=\"T_f9ded_row47_col0\" class=\"data row47 col0\" >1774</td>\n",
+       "      <td id=\"T_f9ded_row47_col1\" class=\"data row47 col1\" >15.577437</td>\n",
+       "      <td id=\"T_f9ded_row47_col2\" class=\"data row47 col2\" >17.702745</td>\n",
+       "      <td id=\"T_f9ded_row47_col3\" class=\"data row47 col3\" >2.125307</td>\n",
+       "      <td id=\"T_f9ded_row47_col4\" class=\"data row47 col4\" >32</td>\n",
+       "      <td id=\"T_f9ded_row47_col5\" class=\"data row47 col5\" >52</td>\n",
+       "      <td id=\"T_f9ded_row47_col6\" class=\"data row47 col6\" >-20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row48\" class=\"row_heading level0 row48\" >humpback-llama2-70b</th>\n",
+       "      <td id=\"T_f9ded_row48_col0\" class=\"data row48 col0\" >1107</td>\n",
+       "      <td id=\"T_f9ded_row48_col1\" class=\"data row48 col1\" >10.121772</td>\n",
+       "      <td id=\"T_f9ded_row48_col2\" class=\"data row48 col2\" >19.416493</td>\n",
+       "      <td id=\"T_f9ded_row48_col3\" class=\"data row48 col3\" >9.294722</td>\n",
+       "      <td id=\"T_f9ded_row48_col4\" class=\"data row48 col4\" >58</td>\n",
+       "      <td id=\"T_f9ded_row48_col5\" class=\"data row48 col5\" >46</td>\n",
+       "      <td id=\"T_f9ded_row48_col6\" class=\"data row48 col6\" >12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row49\" class=\"row_heading level0 row49\" >OpenHermes-2.5-Mistral-7B</th>\n",
+       "      <td id=\"T_f9ded_row49_col0\" class=\"data row49 col0\" >1107</td>\n",
+       "      <td id=\"T_f9ded_row49_col1\" class=\"data row49 col1\" >10.340416</td>\n",
+       "      <td id=\"T_f9ded_row49_col2\" class=\"data row49 col2\" >16.352879</td>\n",
+       "      <td id=\"T_f9ded_row49_col3\" class=\"data row49 col3\" >6.012464</td>\n",
+       "      <td id=\"T_f9ded_row49_col4\" class=\"data row49 col4\" >57</td>\n",
+       "      <td id=\"T_f9ded_row49_col5\" class=\"data row49 col5\" >59</td>\n",
+       "      <td id=\"T_f9ded_row49_col6\" class=\"data row49 col6\" >-2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row50\" class=\"row_heading level0 row50\" >deita-7b-v1.0</th>\n",
+       "      <td id=\"T_f9ded_row50_col0\" class=\"data row50 col0\" >1417</td>\n",
+       "      <td id=\"T_f9ded_row50_col1\" class=\"data row50 col1\" >12.646639</td>\n",
+       "      <td id=\"T_f9ded_row50_col2\" class=\"data row50 col2\" >19.855339</td>\n",
+       "      <td id=\"T_f9ded_row50_col3\" class=\"data row50 col3\" >7.208699</td>\n",
+       "      <td id=\"T_f9ded_row50_col4\" class=\"data row50 col4\" >47</td>\n",
+       "      <td id=\"T_f9ded_row50_col5\" class=\"data row50 col5\" >44</td>\n",
+       "      <td id=\"T_f9ded_row50_col6\" class=\"data row50 col6\" >3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row51\" class=\"row_heading level0 row51\" >jina-chat</th>\n",
+       "      <td id=\"T_f9ded_row51_col0\" class=\"data row51 col0\" >676</td>\n",
+       "      <td id=\"T_f9ded_row51_col1\" class=\"data row51 col1\" >7.786130</td>\n",
+       "      <td id=\"T_f9ded_row51_col2\" class=\"data row51 col2\" >21.063020</td>\n",
+       "      <td id=\"T_f9ded_row51_col3\" class=\"data row51 col3\" >13.276889</td>\n",
+       "      <td id=\"T_f9ded_row51_col4\" class=\"data row51 col4\" >76</td>\n",
+       "      <td id=\"T_f9ded_row51_col5\" class=\"data row51 col5\" >40</td>\n",
+       "      <td id=\"T_f9ded_row51_col6\" class=\"data row51 col6\" >36</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row52\" class=\"row_heading level0 row52\" >gpt-3.5-turbo-1106_concise</th>\n",
+       "      <td id=\"T_f9ded_row52_col0\" class=\"data row52 col0\" >431</td>\n",
+       "      <td id=\"T_f9ded_row52_col1\" class=\"data row52 col1\" >7.415865</td>\n",
+       "      <td id=\"T_f9ded_row52_col2\" class=\"data row52 col2\" >29.490736</td>\n",
+       "      <td id=\"T_f9ded_row52_col3\" class=\"data row52 col3\" >22.074871</td>\n",
+       "      <td id=\"T_f9ded_row52_col4\" class=\"data row52 col4\" >84</td>\n",
+       "      <td id=\"T_f9ded_row52_col5\" class=\"data row52 col5\" >20</td>\n",
+       "      <td id=\"T_f9ded_row52_col6\" class=\"data row52 col6\" >64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row53\" class=\"row_heading level0 row53\" >causallm-14b</th>\n",
+       "      <td id=\"T_f9ded_row53_col0\" class=\"data row53 col0\" >1391</td>\n",
+       "      <td id=\"T_f9ded_row53_col1\" class=\"data row53 col1\" >11.146161</td>\n",
+       "      <td id=\"T_f9ded_row53_col2\" class=\"data row53 col2\" >15.225911</td>\n",
+       "      <td id=\"T_f9ded_row53_col3\" class=\"data row53 col3\" >4.079750</td>\n",
+       "      <td id=\"T_f9ded_row53_col4\" class=\"data row53 col4\" >53</td>\n",
+       "      <td id=\"T_f9ded_row53_col5\" class=\"data row53 col5\" >68</td>\n",
+       "      <td id=\"T_f9ded_row53_col6\" class=\"data row53 col6\" >-15</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row54\" class=\"row_heading level0 row54\" >pairrm-zephyr-7b-beta</th>\n",
+       "      <td id=\"T_f9ded_row54_col0\" class=\"data row54 col0\" >1487</td>\n",
+       "      <td id=\"T_f9ded_row54_col1\" class=\"data row54 col1\" >12.841278</td>\n",
+       "      <td id=\"T_f9ded_row54_col2\" class=\"data row54 col2\" >18.046105</td>\n",
+       "      <td id=\"T_f9ded_row54_col3\" class=\"data row54 col3\" >5.204827</td>\n",
+       "      <td id=\"T_f9ded_row54_col4\" class=\"data row54 col4\" >44</td>\n",
+       "      <td id=\"T_f9ded_row54_col5\" class=\"data row54 col5\" >51</td>\n",
+       "      <td id=\"T_f9ded_row54_col6\" class=\"data row54 col6\" >-7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row55\" class=\"row_heading level0 row55\" >Starling-LM-7B-alpha</th>\n",
+       "      <td id=\"T_f9ded_row55_col0\" class=\"data row55 col0\" >1895</td>\n",
+       "      <td id=\"T_f9ded_row55_col1\" class=\"data row55 col1\" >14.245924</td>\n",
+       "      <td id=\"T_f9ded_row55_col2\" class=\"data row55 col2\" >15.838749</td>\n",
+       "      <td id=\"T_f9ded_row55_col3\" class=\"data row55 col3\" >1.592826</td>\n",
+       "      <td id=\"T_f9ded_row55_col4\" class=\"data row55 col4\" >35</td>\n",
+       "      <td id=\"T_f9ded_row55_col5\" class=\"data row55 col5\" >61</td>\n",
+       "      <td id=\"T_f9ded_row55_col6\" class=\"data row55 col6\" >-26</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row56\" class=\"row_heading level0 row56\" >llama-2-70b-chat-hf</th>\n",
+       "      <td id=\"T_f9ded_row56_col0\" class=\"data row56 col0\" >1790</td>\n",
+       "      <td id=\"T_f9ded_row56_col1\" class=\"data row56 col1\" >13.888258</td>\n",
+       "      <td id=\"T_f9ded_row56_col2\" class=\"data row56 col2\" >16.317284</td>\n",
+       "      <td id=\"T_f9ded_row56_col3\" class=\"data row56 col3\" >2.429026</td>\n",
+       "      <td id=\"T_f9ded_row56_col4\" class=\"data row56 col4\" >38</td>\n",
+       "      <td id=\"T_f9ded_row56_col5\" class=\"data row56 col5\" >60</td>\n",
+       "      <td id=\"T_f9ded_row56_col6\" class=\"data row56 col6\" >-22</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row57\" class=\"row_heading level0 row57\" >openchat-v3.1-13b</th>\n",
+       "      <td id=\"T_f9ded_row57_col0\" class=\"data row57 col0\" >1484</td>\n",
+       "      <td id=\"T_f9ded_row57_col1\" class=\"data row57 col1\" >11.082230</td>\n",
+       "      <td id=\"T_f9ded_row57_col2\" class=\"data row57 col2\" >16.885199</td>\n",
+       "      <td id=\"T_f9ded_row57_col3\" class=\"data row57 col3\" >5.802969</td>\n",
+       "      <td id=\"T_f9ded_row57_col4\" class=\"data row57 col4\" >54</td>\n",
+       "      <td id=\"T_f9ded_row57_col5\" class=\"data row57 col5\" >54</td>\n",
+       "      <td id=\"T_f9ded_row57_col6\" class=\"data row57 col6\" >0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row58\" class=\"row_heading level0 row58\" >wizardlm-13b-v1.2</th>\n",
+       "      <td id=\"T_f9ded_row58_col0\" class=\"data row58 col0\" >1635</td>\n",
+       "      <td id=\"T_f9ded_row58_col1\" class=\"data row58 col1\" >12.027480</td>\n",
+       "      <td id=\"T_f9ded_row58_col2\" class=\"data row58 col2\" >15.578715</td>\n",
+       "      <td id=\"T_f9ded_row58_col3\" class=\"data row58 col3\" >3.551234</td>\n",
+       "      <td id=\"T_f9ded_row58_col4\" class=\"data row58 col4\" >49</td>\n",
+       "      <td id=\"T_f9ded_row58_col5\" class=\"data row58 col5\" >64</td>\n",
+       "      <td id=\"T_f9ded_row58_col6\" class=\"data row58 col6\" >-15</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row59\" class=\"row_heading level0 row59\" >ultralm-13b-v2.0-best-of-16</th>\n",
+       "      <td id=\"T_f9ded_row59_col0\" class=\"data row59 col0\" >1720</td>\n",
+       "      <td id=\"T_f9ded_row59_col1\" class=\"data row59 col1\" >13.853373</td>\n",
+       "      <td id=\"T_f9ded_row59_col2\" class=\"data row59 col2\" >16.749030</td>\n",
+       "      <td id=\"T_f9ded_row59_col3\" class=\"data row59 col3\" >2.895657</td>\n",
+       "      <td id=\"T_f9ded_row59_col4\" class=\"data row59 col4\" >39</td>\n",
+       "      <td id=\"T_f9ded_row59_col5\" class=\"data row59 col5\" >55</td>\n",
+       "      <td id=\"T_f9ded_row59_col6\" class=\"data row59 col6\" >-16</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row60\" class=\"row_heading level0 row60\" >wizardlm-13b-v1.1</th>\n",
+       "      <td id=\"T_f9ded_row60_col0\" class=\"data row60 col0\" >1525</td>\n",
+       "      <td id=\"T_f9ded_row60_col1\" class=\"data row60 col1\" >11.233910</td>\n",
+       "      <td id=\"T_f9ded_row60_col2\" class=\"data row60 col2\" >15.777430</td>\n",
+       "      <td id=\"T_f9ded_row60_col3\" class=\"data row60 col3\" >4.543520</td>\n",
+       "      <td id=\"T_f9ded_row60_col4\" class=\"data row60 col4\" >52</td>\n",
+       "      <td id=\"T_f9ded_row60_col5\" class=\"data row60 col5\" >62</td>\n",
+       "      <td id=\"T_f9ded_row60_col6\" class=\"data row60 col6\" >-10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row61\" class=\"row_heading level0 row61\" >zephyr-7b-beta</th>\n",
+       "      <td id=\"T_f9ded_row61_col0\" class=\"data row61 col0\" >1444</td>\n",
+       "      <td id=\"T_f9ded_row61_col1\" class=\"data row61 col1\" >10.992886</td>\n",
+       "      <td id=\"T_f9ded_row61_col2\" class=\"data row61 col2\" >14.824691</td>\n",
+       "      <td id=\"T_f9ded_row61_col3\" class=\"data row61 col3\" >3.831805</td>\n",
+       "      <td id=\"T_f9ded_row61_col4\" class=\"data row61 col4\" >55</td>\n",
+       "      <td id=\"T_f9ded_row61_col5\" class=\"data row61 col5\" >70</td>\n",
+       "      <td id=\"T_f9ded_row61_col6\" class=\"data row61 col6\" >-15</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row62\" class=\"row_heading level0 row62\" >dolphin-2.2.1-mistral-7b</th>\n",
+       "      <td id=\"T_f9ded_row62_col0\" class=\"data row62 col0\" >1130</td>\n",
+       "      <td id=\"T_f9ded_row62_col1\" class=\"data row62 col1\" >9.039800</td>\n",
+       "      <td id=\"T_f9ded_row62_col2\" class=\"data row62 col2\" >13.974427</td>\n",
+       "      <td id=\"T_f9ded_row62_col3\" class=\"data row62 col3\" >4.934628</td>\n",
+       "      <td id=\"T_f9ded_row62_col4\" class=\"data row62 col4\" >68</td>\n",
+       "      <td id=\"T_f9ded_row62_col5\" class=\"data row62 col5\" >75</td>\n",
+       "      <td id=\"T_f9ded_row62_col6\" class=\"data row62 col6\" >-7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row63\" class=\"row_heading level0 row63\" >humpback-llama-65b</th>\n",
+       "      <td id=\"T_f9ded_row63_col0\" class=\"data row63 col0\" >1232</td>\n",
+       "      <td id=\"T_f9ded_row63_col1\" class=\"data row63 col1\" >9.425139</td>\n",
+       "      <td id=\"T_f9ded_row63_col2\" class=\"data row63 col2\" >15.277149</td>\n",
+       "      <td id=\"T_f9ded_row63_col3\" class=\"data row63 col3\" >5.852010</td>\n",
+       "      <td id=\"T_f9ded_row63_col4\" class=\"data row63 col4\" >62</td>\n",
+       "      <td id=\"T_f9ded_row63_col5\" class=\"data row63 col5\" >67</td>\n",
+       "      <td id=\"T_f9ded_row63_col6\" class=\"data row63 col6\" >-5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row64\" class=\"row_heading level0 row64\" >openbuddy-llama2-70b-v10.1</th>\n",
+       "      <td id=\"T_f9ded_row64_col0\" class=\"data row64 col0\" >1077</td>\n",
+       "      <td id=\"T_f9ded_row64_col1\" class=\"data row64 col1\" >8.096422</td>\n",
+       "      <td id=\"T_f9ded_row64_col2\" class=\"data row64 col2\" >13.879050</td>\n",
+       "      <td id=\"T_f9ded_row64_col3\" class=\"data row64 col3\" >5.782628</td>\n",
+       "      <td id=\"T_f9ded_row64_col4\" class=\"data row64 col4\" >74</td>\n",
+       "      <td id=\"T_f9ded_row64_col5\" class=\"data row64 col5\" >76</td>\n",
+       "      <td id=\"T_f9ded_row64_col6\" class=\"data row64 col6\" >-2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row65\" class=\"row_heading level0 row65\" >openbuddy-llama-65b-v8</th>\n",
+       "      <td id=\"T_f9ded_row65_col0\" class=\"data row65 col0\" >1162</td>\n",
+       "      <td id=\"T_f9ded_row65_col1\" class=\"data row65 col1\" >8.770650</td>\n",
+       "      <td id=\"T_f9ded_row65_col2\" class=\"data row65 col2\" >16.487347</td>\n",
+       "      <td id=\"T_f9ded_row65_col3\" class=\"data row65 col3\" >7.716697</td>\n",
+       "      <td id=\"T_f9ded_row65_col4\" class=\"data row65 col4\" >69</td>\n",
+       "      <td id=\"T_f9ded_row65_col5\" class=\"data row65 col5\" >57</td>\n",
+       "      <td id=\"T_f9ded_row65_col6\" class=\"data row65 col6\" >12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row66\" class=\"row_heading level0 row66\" >Qwen-14B-Chat</th>\n",
+       "      <td id=\"T_f9ded_row66_col0\" class=\"data row66 col0\" >1013</td>\n",
+       "      <td id=\"T_f9ded_row66_col1\" class=\"data row66 col1\" >7.502333</td>\n",
+       "      <td id=\"T_f9ded_row66_col2\" class=\"data row66 col2\" >19.464203</td>\n",
+       "      <td id=\"T_f9ded_row66_col3\" class=\"data row66 col3\" >11.961870</td>\n",
+       "      <td id=\"T_f9ded_row66_col4\" class=\"data row66 col4\" >81</td>\n",
+       "      <td id=\"T_f9ded_row66_col5\" class=\"data row66 col5\" >45</td>\n",
+       "      <td id=\"T_f9ded_row66_col6\" class=\"data row66 col6\" >36</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row67\" class=\"row_heading level0 row67\" >gpt4_gamed</th>\n",
+       "      <td id=\"T_f9ded_row67_col0\" class=\"data row67 col0\" >68</td>\n",
+       "      <td id=\"T_f9ded_row67_col1\" class=\"data row67 col1\" >3.738337</td>\n",
+       "      <td id=\"T_f9ded_row67_col2\" class=\"data row67 col2\" >44.532377</td>\n",
+       "      <td id=\"T_f9ded_row67_col3\" class=\"data row67 col3\" >40.794040</td>\n",
+       "      <td id=\"T_f9ded_row67_col4\" class=\"data row67 col4\" >112</td>\n",
+       "      <td id=\"T_f9ded_row67_col5\" class=\"data row67 col5\" >2</td>\n",
+       "      <td id=\"T_f9ded_row67_col6\" class=\"data row67 col6\" >110</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row68\" class=\"row_heading level0 row68\" >cut-13b</th>\n",
+       "      <td id=\"T_f9ded_row68_col0\" class=\"data row68 col0\" >1637</td>\n",
+       "      <td id=\"T_f9ded_row68_col1\" class=\"data row68 col1\" >10.779089</td>\n",
+       "      <td id=\"T_f9ded_row68_col2\" class=\"data row68 col2\" >14.074431</td>\n",
+       "      <td id=\"T_f9ded_row68_col3\" class=\"data row68 col3\" >3.295342</td>\n",
+       "      <td id=\"T_f9ded_row68_col4\" class=\"data row68 col4\" >56</td>\n",
+       "      <td id=\"T_f9ded_row68_col5\" class=\"data row68 col5\" >74</td>\n",
+       "      <td id=\"T_f9ded_row68_col6\" class=\"data row68 col6\" >-18</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row69\" class=\"row_heading level0 row69\" >openchat-v2-w-13b</th>\n",
+       "      <td id=\"T_f9ded_row69_col0\" class=\"data row69 col0\" >1566</td>\n",
+       "      <td id=\"T_f9ded_row69_col1\" class=\"data row69 col1\" >9.615344</td>\n",
+       "      <td id=\"T_f9ded_row69_col2\" class=\"data row69 col2\" >14.106426</td>\n",
+       "      <td id=\"T_f9ded_row69_col3\" class=\"data row69 col3\" >4.491082</td>\n",
+       "      <td id=\"T_f9ded_row69_col4\" class=\"data row69 col4\" >61</td>\n",
+       "      <td id=\"T_f9ded_row69_col5\" class=\"data row69 col5\" >73</td>\n",
+       "      <td id=\"T_f9ded_row69_col6\" class=\"data row69 col6\" >-12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row70\" class=\"row_heading level0 row70\" >tulu-2-dpo-13b</th>\n",
+       "      <td id=\"T_f9ded_row70_col0\" class=\"data row70 col0\" >1614</td>\n",
+       "      <td id=\"T_f9ded_row70_col1\" class=\"data row70 col1\" >10.119788</td>\n",
+       "      <td id=\"T_f9ded_row70_col2\" class=\"data row70 col2\" >15.521773</td>\n",
+       "      <td id=\"T_f9ded_row70_col3\" class=\"data row70 col3\" >5.401985</td>\n",
+       "      <td id=\"T_f9ded_row70_col4\" class=\"data row70 col4\" >59</td>\n",
+       "      <td id=\"T_f9ded_row70_col5\" class=\"data row70 col5\" >65</td>\n",
+       "      <td id=\"T_f9ded_row70_col6\" class=\"data row70 col6\" >-6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row71\" class=\"row_heading level0 row71\" >claude2-alpaca-13b</th>\n",
+       "      <td id=\"T_f9ded_row71_col0\" class=\"data row71 col0\" >1127</td>\n",
+       "      <td id=\"T_f9ded_row71_col1\" class=\"data row71 col1\" >7.437351</td>\n",
+       "      <td id=\"T_f9ded_row71_col2\" class=\"data row71 col2\" >16.733107</td>\n",
+       "      <td id=\"T_f9ded_row71_col3\" class=\"data row71 col3\" >9.295755</td>\n",
+       "      <td id=\"T_f9ded_row71_col4\" class=\"data row71 col4\" >83</td>\n",
+       "      <td id=\"T_f9ded_row71_col5\" class=\"data row71 col5\" >56</td>\n",
+       "      <td id=\"T_f9ded_row71_col6\" class=\"data row71 col6\" >27</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row72\" class=\"row_heading level0 row72\" >minotaur-13b</th>\n",
+       "      <td id=\"T_f9ded_row72_col0\" class=\"data row72 col0\" >881</td>\n",
+       "      <td id=\"T_f9ded_row72_col1\" class=\"data row72 col1\" >5.738964</td>\n",
+       "      <td id=\"T_f9ded_row72_col2\" class=\"data row72 col2\" >16.471708</td>\n",
+       "      <td id=\"T_f9ded_row72_col3\" class=\"data row72 col3\" >10.732744</td>\n",
+       "      <td id=\"T_f9ded_row72_col4\" class=\"data row72 col4\" >100</td>\n",
+       "      <td id=\"T_f9ded_row72_col5\" class=\"data row72 col5\" >58</td>\n",
+       "      <td id=\"T_f9ded_row72_col6\" class=\"data row72 col6\" >42</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row73\" class=\"row_heading level0 row73\" >airoboros-65b</th>\n",
+       "      <td id=\"T_f9ded_row73_col0\" class=\"data row73 col0\" >1512</td>\n",
+       "      <td id=\"T_f9ded_row73_col1\" class=\"data row73 col1\" >9.388950</td>\n",
+       "      <td id=\"T_f9ded_row73_col2\" class=\"data row73 col2\" >13.035846</td>\n",
+       "      <td id=\"T_f9ded_row73_col3\" class=\"data row73 col3\" >3.646896</td>\n",
+       "      <td id=\"T_f9ded_row73_col4\" class=\"data row73 col4\" >64</td>\n",
+       "      <td id=\"T_f9ded_row73_col5\" class=\"data row73 col5\" >83</td>\n",
+       "      <td id=\"T_f9ded_row73_col6\" class=\"data row73 col6\" >-19</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row74\" class=\"row_heading level0 row74\" >cohere</th>\n",
+       "      <td id=\"T_f9ded_row74_col0\" class=\"data row74 col0\" >1983</td>\n",
+       "      <td id=\"T_f9ded_row74_col1\" class=\"data row74 col1\" >12.901455</td>\n",
+       "      <td id=\"T_f9ded_row74_col2\" class=\"data row74 col2\" >13.147459</td>\n",
+       "      <td id=\"T_f9ded_row74_col3\" class=\"data row74 col3\" >0.246004</td>\n",
+       "      <td id=\"T_f9ded_row74_col4\" class=\"data row74 col4\" >43</td>\n",
+       "      <td id=\"T_f9ded_row74_col5\" class=\"data row74 col5\" >81</td>\n",
+       "      <td id=\"T_f9ded_row74_col6\" class=\"data row74 col6\" >-38</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row75\" class=\"row_heading level0 row75\" >vicuna-13b-v1.3</th>\n",
+       "      <td id=\"T_f9ded_row75_col0\" class=\"data row75 col0\" >1132</td>\n",
+       "      <td id=\"T_f9ded_row75_col1\" class=\"data row75 col1\" >7.137240</td>\n",
+       "      <td id=\"T_f9ded_row75_col2\" class=\"data row75 col2\" >14.467847</td>\n",
+       "      <td id=\"T_f9ded_row75_col3\" class=\"data row75 col3\" >7.330607</td>\n",
+       "      <td id=\"T_f9ded_row75_col4\" class=\"data row75 col4\" >87</td>\n",
+       "      <td id=\"T_f9ded_row75_col5\" class=\"data row75 col5\" >72</td>\n",
+       "      <td id=\"T_f9ded_row75_col6\" class=\"data row75 col6\" >15</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row76\" class=\"row_heading level0 row76\" >xwinlm-7b-v0.1</th>\n",
+       "      <td id=\"T_f9ded_row76_col0\" class=\"data row76 col0\" >1894</td>\n",
+       "      <td id=\"T_f9ded_row76_col1\" class=\"data row76 col1\" >11.245652</td>\n",
+       "      <td id=\"T_f9ded_row76_col2\" class=\"data row76 col2\" >12.644308</td>\n",
+       "      <td id=\"T_f9ded_row76_col3\" class=\"data row76 col3\" >1.398656</td>\n",
+       "      <td id=\"T_f9ded_row76_col4\" class=\"data row76 col4\" >51</td>\n",
+       "      <td id=\"T_f9ded_row76_col5\" class=\"data row76 col5\" >86</td>\n",
+       "      <td id=\"T_f9ded_row76_col6\" class=\"data row76 col6\" >-35</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row77\" class=\"row_heading level0 row77\" >airoboros-33b</th>\n",
+       "      <td id=\"T_f9ded_row77_col0\" class=\"data row77 col0\" >1514</td>\n",
+       "      <td id=\"T_f9ded_row77_col1\" class=\"data row77 col1\" >9.053160</td>\n",
+       "      <td id=\"T_f9ded_row77_col2\" class=\"data row77 col2\" >12.840199</td>\n",
+       "      <td id=\"T_f9ded_row77_col3\" class=\"data row77 col3\" >3.787039</td>\n",
+       "      <td id=\"T_f9ded_row77_col4\" class=\"data row77 col4\" >67</td>\n",
+       "      <td id=\"T_f9ded_row77_col5\" class=\"data row77 col5\" >84</td>\n",
+       "      <td id=\"T_f9ded_row77_col6\" class=\"data row77 col6\" >-17</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row78\" class=\"row_heading level0 row78\" >platolm-7b</th>\n",
+       "      <td id=\"T_f9ded_row78_col0\" class=\"data row78 col0\" >1344</td>\n",
+       "      <td id=\"T_f9ded_row78_col1\" class=\"data row78 col1\" >6.320828</td>\n",
+       "      <td id=\"T_f9ded_row78_col2\" class=\"data row78 col2\" >11.443269</td>\n",
+       "      <td id=\"T_f9ded_row78_col3\" class=\"data row78 col3\" >5.122441</td>\n",
+       "      <td id=\"T_f9ded_row78_col4\" class=\"data row78 col4\" >93</td>\n",
+       "      <td id=\"T_f9ded_row78_col5\" class=\"data row78 col5\" >95</td>\n",
+       "      <td id=\"T_f9ded_row78_col6\" class=\"data row78 col6\" >-2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row79\" class=\"row_heading level0 row79\" >vicuna-13b-v1.5</th>\n",
+       "      <td id=\"T_f9ded_row79_col0\" class=\"data row79 col0\" >1061</td>\n",
+       "      <td id=\"T_f9ded_row79_col1\" class=\"data row79 col1\" >6.722122</td>\n",
+       "      <td id=\"T_f9ded_row79_col2\" class=\"data row79 col2\" >9.559231</td>\n",
+       "      <td id=\"T_f9ded_row79_col3\" class=\"data row79 col3\" >2.837109</td>\n",
+       "      <td id=\"T_f9ded_row79_col4\" class=\"data row79 col4\" >90</td>\n",
+       "      <td id=\"T_f9ded_row79_col5\" class=\"data row79 col5\" >106</td>\n",
+       "      <td id=\"T_f9ded_row79_col6\" class=\"data row79 col6\" >-16</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row80\" class=\"row_heading level0 row80\" >gemma-7b-it</th>\n",
+       "      <td id=\"T_f9ded_row80_col0\" class=\"data row80 col0\" >1115</td>\n",
+       "      <td id=\"T_f9ded_row80_col1\" class=\"data row80 col1\" >6.937294</td>\n",
+       "      <td id=\"T_f9ded_row80_col2\" class=\"data row80 col2\" >13.780013</td>\n",
+       "      <td id=\"T_f9ded_row80_col3\" class=\"data row80 col3\" >6.842719</td>\n",
+       "      <td id=\"T_f9ded_row80_col4\" class=\"data row80 col4\" >88</td>\n",
+       "      <td id=\"T_f9ded_row80_col5\" class=\"data row80 col5\" >78</td>\n",
+       "      <td id=\"T_f9ded_row80_col6\" class=\"data row80 col6\" >10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row81\" class=\"row_heading level0 row81\" >openchat-v2-13b</th>\n",
+       "      <td id=\"T_f9ded_row81_col0\" class=\"data row81 col0\" >1564</td>\n",
+       "      <td id=\"T_f9ded_row81_col1\" class=\"data row81 col1\" >8.435076</td>\n",
+       "      <td id=\"T_f9ded_row81_col2\" class=\"data row81 col2\" >10.921402</td>\n",
+       "      <td id=\"T_f9ded_row81_col3\" class=\"data row81 col3\" >2.486326</td>\n",
+       "      <td id=\"T_f9ded_row81_col4\" class=\"data row81 col4\" >71</td>\n",
+       "      <td id=\"T_f9ded_row81_col5\" class=\"data row81 col5\" >96</td>\n",
+       "      <td id=\"T_f9ded_row81_col6\" class=\"data row81 col6\" >-25</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row82\" class=\"row_heading level0 row82\" >zephyr-7b-alpha</th>\n",
+       "      <td id=\"T_f9ded_row82_col0\" class=\"data row82 col0\" >1302</td>\n",
+       "      <td id=\"T_f9ded_row82_col1\" class=\"data row82 col1\" >8.352664</td>\n",
+       "      <td id=\"T_f9ded_row82_col2\" class=\"data row82 col2\" >12.315627</td>\n",
+       "      <td id=\"T_f9ded_row82_col3\" class=\"data row82 col3\" >3.962963</td>\n",
+       "      <td id=\"T_f9ded_row82_col4\" class=\"data row82 col4\" >72</td>\n",
+       "      <td id=\"T_f9ded_row82_col5\" class=\"data row82 col5\" >88</td>\n",
+       "      <td id=\"T_f9ded_row82_col6\" class=\"data row82 col6\" >-16</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row83\" class=\"row_heading level0 row83\" >openbuddy-llama-30b-v7.1</th>\n",
+       "      <td id=\"T_f9ded_row83_col0\" class=\"data row83 col0\" >968</td>\n",
+       "      <td id=\"T_f9ded_row83_col1\" class=\"data row83 col1\" >6.130015</td>\n",
+       "      <td id=\"T_f9ded_row83_col2\" class=\"data row83 col2\" >13.506367</td>\n",
+       "      <td id=\"T_f9ded_row83_col3\" class=\"data row83 col3\" >7.376352</td>\n",
+       "      <td id=\"T_f9ded_row83_col4\" class=\"data row83 col4\" >96</td>\n",
+       "      <td id=\"T_f9ded_row83_col5\" class=\"data row83 col5\" >79</td>\n",
+       "      <td id=\"T_f9ded_row83_col6\" class=\"data row83 col6\" >17</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row84\" class=\"row_heading level0 row84\" >ultralm-13b-best-of-16</th>\n",
+       "      <td id=\"T_f9ded_row84_col0\" class=\"data row84 col0\" >1980</td>\n",
+       "      <td id=\"T_f9ded_row84_col1\" class=\"data row84 col1\" >11.307315</td>\n",
+       "      <td id=\"T_f9ded_row84_col2\" class=\"data row84 col2\" >12.037139</td>\n",
+       "      <td id=\"T_f9ded_row84_col3\" class=\"data row84 col3\" >0.729824</td>\n",
+       "      <td id=\"T_f9ded_row84_col4\" class=\"data row84 col4\" >50</td>\n",
+       "      <td id=\"T_f9ded_row84_col5\" class=\"data row84 col5\" >90</td>\n",
+       "      <td id=\"T_f9ded_row84_col6\" class=\"data row84 col6\" >-40</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row85\" class=\"row_heading level0 row85\" >oasst-sft-llama-33b</th>\n",
+       "      <td id=\"T_f9ded_row85_col0\" class=\"data row85 col0\" >748</td>\n",
+       "      <td id=\"T_f9ded_row85_col1\" class=\"data row85 col1\" >4.770391</td>\n",
+       "      <td id=\"T_f9ded_row85_col2\" class=\"data row85 col2\" >12.742207</td>\n",
+       "      <td id=\"T_f9ded_row85_col3\" class=\"data row85 col3\" >7.971816</td>\n",
+       "      <td id=\"T_f9ded_row85_col4\" class=\"data row85 col4\" >106</td>\n",
+       "      <td id=\"T_f9ded_row85_col5\" class=\"data row85 col5\" >85</td>\n",
+       "      <td id=\"T_f9ded_row85_col6\" class=\"data row85 col6\" >21</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row86\" class=\"row_heading level0 row86\" >wizardlm-13b</th>\n",
+       "      <td id=\"T_f9ded_row86_col0\" class=\"data row86 col0\" >985</td>\n",
+       "      <td id=\"T_f9ded_row86_col1\" class=\"data row86 col1\" >5.878153</td>\n",
+       "      <td id=\"T_f9ded_row86_col2\" class=\"data row86 col2\" >13.845511</td>\n",
+       "      <td id=\"T_f9ded_row86_col3\" class=\"data row86 col3\" >7.967358</td>\n",
+       "      <td id=\"T_f9ded_row86_col4\" class=\"data row86 col4\" >98</td>\n",
+       "      <td id=\"T_f9ded_row86_col5\" class=\"data row86 col5\" >77</td>\n",
+       "      <td id=\"T_f9ded_row86_col6\" class=\"data row86 col6\" >21</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row87\" class=\"row_heading level0 row87\" >nous-hermes-13b</th>\n",
+       "      <td id=\"T_f9ded_row87_col0\" class=\"data row87 col0\" >844</td>\n",
+       "      <td id=\"T_f9ded_row87_col1\" class=\"data row87 col1\" >5.411879</td>\n",
+       "      <td id=\"T_f9ded_row87_col2\" class=\"data row87 col2\" >14.553850</td>\n",
+       "      <td id=\"T_f9ded_row87_col3\" class=\"data row87 col3\" >9.141971</td>\n",
+       "      <td id=\"T_f9ded_row87_col4\" class=\"data row87 col4\" >101</td>\n",
+       "      <td id=\"T_f9ded_row87_col5\" class=\"data row87 col5\" >71</td>\n",
+       "      <td id=\"T_f9ded_row87_col6\" class=\"data row87 col6\" >30</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row88\" class=\"row_heading level0 row88\" >vicuna-13b</th>\n",
+       "      <td id=\"T_f9ded_row88_col0\" class=\"data row88 col0\" >1037</td>\n",
+       "      <td id=\"T_f9ded_row88_col1\" class=\"data row88 col1\" >5.831103</td>\n",
+       "      <td id=\"T_f9ded_row88_col2\" class=\"data row88 col2\" >12.121340</td>\n",
+       "      <td id=\"T_f9ded_row88_col3\" class=\"data row88 col3\" >6.290237</td>\n",
+       "      <td id=\"T_f9ded_row88_col4\" class=\"data row88 col4\" >99</td>\n",
+       "      <td id=\"T_f9ded_row88_col5\" class=\"data row88 col5\" >89</td>\n",
+       "      <td id=\"T_f9ded_row88_col6\" class=\"data row88 col6\" >10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row89\" class=\"row_heading level0 row89\" >tulu-2-dpo-7b</th>\n",
+       "      <td id=\"T_f9ded_row89_col0\" class=\"data row89 col0\" >1663</td>\n",
+       "      <td id=\"T_f9ded_row89_col1\" class=\"data row89 col1\" >8.197515</td>\n",
+       "      <td id=\"T_f9ded_row89_col2\" class=\"data row89 col2\" >13.475569</td>\n",
+       "      <td id=\"T_f9ded_row89_col3\" class=\"data row89 col3\" >5.278053</td>\n",
+       "      <td id=\"T_f9ded_row89_col4\" class=\"data row89 col4\" >73</td>\n",
+       "      <td id=\"T_f9ded_row89_col5\" class=\"data row89 col5\" >80</td>\n",
+       "      <td id=\"T_f9ded_row89_col6\" class=\"data row89 col6\" >-7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row90\" class=\"row_heading level0 row90\" >openbuddy-llama2-13b-v11.1</th>\n",
+       "      <td id=\"T_f9ded_row90_col0\" class=\"data row90 col0\" >1057</td>\n",
+       "      <td id=\"T_f9ded_row90_col1\" class=\"data row90 col1\" >6.174716</td>\n",
+       "      <td id=\"T_f9ded_row90_col2\" class=\"data row90 col2\" >15.665046</td>\n",
+       "      <td id=\"T_f9ded_row90_col3\" class=\"data row90 col3\" >9.490330</td>\n",
+       "      <td id=\"T_f9ded_row90_col4\" class=\"data row90 col4\" >95</td>\n",
+       "      <td id=\"T_f9ded_row90_col5\" class=\"data row90 col5\" >63</td>\n",
+       "      <td id=\"T_f9ded_row90_col6\" class=\"data row90 col6\" >32</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row91\" class=\"row_heading level0 row91\" >ultralm-13b-v2.0</th>\n",
+       "      <td id=\"T_f9ded_row91_col0\" class=\"data row91 col0\" >1399</td>\n",
+       "      <td id=\"T_f9ded_row91_col1\" class=\"data row91 col1\" >7.504623</td>\n",
+       "      <td id=\"T_f9ded_row91_col2\" class=\"data row91 col2\" >12.353613</td>\n",
+       "      <td id=\"T_f9ded_row91_col3\" class=\"data row91 col3\" >4.848990</td>\n",
+       "      <td id=\"T_f9ded_row91_col4\" class=\"data row91 col4\" >80</td>\n",
+       "      <td id=\"T_f9ded_row91_col5\" class=\"data row91 col5\" >87</td>\n",
+       "      <td id=\"T_f9ded_row91_col6\" class=\"data row91 col6\" >-7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row92\" class=\"row_heading level0 row92\" >text_davinci_001</th>\n",
+       "      <td id=\"T_f9ded_row92_col0\" class=\"data row92 col0\" >296</td>\n",
+       "      <td id=\"T_f9ded_row92_col1\" class=\"data row92 col1\" >2.764005</td>\n",
+       "      <td id=\"T_f9ded_row92_col2\" class=\"data row92 col2\" >8.565768</td>\n",
+       "      <td id=\"T_f9ded_row92_col3\" class=\"data row92 col3\" >5.801762</td>\n",
+       "      <td id=\"T_f9ded_row92_col4\" class=\"data row92 col4\" >122</td>\n",
+       "      <td id=\"T_f9ded_row92_col5\" class=\"data row92 col5\" >111</td>\n",
+       "      <td id=\"T_f9ded_row92_col6\" class=\"data row92 col6\" >11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row93\" class=\"row_heading level0 row93\" >openbuddy-falcon-40b-v9</th>\n",
+       "      <td id=\"T_f9ded_row93_col0\" class=\"data row93 col0\" >1089</td>\n",
+       "      <td id=\"T_f9ded_row93_col1\" class=\"data row93 col1\" >5.955743</td>\n",
+       "      <td id=\"T_f9ded_row93_col2\" class=\"data row93 col2\" >13.140887</td>\n",
+       "      <td id=\"T_f9ded_row93_col3\" class=\"data row93 col3\" >7.185144</td>\n",
+       "      <td id=\"T_f9ded_row93_col4\" class=\"data row93 col4\" >97</td>\n",
+       "      <td id=\"T_f9ded_row93_col5\" class=\"data row93 col5\" >82</td>\n",
+       "      <td id=\"T_f9ded_row93_col6\" class=\"data row93 col6\" >15</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row94\" class=\"row_heading level0 row94\" >openchat-13b</th>\n",
+       "      <td id=\"T_f9ded_row94_col0\" class=\"data row94 col0\" >1632</td>\n",
+       "      <td id=\"T_f9ded_row94_col1\" class=\"data row94 col1\" >8.022386</td>\n",
+       "      <td id=\"T_f9ded_row94_col2\" class=\"data row94 col2\" >10.899403</td>\n",
+       "      <td id=\"T_f9ded_row94_col3\" class=\"data row94 col3\" >2.877017</td>\n",
+       "      <td id=\"T_f9ded_row94_col4\" class=\"data row94 col4\" >75</td>\n",
+       "      <td id=\"T_f9ded_row94_col5\" class=\"data row94 col5\" >97</td>\n",
+       "      <td id=\"T_f9ded_row94_col6\" class=\"data row94 col6\" >-22</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row95\" class=\"row_heading level0 row95\" >llama-2-13b-chat-hf</th>\n",
+       "      <td id=\"T_f9ded_row95_col0\" class=\"data row95 col0\" >1513</td>\n",
+       "      <td id=\"T_f9ded_row95_col1\" class=\"data row95 col1\" >7.702310</td>\n",
+       "      <td id=\"T_f9ded_row95_col2\" class=\"data row95 col2\" >11.844717</td>\n",
+       "      <td id=\"T_f9ded_row95_col3\" class=\"data row95 col3\" >4.142407</td>\n",
+       "      <td id=\"T_f9ded_row95_col4\" class=\"data row95 col4\" >78</td>\n",
+       "      <td id=\"T_f9ded_row95_col5\" class=\"data row95 col5\" >91</td>\n",
+       "      <td id=\"T_f9ded_row95_col6\" class=\"data row95 col6\" >-13</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row96\" class=\"row_heading level0 row96\" >guanaco-65b</th>\n",
+       "      <td id=\"T_f9ded_row96_col0\" class=\"data row96 col0\" >1249</td>\n",
+       "      <td id=\"T_f9ded_row96_col1\" class=\"data row96 col1\" >6.858495</td>\n",
+       "      <td id=\"T_f9ded_row96_col2\" class=\"data row96 col2\" >11.653236</td>\n",
+       "      <td id=\"T_f9ded_row96_col3\" class=\"data row96 col3\" >4.794742</td>\n",
+       "      <td id=\"T_f9ded_row96_col4\" class=\"data row96 col4\" >89</td>\n",
+       "      <td id=\"T_f9ded_row96_col5\" class=\"data row96 col5\" >92</td>\n",
+       "      <td id=\"T_f9ded_row96_col6\" class=\"data row96 col6\" >-3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row97\" class=\"row_heading level0 row97\" >opencoderplus-15b</th>\n",
+       "      <td id=\"T_f9ded_row97_col0\" class=\"data row97 col0\" >1628</td>\n",
+       "      <td id=\"T_f9ded_row97_col1\" class=\"data row97 col1\" >7.406222</td>\n",
+       "      <td id=\"T_f9ded_row97_col2\" class=\"data row97 col2\" >9.927700</td>\n",
+       "      <td id=\"T_f9ded_row97_col3\" class=\"data row97 col3\" >2.521477</td>\n",
+       "      <td id=\"T_f9ded_row97_col4\" class=\"data row97 col4\" >85</td>\n",
+       "      <td id=\"T_f9ded_row97_col5\" class=\"data row97 col5\" >103</td>\n",
+       "      <td id=\"T_f9ded_row97_col6\" class=\"data row97 col6\" >-18</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row98\" class=\"row_heading level0 row98\" >oasst-rlhf-llama-33b</th>\n",
+       "      <td id=\"T_f9ded_row98_col0\" class=\"data row98 col0\" >1079</td>\n",
+       "      <td id=\"T_f9ded_row98_col1\" class=\"data row98 col1\" >6.296435</td>\n",
+       "      <td id=\"T_f9ded_row98_col2\" class=\"data row98 col2\" >10.199504</td>\n",
+       "      <td id=\"T_f9ded_row98_col3\" class=\"data row98 col3\" >3.903069</td>\n",
+       "      <td id=\"T_f9ded_row98_col4\" class=\"data row98 col4\" >94</td>\n",
+       "      <td id=\"T_f9ded_row98_col5\" class=\"data row98 col5\" >100</td>\n",
+       "      <td id=\"T_f9ded_row98_col6\" class=\"data row98 col6\" >-6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row99\" class=\"row_heading level0 row99\" >openchat8192-13b</th>\n",
+       "      <td id=\"T_f9ded_row99_col0\" class=\"data row99 col0\" >1664</td>\n",
+       "      <td id=\"T_f9ded_row99_col1\" class=\"data row99 col1\" >7.472767</td>\n",
+       "      <td id=\"T_f9ded_row99_col2\" class=\"data row99 col2\" >9.674293</td>\n",
+       "      <td id=\"T_f9ded_row99_col3\" class=\"data row99 col3\" >2.201526</td>\n",
+       "      <td id=\"T_f9ded_row99_col4\" class=\"data row99 col4\" >82</td>\n",
+       "      <td id=\"T_f9ded_row99_col5\" class=\"data row99 col5\" >105</td>\n",
+       "      <td id=\"T_f9ded_row99_col6\" class=\"data row99 col6\" >-23</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row100\" class=\"row_heading level0 row100\" >phi-2-dpo</th>\n",
+       "      <td id=\"T_f9ded_row100_col0\" class=\"data row100 col0\" >1687</td>\n",
+       "      <td id=\"T_f9ded_row100_col1\" class=\"data row100 col1\" >7.757096</td>\n",
+       "      <td id=\"T_f9ded_row100_col2\" class=\"data row100 col2\" >10.102981</td>\n",
+       "      <td id=\"T_f9ded_row100_col3\" class=\"data row100 col3\" >2.345885</td>\n",
+       "      <td id=\"T_f9ded_row100_col4\" class=\"data row100 col4\" >77</td>\n",
+       "      <td id=\"T_f9ded_row100_col5\" class=\"data row100 col5\" >101</td>\n",
+       "      <td id=\"T_f9ded_row100_col6\" class=\"data row100 col6\" >-24</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row101\" class=\"row_heading level0 row101\" >minichat-1.5-3b</th>\n",
+       "      <td id=\"T_f9ded_row101_col0\" class=\"data row101 col0\" >1545</td>\n",
+       "      <td id=\"T_f9ded_row101_col1\" class=\"data row101 col1\" >6.553443</td>\n",
+       "      <td id=\"T_f9ded_row101_col2\" class=\"data row101 col2\" >8.493973</td>\n",
+       "      <td id=\"T_f9ded_row101_col3\" class=\"data row101 col3\" >1.940530</td>\n",
+       "      <td id=\"T_f9ded_row101_col4\" class=\"data row101 col4\" >92</td>\n",
+       "      <td id=\"T_f9ded_row101_col5\" class=\"data row101 col5\" >112</td>\n",
+       "      <td id=\"T_f9ded_row101_col6\" class=\"data row101 col6\" >-20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row102\" class=\"row_heading level0 row102\" >vicuna-7b-v1.5</th>\n",
+       "      <td id=\"T_f9ded_row102_col0\" class=\"data row102 col0\" >1083</td>\n",
+       "      <td id=\"T_f9ded_row102_col1\" class=\"data row102 col1\" >4.797494</td>\n",
+       "      <td id=\"T_f9ded_row102_col2\" class=\"data row102 col2\" >9.831513</td>\n",
+       "      <td id=\"T_f9ded_row102_col3\" class=\"data row102 col3\" >5.034019</td>\n",
+       "      <td id=\"T_f9ded_row102_col4\" class=\"data row102 col4\" >105</td>\n",
+       "      <td id=\"T_f9ded_row102_col5\" class=\"data row102 col5\" >104</td>\n",
+       "      <td id=\"T_f9ded_row102_col6\" class=\"data row102 col6\" >1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row103\" class=\"row_heading level0 row103\" >llama-2-chat-7b-evol70k-neft</th>\n",
+       "      <td id=\"T_f9ded_row103_col0\" class=\"data row103 col0\" >1612</td>\n",
+       "      <td id=\"T_f9ded_row103_col1\" class=\"data row103 col1\" >7.602384</td>\n",
+       "      <td id=\"T_f9ded_row103_col2\" class=\"data row103 col2\" >10.530830</td>\n",
+       "      <td id=\"T_f9ded_row103_col3\" class=\"data row103 col3\" >2.928447</td>\n",
+       "      <td id=\"T_f9ded_row103_col4\" class=\"data row103 col4\" >79</td>\n",
+       "      <td id=\"T_f9ded_row103_col5\" class=\"data row103 col5\" >98</td>\n",
+       "      <td id=\"T_f9ded_row103_col6\" class=\"data row103 col6\" >-19</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row104\" class=\"row_heading level0 row104\" >recycled-wizardlm-7b-v2.0</th>\n",
+       "      <td id=\"T_f9ded_row104_col0\" class=\"data row104 col0\" >1583</td>\n",
+       "      <td id=\"T_f9ded_row104_col1\" class=\"data row104 col1\" >7.337129</td>\n",
+       "      <td id=\"T_f9ded_row104_col2\" class=\"data row104 col2\" >10.438112</td>\n",
+       "      <td id=\"T_f9ded_row104_col3\" class=\"data row104 col3\" >3.100983</td>\n",
+       "      <td id=\"T_f9ded_row104_col4\" class=\"data row104 col4\" >86</td>\n",
+       "      <td id=\"T_f9ded_row104_col5\" class=\"data row104 col5\" >99</td>\n",
+       "      <td id=\"T_f9ded_row104_col6\" class=\"data row104 col6\" >-13</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row105\" class=\"row_heading level0 row105\" >vicuna-7b-v1.3</th>\n",
+       "      <td id=\"T_f9ded_row105_col0\" class=\"data row105 col0\" >1110</td>\n",
+       "      <td id=\"T_f9ded_row105_col1\" class=\"data row105 col1\" >4.642512</td>\n",
+       "      <td id=\"T_f9ded_row105_col2\" class=\"data row105 col2\" >11.599864</td>\n",
+       "      <td id=\"T_f9ded_row105_col3\" class=\"data row105 col3\" >6.957352</td>\n",
+       "      <td id=\"T_f9ded_row105_col4\" class=\"data row105 col4\" >107</td>\n",
+       "      <td id=\"T_f9ded_row105_col5\" class=\"data row105 col5\" >93</td>\n",
+       "      <td id=\"T_f9ded_row105_col6\" class=\"data row105 col6\" >14</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row106\" class=\"row_heading level0 row106\" >alpaca-farm-ppo-sim-gpt4-20k</th>\n",
+       "      <td id=\"T_f9ded_row106_col0\" class=\"data row106 col0\" >511</td>\n",
+       "      <td id=\"T_f9ded_row106_col1\" class=\"data row106 col1\" >3.450342</td>\n",
+       "      <td id=\"T_f9ded_row106_col2\" class=\"data row106 col2\" >7.809135</td>\n",
+       "      <td id=\"T_f9ded_row106_col3\" class=\"data row106 col3\" >4.358793</td>\n",
+       "      <td id=\"T_f9ded_row106_col4\" class=\"data row106 col4\" >115</td>\n",
+       "      <td id=\"T_f9ded_row106_col5\" class=\"data row106 col5\" >115</td>\n",
+       "      <td id=\"T_f9ded_row106_col6\" class=\"data row106 col6\" >0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row107\" class=\"row_heading level0 row107\" >ultralm-13b</th>\n",
+       "      <td id=\"T_f9ded_row107_col0\" class=\"data row107 col0\" >1087</td>\n",
+       "      <td id=\"T_f9ded_row107_col1\" class=\"data row107 col1\" >5.074590</td>\n",
+       "      <td id=\"T_f9ded_row107_col2\" class=\"data row107 col2\" >11.539285</td>\n",
+       "      <td id=\"T_f9ded_row107_col3\" class=\"data row107 col3\" >6.464695</td>\n",
+       "      <td id=\"T_f9ded_row107_col4\" class=\"data row107 col4\" >102</td>\n",
+       "      <td id=\"T_f9ded_row107_col5\" class=\"data row107 col5\" >94</td>\n",
+       "      <td id=\"T_f9ded_row107_col6\" class=\"data row107 col6\" >8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row108\" class=\"row_heading level0 row108\" >baize-v2-13b</th>\n",
+       "      <td id=\"T_f9ded_row108_col0\" class=\"data row108 col0\" >930</td>\n",
+       "      <td id=\"T_f9ded_row108_col1\" class=\"data row108 col1\" >4.590545</td>\n",
+       "      <td id=\"T_f9ded_row108_col2\" class=\"data row108 col2\" >9.054781</td>\n",
+       "      <td id=\"T_f9ded_row108_col3\" class=\"data row108 col3\" >4.464236</td>\n",
+       "      <td id=\"T_f9ded_row108_col4\" class=\"data row108 col4\" >108</td>\n",
+       "      <td id=\"T_f9ded_row108_col5\" class=\"data row108 col5\" >109</td>\n",
+       "      <td id=\"T_f9ded_row108_col6\" class=\"data row108 col6\" >-1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row109\" class=\"row_heading level0 row109\" >recycled-wizardlm-7b-v1.0</th>\n",
+       "      <td id=\"T_f9ded_row109_col0\" class=\"data row109 col0\" >1494</td>\n",
+       "      <td id=\"T_f9ded_row109_col1\" class=\"data row109 col1\" >6.632750</td>\n",
+       "      <td id=\"T_f9ded_row109_col2\" class=\"data row109 col2\" >9.200354</td>\n",
+       "      <td id=\"T_f9ded_row109_col3\" class=\"data row109 col3\" >2.567604</td>\n",
+       "      <td id=\"T_f9ded_row109_col4\" class=\"data row109 col4\" >91</td>\n",
+       "      <td id=\"T_f9ded_row109_col5\" class=\"data row109 col5\" >108</td>\n",
+       "      <td id=\"T_f9ded_row109_col6\" class=\"data row109 col6\" >-17</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row110\" class=\"row_heading level0 row110\" >alpaca-7b_verbose</th>\n",
+       "      <td id=\"T_f9ded_row110_col0\" class=\"data row110 col0\" >537</td>\n",
+       "      <td id=\"T_f9ded_row110_col1\" class=\"data row110 col1\" >2.933102</td>\n",
+       "      <td id=\"T_f9ded_row110_col2\" class=\"data row110 col2\" >8.155702</td>\n",
+       "      <td id=\"T_f9ded_row110_col3\" class=\"data row110 col3\" >5.222601</td>\n",
+       "      <td id=\"T_f9ded_row110_col4\" class=\"data row110 col4\" >120</td>\n",
+       "      <td id=\"T_f9ded_row110_col5\" class=\"data row110 col5\" >114</td>\n",
+       "      <td id=\"T_f9ded_row110_col6\" class=\"data row110 col6\" >6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row111\" class=\"row_heading level0 row111\" >alpaca-farm-ppo-human</th>\n",
+       "      <td id=\"T_f9ded_row111_col0\" class=\"data row111 col0\" >803</td>\n",
+       "      <td id=\"T_f9ded_row111_col1\" class=\"data row111 col1\" >4.100427</td>\n",
+       "      <td id=\"T_f9ded_row111_col2\" class=\"data row111 col2\" >9.954076</td>\n",
+       "      <td id=\"T_f9ded_row111_col3\" class=\"data row111 col3\" >5.853649</td>\n",
+       "      <td id=\"T_f9ded_row111_col4\" class=\"data row111 col4\" >110</td>\n",
+       "      <td id=\"T_f9ded_row111_col5\" class=\"data row111 col5\" >102</td>\n",
+       "      <td id=\"T_f9ded_row111_col6\" class=\"data row111 col6\" >8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row112\" class=\"row_heading level0 row112\" >vicuna-7b</th>\n",
+       "      <td id=\"T_f9ded_row112_col0\" class=\"data row112 col0\" >1044</td>\n",
+       "      <td id=\"T_f9ded_row112_col1\" class=\"data row112 col1\" >4.162611</td>\n",
+       "      <td id=\"T_f9ded_row112_col2\" class=\"data row112 col2\" >8.263311</td>\n",
+       "      <td id=\"T_f9ded_row112_col3\" class=\"data row112 col3\" >4.100700</td>\n",
+       "      <td id=\"T_f9ded_row112_col4\" class=\"data row112 col4\" >109</td>\n",
+       "      <td id=\"T_f9ded_row112_col5\" class=\"data row112 col5\" >113</td>\n",
+       "      <td id=\"T_f9ded_row112_col6\" class=\"data row112 col6\" >-4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row113\" class=\"row_heading level0 row113\" >alpaca-7b</th>\n",
+       "      <td id=\"T_f9ded_row113_col0\" class=\"data row113 col0\" >396</td>\n",
+       "      <td id=\"T_f9ded_row113_col1\" class=\"data row113 col1\" >2.591451</td>\n",
+       "      <td id=\"T_f9ded_row113_col2\" class=\"data row113 col2\" >15.393406</td>\n",
+       "      <td id=\"T_f9ded_row113_col3\" class=\"data row113 col3\" >12.801955</td>\n",
+       "      <td id=\"T_f9ded_row113_col4\" class=\"data row113 col4\" >124</td>\n",
+       "      <td id=\"T_f9ded_row113_col5\" class=\"data row113 col5\" >66</td>\n",
+       "      <td id=\"T_f9ded_row113_col6\" class=\"data row113 col6\" >58</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row114\" class=\"row_heading level0 row114\" >phi-2-sft</th>\n",
+       "      <td id=\"T_f9ded_row114_col0\" class=\"data row114 col0\" >1068</td>\n",
+       "      <td id=\"T_f9ded_row114_col1\" class=\"data row114 col1\" >3.977568</td>\n",
+       "      <td id=\"T_f9ded_row114_col2\" class=\"data row114 col2\" >7.608799</td>\n",
+       "      <td id=\"T_f9ded_row114_col3\" class=\"data row114 col3\" >3.631231</td>\n",
+       "      <td id=\"T_f9ded_row114_col4\" class=\"data row114 col4\" >111</td>\n",
+       "      <td id=\"T_f9ded_row114_col5\" class=\"data row114 col5\" >116</td>\n",
+       "      <td id=\"T_f9ded_row114_col6\" class=\"data row114 col6\" >-5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row115\" class=\"row_heading level0 row115\" >minichat-3b</th>\n",
+       "      <td id=\"T_f9ded_row115_col0\" class=\"data row115 col0\" >868</td>\n",
+       "      <td id=\"T_f9ded_row115_col1\" class=\"data row115 col1\" >3.007151</td>\n",
+       "      <td id=\"T_f9ded_row115_col2\" class=\"data row115 col2\" >9.394740</td>\n",
+       "      <td id=\"T_f9ded_row115_col3\" class=\"data row115 col3\" >6.387589</td>\n",
+       "      <td id=\"T_f9ded_row115_col4\" class=\"data row115 col4\" >119</td>\n",
+       "      <td id=\"T_f9ded_row115_col5\" class=\"data row115 col5\" >107</td>\n",
+       "      <td id=\"T_f9ded_row115_col6\" class=\"data row115 col6\" >12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row116\" class=\"row_heading level0 row116\" >guanaco-33b</th>\n",
+       "      <td id=\"T_f9ded_row116_col0\" class=\"data row116 col0\" >1311</td>\n",
+       "      <td id=\"T_f9ded_row116_col1\" class=\"data row116 col1\" >5.002494</td>\n",
+       "      <td id=\"T_f9ded_row116_col2\" class=\"data row116 col2\" >7.568960</td>\n",
+       "      <td id=\"T_f9ded_row116_col3\" class=\"data row116 col3\" >2.566467</td>\n",
+       "      <td id=\"T_f9ded_row116_col4\" class=\"data row116 col4\" >103</td>\n",
+       "      <td id=\"T_f9ded_row116_col5\" class=\"data row116 col5\" >117</td>\n",
+       "      <td id=\"T_f9ded_row116_col6\" class=\"data row116 col6\" >-14</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row117\" class=\"row_heading level0 row117\" >falcon-40b-instruct</th>\n",
+       "      <td id=\"T_f9ded_row117_col0\" class=\"data row117 col0\" >662</td>\n",
+       "      <td id=\"T_f9ded_row117_col1\" class=\"data row117 col1\" >3.342919</td>\n",
+       "      <td id=\"T_f9ded_row117_col2\" class=\"data row117 col2\" >8.765865</td>\n",
+       "      <td id=\"T_f9ded_row117_col3\" class=\"data row117 col3\" >5.422946</td>\n",
+       "      <td id=\"T_f9ded_row117_col4\" class=\"data row117 col4\" >118</td>\n",
+       "      <td id=\"T_f9ded_row117_col5\" class=\"data row117 col5\" >110</td>\n",
+       "      <td id=\"T_f9ded_row117_col6\" class=\"data row117 col6\" >8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row118\" class=\"row_heading level0 row118\" >gemma-2b-it</th>\n",
+       "      <td id=\"T_f9ded_row118_col0\" class=\"data row118 col0\" >1041</td>\n",
+       "      <td id=\"T_f9ded_row118_col1\" class=\"data row118 col1\" >3.401971</td>\n",
+       "      <td id=\"T_f9ded_row118_col2\" class=\"data row118 col2\" >6.002278</td>\n",
+       "      <td id=\"T_f9ded_row118_col3\" class=\"data row118 col3\" >2.600306</td>\n",
+       "      <td id=\"T_f9ded_row118_col4\" class=\"data row118 col4\" >117</td>\n",
+       "      <td id=\"T_f9ded_row118_col5\" class=\"data row118 col5\" >122</td>\n",
+       "      <td id=\"T_f9ded_row118_col6\" class=\"data row118 col6\" >-5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row119\" class=\"row_heading level0 row119\" >llama-2-7b-chat-hf</th>\n",
+       "      <td id=\"T_f9ded_row119_col0\" class=\"data row119 col0\" >1479</td>\n",
+       "      <td id=\"T_f9ded_row119_col1\" class=\"data row119 col1\" >4.961340</td>\n",
+       "      <td id=\"T_f9ded_row119_col2\" class=\"data row119 col2\" >6.711881</td>\n",
+       "      <td id=\"T_f9ded_row119_col3\" class=\"data row119 col3\" >1.750541</td>\n",
+       "      <td id=\"T_f9ded_row119_col4\" class=\"data row119 col4\" >104</td>\n",
+       "      <td id=\"T_f9ded_row119_col5\" class=\"data row119 col5\" >120</td>\n",
+       "      <td id=\"T_f9ded_row119_col6\" class=\"data row119 col6\" >-16</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row120\" class=\"row_heading level0 row120\" >openbuddy-falcon-7b-v6</th>\n",
+       "      <td id=\"T_f9ded_row120_col0\" class=\"data row120 col0\" >1152</td>\n",
+       "      <td id=\"T_f9ded_row120_col1\" class=\"data row120 col1\" >3.521174</td>\n",
+       "      <td id=\"T_f9ded_row120_col2\" class=\"data row120 col2\" >6.978847</td>\n",
+       "      <td id=\"T_f9ded_row120_col3\" class=\"data row120 col3\" >3.457673</td>\n",
+       "      <td id=\"T_f9ded_row120_col4\" class=\"data row120 col4\" >113</td>\n",
+       "      <td id=\"T_f9ded_row120_col5\" class=\"data row120 col5\" >118</td>\n",
+       "      <td id=\"T_f9ded_row120_col6\" class=\"data row120 col6\" >-5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row121\" class=\"row_heading level0 row121\" >alpaca-7b_concise</th>\n",
+       "      <td id=\"T_f9ded_row121_col0\" class=\"data row121 col0\" >351</td>\n",
+       "      <td id=\"T_f9ded_row121_col1\" class=\"data row121 col1\" >1.991176</td>\n",
+       "      <td id=\"T_f9ded_row121_col2\" class=\"data row121 col2\" >6.673438</td>\n",
+       "      <td id=\"T_f9ded_row121_col3\" class=\"data row121 col3\" >4.682261</td>\n",
+       "      <td id=\"T_f9ded_row121_col4\" class=\"data row121 col4\" >129</td>\n",
+       "      <td id=\"T_f9ded_row121_col5\" class=\"data row121 col5\" >121</td>\n",
+       "      <td id=\"T_f9ded_row121_col6\" class=\"data row121 col6\" >8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row122\" class=\"row_heading level0 row122\" >phi-2</th>\n",
+       "      <td id=\"T_f9ded_row122_col0\" class=\"data row122 col0\" >626</td>\n",
+       "      <td id=\"T_f9ded_row122_col1\" class=\"data row122 col1\" >2.350210</td>\n",
+       "      <td id=\"T_f9ded_row122_col2\" class=\"data row122 col2\" >3.105325</td>\n",
+       "      <td id=\"T_f9ded_row122_col3\" class=\"data row122 col3\" >0.755115</td>\n",
+       "      <td id=\"T_f9ded_row122_col4\" class=\"data row122 col4\" >126</td>\n",
+       "      <td id=\"T_f9ded_row122_col5\" class=\"data row122 col5\" >128</td>\n",
+       "      <td id=\"T_f9ded_row122_col6\" class=\"data row122 col6\" >-2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row123\" class=\"row_heading level0 row123\" >baize-v2-7b</th>\n",
+       "      <td id=\"T_f9ded_row123_col0\" class=\"data row123 col0\" >1127</td>\n",
+       "      <td id=\"T_f9ded_row123_col1\" class=\"data row123 col1\" >3.404815</td>\n",
+       "      <td id=\"T_f9ded_row123_col2\" class=\"data row123 col2\" >5.322234</td>\n",
+       "      <td id=\"T_f9ded_row123_col3\" class=\"data row123 col3\" >1.917420</td>\n",
+       "      <td id=\"T_f9ded_row123_col4\" class=\"data row123 col4\" >116</td>\n",
+       "      <td id=\"T_f9ded_row123_col5\" class=\"data row123 col5\" >123</td>\n",
+       "      <td id=\"T_f9ded_row123_col6\" class=\"data row123 col6\" >-7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row124\" class=\"row_heading level0 row124\" >chatglm2-6b</th>\n",
+       "      <td id=\"T_f9ded_row124_col0\" class=\"data row124 col0\" >1027</td>\n",
+       "      <td id=\"T_f9ded_row124_col1\" class=\"data row124 col1\" >2.762185</td>\n",
+       "      <td id=\"T_f9ded_row124_col2\" class=\"data row124 col2\" >4.570916</td>\n",
+       "      <td id=\"T_f9ded_row124_col3\" class=\"data row124 col3\" >1.808732</td>\n",
+       "      <td id=\"T_f9ded_row124_col4\" class=\"data row124 col4\" >123</td>\n",
+       "      <td id=\"T_f9ded_row124_col5\" class=\"data row124 col5\" >125</td>\n",
+       "      <td id=\"T_f9ded_row124_col6\" class=\"data row124 col6\" >-2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row125\" class=\"row_heading level0 row125\" >pythia-12b-mix-sft</th>\n",
+       "      <td id=\"T_f9ded_row125_col0\" class=\"data row125 col0\" >913</td>\n",
+       "      <td id=\"T_f9ded_row125_col1\" class=\"data row125 col1\" >2.578090</td>\n",
+       "      <td id=\"T_f9ded_row125_col2\" class=\"data row125 col2\" >3.344637</td>\n",
+       "      <td id=\"T_f9ded_row125_col3\" class=\"data row125 col3\" >0.766547</td>\n",
+       "      <td id=\"T_f9ded_row125_col4\" class=\"data row125 col4\" >125</td>\n",
+       "      <td id=\"T_f9ded_row125_col5\" class=\"data row125 col5\" >127</td>\n",
+       "      <td id=\"T_f9ded_row125_col6\" class=\"data row125 col6\" >-2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row126\" class=\"row_heading level0 row126\" >falcon-7b-instruct</th>\n",
+       "      <td id=\"T_f9ded_row126_col0\" class=\"data row126 col0\" >478</td>\n",
+       "      <td id=\"T_f9ded_row126_col1\" class=\"data row126 col1\" >2.146618</td>\n",
+       "      <td id=\"T_f9ded_row126_col2\" class=\"data row126 col2\" >6.787961</td>\n",
+       "      <td id=\"T_f9ded_row126_col3\" class=\"data row126 col3\" >4.641344</td>\n",
+       "      <td id=\"T_f9ded_row126_col4\" class=\"data row126 col4\" >127</td>\n",
+       "      <td id=\"T_f9ded_row126_col5\" class=\"data row126 col5\" >119</td>\n",
+       "      <td id=\"T_f9ded_row126_col6\" class=\"data row126 col6\" >8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row127\" class=\"row_heading level0 row127\" >oasst-sft-pythia-12b</th>\n",
+       "      <td id=\"T_f9ded_row127_col0\" class=\"data row127 col0\" >726</td>\n",
+       "      <td id=\"T_f9ded_row127_col1\" class=\"data row127 col1\" >1.790114</td>\n",
+       "      <td id=\"T_f9ded_row127_col2\" class=\"data row127 col2\" >2.274166</td>\n",
+       "      <td id=\"T_f9ded_row127_col3\" class=\"data row127 col3\" >0.484052</td>\n",
+       "      <td id=\"T_f9ded_row127_col4\" class=\"data row127 col4\" >130</td>\n",
+       "      <td id=\"T_f9ded_row127_col5\" class=\"data row127 col5\" >130</td>\n",
+       "      <td id=\"T_f9ded_row127_col6\" class=\"data row127 col6\" >0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row128\" class=\"row_heading level0 row128\" >guanaco-13b</th>\n",
+       "      <td id=\"T_f9ded_row128_col0\" class=\"data row128 col0\" >1774</td>\n",
+       "      <td id=\"T_f9ded_row128_col1\" class=\"data row128 col1\" >3.469597</td>\n",
+       "      <td id=\"T_f9ded_row128_col2\" class=\"data row128 col2\" >4.103434</td>\n",
+       "      <td id=\"T_f9ded_row128_col3\" class=\"data row128 col3\" >0.633838</td>\n",
+       "      <td id=\"T_f9ded_row128_col4\" class=\"data row128 col4\" >114</td>\n",
+       "      <td id=\"T_f9ded_row128_col5\" class=\"data row128 col5\" >126</td>\n",
+       "      <td id=\"T_f9ded_row128_col6\" class=\"data row128 col6\" >-12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row129\" class=\"row_heading level0 row129\" >guanaco-7b</th>\n",
+       "      <td id=\"T_f9ded_row129_col0\" class=\"data row129 col0\" >1364</td>\n",
+       "      <td id=\"T_f9ded_row129_col1\" class=\"data row129 col1\" >2.880002</td>\n",
+       "      <td id=\"T_f9ded_row129_col2\" class=\"data row129 col2\" >4.644985</td>\n",
+       "      <td id=\"T_f9ded_row129_col3\" class=\"data row129 col3\" >1.764983</td>\n",
+       "      <td id=\"T_f9ded_row129_col4\" class=\"data row129 col4\" >121</td>\n",
+       "      <td id=\"T_f9ded_row129_col5\" class=\"data row129 col5\" >124</td>\n",
+       "      <td id=\"T_f9ded_row129_col6\" class=\"data row129 col6\" >-3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_f9ded_level0_row130\" class=\"row_heading level0 row130\" >baichuan-13b-chat</th>\n",
+       "      <td id=\"T_f9ded_row130_col0\" class=\"data row130 col0\" >1727</td>\n",
+       "      <td id=\"T_f9ded_row130_col1\" class=\"data row130 col1\" >1.992146</td>\n",
+       "      <td id=\"T_f9ded_row130_col2\" class=\"data row130 col2\" >2.464749</td>\n",
+       "      <td id=\"T_f9ded_row130_col3\" class=\"data row130 col3\" >0.472603</td>\n",
+       "      <td id=\"T_f9ded_row130_col4\" class=\"data row130 col4\" >128</td>\n",
+       "      <td id=\"T_f9ded_row130_col5\" class=\"data row130 col5\" >129</td>\n",
+       "      <td id=\"T_f9ded_row130_col6\" class=\"data row130 col6\" >-1</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x15f129ed0>"
+       "<pandas.io.formats.style.Styler at 0x10fdac850>"
       ]
      },
      "execution_count": 17,
@@ -2352,18 +2380,18 @@
       "# Report for **avg_sigmoid_length_corrected_win_rate**\n",
       "\n",
       "## Gameability (lower is better)\n",
-      "Verbosity gameability (relative std metric): 12.9%\n",
-      "Conciseness gameability (relative std metric): 16.2%\n",
+      "Verbosity gameability (relative std metric): 13.2%\n",
+      "Conciseness gameability (relative std metric): 16.6%\n",
       "Adversarial winrate gain: 3.6\n",
       "Adversarial rank gain: 1.0\n",
       "\n",
       "## Correlation with Arena (higher is better)\n",
-      "Spearman Corr: 0.954\n",
-      "Kendall Corr: 0.830\n",
+      "Spearman Corr: 0.964\n",
+      "Kendall Corr: 0.854\n",
       "\n",
-      "## Correlation with length (closer to spearman=0.28, kendall=0.19 is better)\n",
-      "Spearman Corr: 0.260\n",
-      "Kendall Corr: 0.165\n",
+      "## Correlation with length (closer to spearman=0.28, kendall=0.20 is better)\n",
+      "Spearman Corr: 0.268\n",
+      "Kendall Corr: 0.176\n",
       "\n",
       "## Top 10 models\n"
      ]
@@ -2442,1560 +2470,1580 @@
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_c0e9c_row0_col3, #T_c0e9c_row17_col6 {\n",
+       "#T_059fc_row0_col3, #T_059fc_row19_col6 {\n",
        "  background-color: #6bacd1;\n",
        "  color: #f1f1f1;\n",
        "}\n",
-       "#T_c0e9c_row0_col6, #T_c0e9c_row23_col6, #T_c0e9c_row118_col6, #T_c0e9c_row128_col6 {\n",
+       "#T_059fc_row0_col6, #T_059fc_row32_col6, #T_059fc_row120_col6, #T_059fc_row130_col6 {\n",
        "  background-color: #f5f6f7;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row1_col3, #T_c0e9c_row1_col6, #T_c0e9c_row20_col6, #T_c0e9c_row32_col6, #T_c0e9c_row41_col6, #T_c0e9c_row55_col6, #T_c0e9c_row65_col6, #T_c0e9c_row85_col6, #T_c0e9c_row100_col6, #T_c0e9c_row103_col6, #T_c0e9c_row113_col6, #T_c0e9c_row116_col6, #T_c0e9c_row119_col6, #T_c0e9c_row120_col6, #T_c0e9c_row122_col6, #T_c0e9c_row124_col6, #T_c0e9c_row125_col6 {\n",
+       "#T_059fc_row1_col3, #T_059fc_row1_col6, #T_059fc_row22_col6, #T_059fc_row43_col6, #T_059fc_row57_col6, #T_059fc_row67_col6, #T_059fc_row87_col6, #T_059fc_row102_col6, #T_059fc_row105_col6, #T_059fc_row115_col6, #T_059fc_row118_col6, #T_059fc_row121_col6, #T_059fc_row122_col6, #T_059fc_row124_col6, #T_059fc_row126_col6, #T_059fc_row127_col6 {\n",
        "  background-color: #f7f6f6;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row2_col3 {\n",
+       "#T_059fc_row2_col3 {\n",
        "  background-color: #f5aa89;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row2_col6, #T_c0e9c_row10_col6, #T_c0e9c_row63_col6, #T_c0e9c_row64_col6, #T_c0e9c_row69_col6, #T_c0e9c_row78_col6, #T_c0e9c_row81_col6, #T_c0e9c_row87_col3, #T_c0e9c_row95_col3, #T_c0e9c_row97_col3, #T_c0e9c_row99_col3, #T_c0e9c_row112_col3, #T_c0e9c_row115_col3 {\n",
+       "#T_059fc_row2_col6, #T_059fc_row9_col6, #T_059fc_row11_col6, #T_059fc_row50_col6, #T_059fc_row62_col6, #T_059fc_row65_col6, #T_059fc_row66_col6, #T_059fc_row71_col6, #T_059fc_row79_col6, #T_059fc_row80_col6, #T_059fc_row83_col6, #T_059fc_row89_col3, #T_059fc_row97_col3, #T_059fc_row99_col3, #T_059fc_row101_col3, #T_059fc_row114_col3, #T_059fc_row117_col3 {\n",
        "  background-color: #f9eee7;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row3_col3 {\n",
+       "#T_059fc_row3_col3 {\n",
        "  background-color: #f5a886;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row3_col6, #T_c0e9c_row6_col6, #T_c0e9c_row7_col6, #T_c0e9c_row13_col6, #T_c0e9c_row42_col6, #T_c0e9c_row61_col6, #T_c0e9c_row125_col3 {\n",
-       "  background-color: #f8f2ef;\n",
+       "#T_059fc_row3_col6, #T_059fc_row6_col6, #T_059fc_row7_col6, #T_059fc_row44_col6, #T_059fc_row76_col3, #T_059fc_row96_col6, #T_059fc_row121_col3, #T_059fc_row126_col3, #T_059fc_row129_col3 {\n",
+       "  background-color: #f8f1ed;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row4_col3, #T_c0e9c_row7_col3 {\n",
+       "#T_059fc_row4_col3, #T_059fc_row7_col3 {\n",
        "  background-color: #f7b99c;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row4_col6, #T_c0e9c_row8_col6, #T_c0e9c_row9_col6, #T_c0e9c_row52_col6, #T_c0e9c_row83_col6, #T_c0e9c_row115_col6 {\n",
-       "  background-color: #f8f3f0;\n",
+       "#T_059fc_row4_col6, #T_059fc_row8_col6, #T_059fc_row10_col6, #T_059fc_row15_col6, #T_059fc_row54_col6, #T_059fc_row63_col6, #T_059fc_row127_col3 {\n",
+       "  background-color: #f8f2ef;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row5_col3, #T_c0e9c_row8_col3 {\n",
+       "#T_059fc_row5_col3, #T_059fc_row8_col3 {\n",
        "  background-color: #f9c6ac;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row5_col6, #T_c0e9c_row80_col6, #T_c0e9c_row90_col6, #T_c0e9c_row104_col6, #T_c0e9c_row108_col6, #T_c0e9c_row109_col6, #T_c0e9c_row123_col6, #T_c0e9c_row128_col3 {\n",
-       "  background-color: #f7f5f4;\n",
+       "#T_059fc_row5_col6, #T_059fc_row61_col6, #T_059fc_row74_col3, #T_059fc_row84_col3, #T_059fc_row88_col6, #T_059fc_row93_col6, #T_059fc_row108_col6, #T_059fc_row113_col6, #T_059fc_row128_col3 {\n",
+       "  background-color: #f8f4f2;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row6_col3 {\n",
+       "#T_059fc_row6_col3 {\n",
        "  background-color: #f8bfa4;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row9_col3 {\n",
+       "#T_059fc_row9_col3, #T_059fc_row16_col3, #T_059fc_row17_col3 {\n",
+       "  background-color: #f9c2a7;\n",
+       "  color: #000000;\n",
+       "}\n",
+       "#T_059fc_row10_col3 {\n",
        "  background-color: #f8bb9e;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row10_col3 {\n",
+       "#T_059fc_row11_col3 {\n",
        "  background-color: #facab1;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row11_col3, #T_c0e9c_row17_col3 {\n",
+       "#T_059fc_row12_col3, #T_059fc_row19_col3 {\n",
        "  background-color: #8dc2dc;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row11_col6 {\n",
-       "  background-color: #a9d1e5;\n",
+       "#T_059fc_row12_col6, #T_059fc_row13_col3 {\n",
+       "  background-color: #a7d0e4;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row12_col3, #T_c0e9c_row97_col6 {\n",
-       "  background-color: #e3edf3;\n",
+       "#T_059fc_row13_col6 {\n",
+       "  background-color: #bddbea;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row12_col6 {\n",
-       "  background-color: #deebf2;\n",
+       "#T_059fc_row14_col3, #T_059fc_row99_col6 {\n",
+       "  background-color: #e3edf3;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row13_col3, #T_c0e9c_row25_col3 {\n",
-       "  background-color: #fbccb4;\n",
+       "#T_059fc_row14_col6, #T_059fc_row26_col6 {\n",
+       "  background-color: #e0ecf3;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row14_col3, #T_c0e9c_row15_col3 {\n",
-       "  background-color: #f9c2a7;\n",
+       "#T_059fc_row15_col3, #T_059fc_row27_col3 {\n",
+       "  background-color: #fbccb4;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row14_col6, #T_c0e9c_row15_col6, #T_c0e9c_row18_col6, #T_c0e9c_row54_col3, #T_c0e9c_row65_col3, #T_c0e9c_row73_col6, #T_c0e9c_row100_col3, #T_c0e9c_row103_col3, #T_c0e9c_row106_col3, #T_c0e9c_row109_col3 {\n",
-       "  background-color: #f9ebe3;\n",
+       "#T_059fc_row16_col6, #T_059fc_row17_col6, #T_059fc_row20_col6, #T_059fc_row51_col6, #T_059fc_row78_col3, #T_059fc_row81_col3, #T_059fc_row95_col3, #T_059fc_row107_col3 {\n",
+       "  background-color: #faeae1;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row16_col3, #T_c0e9c_row67_col6 {\n",
+       "#T_059fc_row18_col3, #T_059fc_row69_col6 {\n",
        "  background-color: #edf2f5;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row16_col6, #T_c0e9c_row38_col6, #T_c0e9c_row126_col6 {\n",
+       "#T_059fc_row18_col6, #T_059fc_row128_col6 {\n",
        "  background-color: #e7f0f4;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row18_col3, #T_c0e9c_row19_col3 {\n",
+       "#T_059fc_row20_col3, #T_059fc_row21_col3 {\n",
        "  background-color: #fac8af;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row19_col6, #T_c0e9c_row34_col6, #T_c0e9c_row40_col6, #T_c0e9c_row46_col6, #T_c0e9c_row60_col6, #T_c0e9c_row77_col6, #T_c0e9c_row92_col3, #T_c0e9c_row101_col3, #T_c0e9c_row102_col3, #T_c0e9c_row104_col3, #T_c0e9c_row107_col3, #T_c0e9c_row110_col3, #T_c0e9c_row114_col3 {\n",
-       "  background-color: #f9ede5;\n",
+       "#T_059fc_row21_col6, #T_059fc_row56_col3, #T_059fc_row67_col3, #T_059fc_row75_col6, #T_059fc_row102_col3, #T_059fc_row105_col3, #T_059fc_row108_col3, #T_059fc_row111_col3 {\n",
+       "  background-color: #f9ebe3;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row20_col3, #T_c0e9c_row23_col3, #T_c0e9c_row29_col6, #T_c0e9c_row59_col3, #T_c0e9c_row62_col3, #T_c0e9c_row64_col3 {\n",
+       "#T_059fc_row22_col3, #T_059fc_row25_col3, #T_059fc_row52_col6, #T_059fc_row61_col3, #T_059fc_row64_col3, #T_059fc_row66_col3 {\n",
        "  background-color: #fbe4d6;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row21_col3, #T_c0e9c_row22_col3, #T_c0e9c_row28_col3 {\n",
+       "#T_059fc_row23_col3, #T_059fc_row24_col3, #T_059fc_row30_col3 {\n",
        "  background-color: #fcd5bf;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row21_col6, #T_c0e9c_row22_col6, #T_c0e9c_row74_col3, #T_c0e9c_row94_col6, #T_c0e9c_row119_col3, #T_c0e9c_row124_col3, #T_c0e9c_row127_col3 {\n",
-       "  background-color: #f8f1ed;\n",
+       "#T_059fc_row23_col6, #T_059fc_row24_col6, #T_059fc_row53_col6, #T_059fc_row55_col3, #T_059fc_row86_col6, #T_059fc_row90_col6, #T_059fc_row122_col3, #T_059fc_row124_col3, #T_059fc_row125_col3 {\n",
+       "  background-color: #f9f0eb;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row24_col3, #T_c0e9c_row30_col6, #T_c0e9c_row57_col6, #T_c0e9c_row58_col6, #T_c0e9c_row71_col6, #T_c0e9c_row114_col6, #T_c0e9c_row127_col6 {\n",
-       "  background-color: #f3f5f6;\n",
+       "#T_059fc_row25_col6, #T_059fc_row91_col6, #T_059fc_row107_col6, #T_059fc_row112_col6, #T_059fc_row114_col6, #T_059fc_row123_col6 {\n",
+       "  background-color: #f6f7f7;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row24_col6 {\n",
-       "  background-color: #e0ecf3;\n",
+       "#T_059fc_row26_col3, #T_059fc_row46_col6, #T_059fc_row59_col6, #T_059fc_row60_col6, #T_059fc_row73_col6, #T_059fc_row116_col6, #T_059fc_row129_col6 {\n",
+       "  background-color: #f3f5f6;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row25_col6, #T_c0e9c_row77_col3, #T_c0e9c_row78_col3, #T_c0e9c_row81_col3 {\n",
-       "  background-color: #fae7dc;\n",
+       "#T_059fc_row27_col6, #T_059fc_row38_col6, #T_059fc_row46_col3, #T_059fc_row60_col3, #T_059fc_row71_col3, #T_059fc_row75_col3, #T_059fc_row82_col3 {\n",
+       "  background-color: #fbe6da;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row26_col3, #T_c0e9c_row27_col3, #T_c0e9c_row39_col3 {\n",
+       "#T_059fc_row28_col3, #T_059fc_row29_col3, #T_059fc_row41_col3 {\n",
        "  background-color: #fddbc7;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row26_col6, #T_c0e9c_row27_col6, #T_c0e9c_row43_col6, #T_c0e9c_row51_col6, #T_c0e9c_row53_col3, #T_c0e9c_row84_col6, #T_c0e9c_row88_col6, #T_c0e9c_row120_col3, #T_c0e9c_row122_col3, #T_c0e9c_row123_col3 {\n",
-       "  background-color: #f9f0eb;\n",
+       "#T_059fc_row28_col6, #T_059fc_row29_col6, #T_059fc_row40_col3, #T_059fc_row45_col6, #T_059fc_row64_col6, #T_059fc_row72_col6, #T_059fc_row92_col3, #T_059fc_row98_col6, #T_059fc_row100_col3, #T_059fc_row110_col3, #T_059fc_row113_col3, #T_059fc_row115_col3, #T_059fc_row118_col3, #T_059fc_row119_col3, #T_059fc_row120_col3, #T_059fc_row123_col3 {\n",
+       "  background-color: #f9efe9;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row28_col6, #T_c0e9c_row45_col3, #T_c0e9c_row47_col6, #T_c0e9c_row57_col3, #T_c0e9c_row66_col3, #T_c0e9c_row67_col3, #T_c0e9c_row68_col3, #T_c0e9c_row83_col3, #T_c0e9c_row89_col3 {\n",
-       "  background-color: #fae9df;\n",
+       "#T_059fc_row30_col6, #T_059fc_row35_col6, #T_059fc_row39_col6, #T_059fc_row58_col3, #T_059fc_row72_col3, #T_059fc_row73_col3, #T_059fc_row77_col3, #T_059fc_row86_col3, #T_059fc_row87_col3, #T_059fc_row88_col3, #T_059fc_row90_col3, #T_059fc_row93_col3, #T_059fc_row96_col3, #T_059fc_row98_col3 {\n",
+       "  background-color: #fae8de;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row29_col3, #T_c0e9c_row32_col3, #T_c0e9c_row36_col3 {\n",
+       "#T_059fc_row31_col3, #T_059fc_row34_col3, #T_059fc_row38_col3 {\n",
        "  background-color: #fddcc9;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row30_col3, #T_c0e9c_row33_col3, #T_c0e9c_row47_col3 {\n",
+       "#T_059fc_row31_col6, #T_059fc_row57_col3 {\n",
+       "  background-color: #fbe5d8;\n",
+       "  color: #000000;\n",
+       "}\n",
+       "#T_059fc_row32_col3, #T_059fc_row35_col3, #T_059fc_row49_col3 {\n",
        "  background-color: #fcdecd;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row31_col3, #T_c0e9c_row34_col3 {\n",
+       "#T_059fc_row33_col3, #T_059fc_row36_col3 {\n",
        "  background-color: #fdd9c4;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row31_col6, #T_c0e9c_row59_col6, #T_c0e9c_row72_col3, #T_c0e9c_row82_col3, #T_c0e9c_row86_col6, #T_c0e9c_row91_col6, #T_c0e9c_row106_col6, #T_c0e9c_row111_col6, #T_c0e9c_row126_col3 {\n",
-       "  background-color: #f8f4f2;\n",
+       "#T_059fc_row33_col6, #T_059fc_row85_col6, #T_059fc_row117_col6 {\n",
+       "  background-color: #f8f3f0;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row33_col6, #T_c0e9c_row37_col6, #T_c0e9c_row56_col3, #T_c0e9c_row70_col3, #T_c0e9c_row71_col3, #T_c0e9c_row75_col3, #T_c0e9c_row84_col3, #T_c0e9c_row85_col3, #T_c0e9c_row86_col3, #T_c0e9c_row88_col3, #T_c0e9c_row91_col3, #T_c0e9c_row94_col3, #T_c0e9c_row96_col3 {\n",
-       "  background-color: #fae8de;\n",
+       "#T_059fc_row34_col6, #T_059fc_row82_col6, #T_059fc_row92_col6, #T_059fc_row106_col6, #T_059fc_row110_col6, #T_059fc_row111_col6, #T_059fc_row125_col6, #T_059fc_row130_col3 {\n",
+       "  background-color: #f7f5f4;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row35_col3, #T_c0e9c_row74_col6 {\n",
-       "  background-color: #dae9f2;\n",
+       "#T_059fc_row36_col6, #T_059fc_row42_col6, #T_059fc_row48_col6, #T_059fc_row94_col3, #T_059fc_row103_col3, #T_059fc_row104_col3, #T_059fc_row106_col3, #T_059fc_row109_col3, #T_059fc_row112_col3, #T_059fc_row116_col3 {\n",
+       "  background-color: #f9ede5;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row35_col6 {\n",
-       "  background-color: #b1d5e7;\n",
+       "#T_059fc_row37_col3, #T_059fc_row76_col6 {\n",
+       "  background-color: #dae9f2;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row36_col6, #T_c0e9c_row44_col3, #T_c0e9c_row58_col3, #T_c0e9c_row69_col3, #T_c0e9c_row73_col3, #T_c0e9c_row80_col3 {\n",
-       "  background-color: #fbe6da;\n",
+       "#T_059fc_row37_col6 {\n",
+       "  background-color: #aed3e6;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row37_col3 {\n",
+       "#T_059fc_row39_col3 {\n",
        "  background-color: #fdddcb;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row38_col3, #T_c0e9c_row48_col6, #T_c0e9c_row62_col6, #T_c0e9c_row70_col6, #T_c0e9c_row90_col3, #T_c0e9c_row96_col6, #T_c0e9c_row98_col3, #T_c0e9c_row108_col3, #T_c0e9c_row111_col3, #T_c0e9c_row113_col3, #T_c0e9c_row116_col3, #T_c0e9c_row117_col3, #T_c0e9c_row118_col3, #T_c0e9c_row121_col3 {\n",
-       "  background-color: #f9efe9;\n",
+       "#T_059fc_row40_col6, #T_059fc_row56_col6, #T_059fc_row89_col6 {\n",
+       "  background-color: #e9f0f4;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row39_col6, #T_c0e9c_row49_col6, #T_c0e9c_row76_col3, #T_c0e9c_row79_col3, #T_c0e9c_row93_col3, #T_c0e9c_row105_col3 {\n",
-       "  background-color: #faeae1;\n",
+       "#T_059fc_row41_col6, #T_059fc_row47_col3, #T_059fc_row49_col6, #T_059fc_row59_col3, #T_059fc_row68_col3, #T_059fc_row69_col3, #T_059fc_row70_col3, #T_059fc_row85_col3, #T_059fc_row91_col3 {\n",
+       "  background-color: #fae9df;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row40_col3, #T_c0e9c_row41_col3, #T_c0e9c_row42_col3, #T_c0e9c_row52_col3, #T_c0e9c_row60_col3 {\n",
+       "#T_059fc_row42_col3, #T_059fc_row43_col3, #T_059fc_row44_col3, #T_059fc_row54_col3, #T_059fc_row62_col3 {\n",
        "  background-color: #fce2d2;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row43_col3, #T_c0e9c_row46_col3 {\n",
+       "#T_059fc_row45_col3, #T_059fc_row48_col3 {\n",
        "  background-color: #fcdfcf;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row44_col6, #T_c0e9c_row75_col6, #T_c0e9c_row93_col6, #T_c0e9c_row102_col6 {\n",
-       "  background-color: #f2f5f6;\n",
-       "  color: #000000;\n",
-       "}\n",
-       "#T_c0e9c_row45_col6, #T_c0e9c_row68_col6 {\n",
-       "  background-color: #eff3f5;\n",
+       "#T_059fc_row47_col6, #T_059fc_row58_col6, #T_059fc_row68_col6, #T_059fc_row78_col6, #T_059fc_row81_col6, #T_059fc_row119_col6 {\n",
+       "  background-color: #f0f4f6;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row48_col3, #T_c0e9c_row49_col3, #T_c0e9c_row50_col3 {\n",
+       "#T_059fc_row50_col3, #T_059fc_row51_col3, #T_059fc_row52_col3 {\n",
        "  background-color: #fce0d0;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row50_col6, #T_c0e9c_row51_col3, #T_c0e9c_row61_col3, #T_c0e9c_row63_col3 {\n",
+       "#T_059fc_row53_col3, #T_059fc_row63_col3, #T_059fc_row65_col3 {\n",
        "  background-color: #fbe3d4;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row53_col6 {\n",
+       "#T_059fc_row55_col6 {\n",
        "  background-color: #dbeaf2;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row54_col6, #T_c0e9c_row87_col6, #T_c0e9c_row92_col6, #T_c0e9c_row95_col6, #T_c0e9c_row101_col6 {\n",
-       "  background-color: #e9f0f4;\n",
+       "#T_059fc_row70_col6 {\n",
+       "  background-color: #eff3f5;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row55_col3 {\n",
-       "  background-color: #fbe5d8;\n",
+       "#T_059fc_row74_col6 {\n",
+       "  background-color: #d4e6f1;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row56_col6, #T_c0e9c_row66_col6, #T_c0e9c_row76_col6, #T_c0e9c_row79_col6, #T_c0e9c_row117_col6 {\n",
-       "  background-color: #f0f4f6;\n",
+       "#T_059fc_row77_col6, #T_059fc_row95_col6, #T_059fc_row104_col6 {\n",
+       "  background-color: #f2f5f6;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row72_col6 {\n",
-       "  background-color: #d4e6f1;\n",
+       "#T_059fc_row79_col3, #T_059fc_row80_col3, #T_059fc_row83_col3 {\n",
+       "  background-color: #fae7dc;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row82_col6 {\n",
-       "  background-color: #d1e5f0;\n",
+       "#T_059fc_row84_col6 {\n",
+       "  background-color: #d2e6f0;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row89_col6, #T_c0e9c_row105_col6, #T_c0e9c_row110_col6, #T_c0e9c_row112_col6, #T_c0e9c_row121_col6 {\n",
-       "  background-color: #f6f7f7;\n",
+       "#T_059fc_row94_col6, #T_059fc_row97_col6, #T_059fc_row103_col6 {\n",
+       "  background-color: #eaf1f5;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row98_col6 {\n",
+       "#T_059fc_row100_col6 {\n",
        "  background-color: #e1edf3;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_c0e9c_row99_col6 {\n",
-       "  background-color: #eaf1f5;\n",
-       "  color: #000000;\n",
-       "}\n",
-       "#T_c0e9c_row107_col6 {\n",
+       "#T_059fc_row101_col6, #T_059fc_row109_col6 {\n",
        "  background-color: #ecf2f5;\n",
        "  color: #000000;\n",
        "}\n",
        "</style>\n",
-       "<table id=\"T_c0e9c\">\n",
+       "<table id=\"T_059fc\">\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_c0e9c_level0_col0\" class=\"col_heading level0 col0\" >avg_length</th>\n",
-       "      <th id=\"T_c0e9c_level0_col1\" class=\"col_heading level0 col1\" >win_rate</th>\n",
-       "      <th id=\"T_c0e9c_level0_col2\" class=\"col_heading level0 col2\" >new_win_rate</th>\n",
-       "      <th id=\"T_c0e9c_level0_col3\" class=\"col_heading level0 col3\" >delta_win_rate</th>\n",
-       "      <th id=\"T_c0e9c_level0_col4\" class=\"col_heading level0 col4\" >rank_win_rate</th>\n",
-       "      <th id=\"T_c0e9c_level0_col5\" class=\"col_heading level0 col5\" >rank_new_win_rate</th>\n",
-       "      <th id=\"T_c0e9c_level0_col6\" class=\"col_heading level0 col6\" >delta_rank</th>\n",
+       "      <th id=\"T_059fc_level0_col0\" class=\"col_heading level0 col0\" >avg_length</th>\n",
+       "      <th id=\"T_059fc_level0_col1\" class=\"col_heading level0 col1\" >win_rate</th>\n",
+       "      <th id=\"T_059fc_level0_col2\" class=\"col_heading level0 col2\" >new_win_rate</th>\n",
+       "      <th id=\"T_059fc_level0_col3\" class=\"col_heading level0 col3\" >delta_win_rate</th>\n",
+       "      <th id=\"T_059fc_level0_col4\" class=\"col_heading level0 col4\" >rank_win_rate</th>\n",
+       "      <th id=\"T_059fc_level0_col5\" class=\"col_heading level0 col5\" >rank_new_win_rate</th>\n",
+       "      <th id=\"T_059fc_level0_col6\" class=\"col_heading level0 col6\" >delta_rank</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row0\" class=\"row_heading level0 row0\" >gpt4_1106_preview_verbose</th>\n",
-       "      <td id=\"T_c0e9c_row0_col0\" class=\"data row0 col0\" >2402</td>\n",
-       "      <td id=\"T_c0e9c_row0_col1\" class=\"data row0 col1\" >64.303601</td>\n",
-       "      <td id=\"T_c0e9c_row0_col2\" class=\"data row0 col2\" >42.502532</td>\n",
-       "      <td id=\"T_c0e9c_row0_col3\" class=\"data row0 col3\" >-21.801069</td>\n",
-       "      <td id=\"T_c0e9c_row0_col4\" class=\"data row0 col4\" >0</td>\n",
-       "      <td id=\"T_c0e9c_row0_col5\" class=\"data row0 col5\" >2</td>\n",
-       "      <td id=\"T_c0e9c_row0_col6\" class=\"data row0 col6\" >-2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row1\" class=\"row_heading level0 row1\" >gpt4_1106_preview</th>\n",
-       "      <td id=\"T_c0e9c_row1_col0\" class=\"data row1 col0\" >2049</td>\n",
-       "      <td id=\"T_c0e9c_row1_col1\" class=\"data row1 col1\" >50.000000</td>\n",
-       "      <td id=\"T_c0e9c_row1_col2\" class=\"data row1 col2\" >50.000000</td>\n",
-       "      <td id=\"T_c0e9c_row1_col3\" class=\"data row1 col3\" >0.000000</td>\n",
-       "      <td id=\"T_c0e9c_row1_col4\" class=\"data row1 col4\" >1</td>\n",
-       "      <td id=\"T_c0e9c_row1_col5\" class=\"data row1 col5\" >0</td>\n",
-       "      <td id=\"T_c0e9c_row1_col6\" class=\"data row1 col6\" >1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row2\" class=\"row_heading level0 row2\" >gpt4_1106_preview_concise</th>\n",
-       "      <td id=\"T_c0e9c_row2_col0\" class=\"data row2 col0\" >1136</td>\n",
-       "      <td id=\"T_c0e9c_row2_col1\" class=\"data row2 col1\" >22.920194</td>\n",
-       "      <td id=\"T_c0e9c_row2_col2\" class=\"data row2 col2\" >39.481617</td>\n",
-       "      <td id=\"T_c0e9c_row2_col3\" class=\"data row2 col3\" >16.561423</td>\n",
-       "      <td id=\"T_c0e9c_row2_col4\" class=\"data row2 col4\" >13</td>\n",
-       "      <td id=\"T_c0e9c_row2_col5\" class=\"data row2 col5\" >4</td>\n",
-       "      <td id=\"T_c0e9c_row2_col6\" class=\"data row2 col6\" >9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row3\" class=\"row_heading level0 row3\" >claude-3-opus-20240229</th>\n",
-       "      <td id=\"T_c0e9c_row3_col0\" class=\"data row3 col0\" >1388</td>\n",
-       "      <td id=\"T_c0e9c_row3_col1\" class=\"data row3 col1\" >29.041764</td>\n",
-       "      <td id=\"T_c0e9c_row3_col2\" class=\"data row3 col2\" >45.857774</td>\n",
-       "      <td id=\"T_c0e9c_row3_col3\" class=\"data row3 col3\" >16.816010</td>\n",
-       "      <td id=\"T_c0e9c_row3_col4\" class=\"data row3 col4\" >6</td>\n",
-       "      <td id=\"T_c0e9c_row3_col5\" class=\"data row3 col5\" >1</td>\n",
-       "      <td id=\"T_c0e9c_row3_col6\" class=\"data row3 col6\" >5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row4\" class=\"row_heading level0 row4\" >gpt4</th>\n",
-       "      <td id=\"T_c0e9c_row4_col0\" class=\"data row4 col0\" >1365</td>\n",
-       "      <td id=\"T_c0e9c_row4_col1\" class=\"data row4 col1\" >23.576789</td>\n",
-       "      <td id=\"T_c0e9c_row4_col2\" class=\"data row4 col2\" >37.584082</td>\n",
-       "      <td id=\"T_c0e9c_row4_col3\" class=\"data row4 col3\" >14.007293</td>\n",
-       "      <td id=\"T_c0e9c_row4_col4\" class=\"data row4 col4\" >11</td>\n",
-       "      <td id=\"T_c0e9c_row4_col5\" class=\"data row4 col5\" >7</td>\n",
-       "      <td id=\"T_c0e9c_row4_col6\" class=\"data row4 col6\" >4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row5\" class=\"row_heading level0 row5\" >Qwen1.5-72B-Chat</th>\n",
-       "      <td id=\"T_c0e9c_row5_col0\" class=\"data row5 col0\" >1549</td>\n",
-       "      <td id=\"T_c0e9c_row5_col1\" class=\"data row5 col1\" >26.498283</td>\n",
-       "      <td id=\"T_c0e9c_row5_col2\" class=\"data row5 col2\" >38.743595</td>\n",
-       "      <td id=\"T_c0e9c_row5_col3\" class=\"data row5 col3\" >12.245311</td>\n",
-       "      <td id=\"T_c0e9c_row5_col4\" class=\"data row5 col4\" >7</td>\n",
-       "      <td id=\"T_c0e9c_row5_col5\" class=\"data row5 col5\" >5</td>\n",
-       "      <td id=\"T_c0e9c_row5_col6\" class=\"data row5 col6\" >2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row6\" class=\"row_heading level0 row6\" >gpt4_0314</th>\n",
-       "      <td id=\"T_c0e9c_row6_col0\" class=\"data row6 col0\" >1371</td>\n",
-       "      <td id=\"T_c0e9c_row6_col1\" class=\"data row6 col1\" >22.073259</td>\n",
-       "      <td id=\"T_c0e9c_row6_col2\" class=\"data row6 col2\" >35.101286</td>\n",
-       "      <td id=\"T_c0e9c_row6_col3\" class=\"data row6 col3\" >13.028027</td>\n",
-       "      <td id=\"T_c0e9c_row6_col4\" class=\"data row6 col4\" >14</td>\n",
-       "      <td id=\"T_c0e9c_row6_col5\" class=\"data row6 col5\" >9</td>\n",
-       "      <td id=\"T_c0e9c_row6_col6\" class=\"data row6 col6\" >5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row7\" class=\"row_heading level0 row7\" >claude-3-sonnet-20240229</th>\n",
-       "      <td id=\"T_c0e9c_row7_col0\" class=\"data row7 col0\" >1420</td>\n",
-       "      <td id=\"T_c0e9c_row7_col1\" class=\"data row7 col1\" >25.556325</td>\n",
-       "      <td id=\"T_c0e9c_row7_col2\" class=\"data row7 col2\" >39.800482</td>\n",
-       "      <td id=\"T_c0e9c_row7_col3\" class=\"data row7 col3\" >14.244157</td>\n",
-       "      <td id=\"T_c0e9c_row7_col4\" class=\"data row7 col4\" >8</td>\n",
-       "      <td id=\"T_c0e9c_row7_col5\" class=\"data row7 col5\" >3</td>\n",
-       "      <td id=\"T_c0e9c_row7_col6\" class=\"data row7 col6\" >5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row8\" class=\"row_heading level0 row8\" >gpt4_0613_verbose</th>\n",
-       "      <td id=\"T_c0e9c_row8_col0\" class=\"data row8 col0\" >1473</td>\n",
-       "      <td id=\"T_c0e9c_row8_col1\" class=\"data row8 col1\" >23.237360</td>\n",
-       "      <td id=\"T_c0e9c_row8_col2\" class=\"data row8 col2\" >35.315026</td>\n",
-       "      <td id=\"T_c0e9c_row8_col3\" class=\"data row8 col3\" >12.077666</td>\n",
-       "      <td id=\"T_c0e9c_row8_col4\" class=\"data row8 col4\" >12</td>\n",
-       "      <td id=\"T_c0e9c_row8_col5\" class=\"data row8 col5\" >8</td>\n",
-       "      <td id=\"T_c0e9c_row8_col6\" class=\"data row8 col6\" >4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row9\" class=\"row_heading level0 row9\" >claude-2.1_verbose</th>\n",
-       "      <td id=\"T_c0e9c_row9_col0\" class=\"data row9 col0\" >1414</td>\n",
-       "      <td id=\"T_c0e9c_row9_col1\" class=\"data row9 col1\" >24.354071</td>\n",
-       "      <td id=\"T_c0e9c_row9_col2\" class=\"data row9 col2\" >38.028529</td>\n",
-       "      <td id=\"T_c0e9c_row9_col3\" class=\"data row9 col3\" >13.674458</td>\n",
-       "      <td id=\"T_c0e9c_row9_col4\" class=\"data row9 col4\" >10</td>\n",
-       "      <td id=\"T_c0e9c_row9_col5\" class=\"data row9 col5\" >6</td>\n",
-       "      <td id=\"T_c0e9c_row9_col6\" class=\"data row9 col6\" >4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row10\" class=\"row_heading level0 row10\" >gpt4_0613</th>\n",
-       "      <td id=\"T_c0e9c_row10_col0\" class=\"data row10 col0\" >1140</td>\n",
-       "      <td id=\"T_c0e9c_row10_col1\" class=\"data row10 col1\" >15.755038</td>\n",
-       "      <td id=\"T_c0e9c_row10_col2\" class=\"data row10 col2\" >27.108937</td>\n",
-       "      <td id=\"T_c0e9c_row10_col3\" class=\"data row10 col3\" >11.353899</td>\n",
-       "      <td id=\"T_c0e9c_row10_col4\" class=\"data row10 col4\" >28</td>\n",
-       "      <td id=\"T_c0e9c_row10_col5\" class=\"data row10 col5\" >19</td>\n",
-       "      <td id=\"T_c0e9c_row10_col6\" class=\"data row10 col6\" >9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row11\" class=\"row_heading level0 row11\" >Snorkel-Mistral-PairRM-DPO-best-of-16</th>\n",
-       "      <td id=\"T_c0e9c_row11_col0\" class=\"data row11 col0\" >2616</td>\n",
-       "      <td id=\"T_c0e9c_row11_col1\" class=\"data row11 col1\" >34.860133</td>\n",
-       "      <td id=\"T_c0e9c_row11_col2\" class=\"data row11 col2\" >16.971563</td>\n",
-       "      <td id=\"T_c0e9c_row11_col3\" class=\"data row11 col3\" >-17.888570</td>\n",
-       "      <td id=\"T_c0e9c_row11_col4\" class=\"data row11 col4\" >2</td>\n",
-       "      <td id=\"T_c0e9c_row11_col5\" class=\"data row11 col5\" >48</td>\n",
-       "      <td id=\"T_c0e9c_row11_col6\" class=\"data row11 col6\" >-46</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row12\" class=\"row_heading level0 row12\" >pairrm-Yi-34B-Chat</th>\n",
-       "      <td id=\"T_c0e9c_row12_col0\" class=\"data row12 col0\" >2195</td>\n",
-       "      <td id=\"T_c0e9c_row12_col1\" class=\"data row12 col1\" >31.241283</td>\n",
-       "      <td id=\"T_c0e9c_row12_col2\" class=\"data row12 col2\" >26.712191</td>\n",
-       "      <td id=\"T_c0e9c_row12_col3\" class=\"data row12 col3\" >-4.529092</td>\n",
-       "      <td id=\"T_c0e9c_row12_col4\" class=\"data row12 col4\" >3</td>\n",
-       "      <td id=\"T_c0e9c_row12_col5\" class=\"data row12 col5\" >21</td>\n",
-       "      <td id=\"T_c0e9c_row12_col6\" class=\"data row12 col6\" >-18</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row13\" class=\"row_heading level0 row13\" >mistral-medium</th>\n",
-       "      <td id=\"T_c0e9c_row13_col0\" class=\"data row13 col0\" >1500</td>\n",
-       "      <td id=\"T_c0e9c_row13_col1\" class=\"data row13 col1\" >21.855773</td>\n",
-       "      <td id=\"T_c0e9c_row13_col2\" class=\"data row13 col2\" >32.778640</td>\n",
-       "      <td id=\"T_c0e9c_row13_col3\" class=\"data row13 col3\" >10.922867</td>\n",
-       "      <td id=\"T_c0e9c_row13_col4\" class=\"data row13 col4\" >15</td>\n",
-       "      <td id=\"T_c0e9c_row13_col5\" class=\"data row13 col5\" >10</td>\n",
-       "      <td id=\"T_c0e9c_row13_col6\" class=\"data row13 col6\" >5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row14\" class=\"row_heading level0 row14\" >claude-2</th>\n",
-       "      <td id=\"T_c0e9c_row14_col0\" class=\"data row14 col0\" >1069</td>\n",
-       "      <td id=\"T_c0e9c_row14_col1\" class=\"data row14 col1\" >17.188240</td>\n",
-       "      <td id=\"T_c0e9c_row14_col2\" class=\"data row14 col2\" >30.132118</td>\n",
-       "      <td id=\"T_c0e9c_row14_col3\" class=\"data row14 col3\" >12.943878</td>\n",
-       "      <td id=\"T_c0e9c_row14_col4\" class=\"data row14 col4\" >23</td>\n",
-       "      <td id=\"T_c0e9c_row14_col5\" class=\"data row14 col5\" >11</td>\n",
-       "      <td id=\"T_c0e9c_row14_col6\" class=\"data row14 col6\" >12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row15\" class=\"row_heading level0 row15\" >claude</th>\n",
-       "      <td id=\"T_c0e9c_row15_col0\" class=\"data row15 col0\" >1082</td>\n",
-       "      <td id=\"T_c0e9c_row15_col1\" class=\"data row15 col1\" >16.985344</td>\n",
-       "      <td id=\"T_c0e9c_row15_col2\" class=\"data row15 col2\" >29.679901</td>\n",
-       "      <td id=\"T_c0e9c_row15_col3\" class=\"data row15 col3\" >12.694557</td>\n",
-       "      <td id=\"T_c0e9c_row15_col4\" class=\"data row15 col4\" >24</td>\n",
-       "      <td id=\"T_c0e9c_row15_col5\" class=\"data row15 col5\" >12</td>\n",
-       "      <td id=\"T_c0e9c_row15_col6\" class=\"data row15 col6\" >12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row16\" class=\"row_heading level0 row16\" >Yi-34B-Chat</th>\n",
-       "      <td id=\"T_c0e9c_row16_col0\" class=\"data row16 col0\" >2123</td>\n",
-       "      <td id=\"T_c0e9c_row16_col1\" class=\"data row16 col1\" >29.659947</td>\n",
-       "      <td id=\"T_c0e9c_row16_col2\" class=\"data row16 col2\" >27.469108</td>\n",
-       "      <td id=\"T_c0e9c_row16_col3\" class=\"data row16 col3\" >-2.190839</td>\n",
-       "      <td id=\"T_c0e9c_row16_col4\" class=\"data row16 col4\" >5</td>\n",
-       "      <td id=\"T_c0e9c_row16_col5\" class=\"data row16 col5\" >17</td>\n",
-       "      <td id=\"T_c0e9c_row16_col6\" class=\"data row16 col6\" >-12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row17\" class=\"row_heading level0 row17\" >Snorkel-Mistral-PairRM-DPO</th>\n",
-       "      <td id=\"T_c0e9c_row17_col0\" class=\"data row17 col0\" >2736</td>\n",
-       "      <td id=\"T_c0e9c_row17_col1\" class=\"data row17 col1\" >30.220053</td>\n",
-       "      <td id=\"T_c0e9c_row17_col2\" class=\"data row17 col2\" >12.207351</td>\n",
-       "      <td id=\"T_c0e9c_row17_col3\" class=\"data row17 col3\" >-18.012701</td>\n",
-       "      <td id=\"T_c0e9c_row17_col4\" class=\"data row17 col4\" >4</td>\n",
-       "      <td id=\"T_c0e9c_row17_col5\" class=\"data row17 col5\" >75</td>\n",
-       "      <td id=\"T_c0e9c_row17_col6\" class=\"data row17 col6\" >-71</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row18\" class=\"row_heading level0 row18\" >claude-instant-1.2</th>\n",
-       "      <td id=\"T_c0e9c_row18_col0\" class=\"data row18 col0\" >1112</td>\n",
-       "      <td id=\"T_c0e9c_row18_col1\" class=\"data row18 col1\" >16.127400</td>\n",
-       "      <td id=\"T_c0e9c_row18_col2\" class=\"data row18 col2\" >27.962345</td>\n",
-       "      <td id=\"T_c0e9c_row18_col3\" class=\"data row18 col3\" >11.834945</td>\n",
-       "      <td id=\"T_c0e9c_row18_col4\" class=\"data row18 col4\" >25</td>\n",
-       "      <td id=\"T_c0e9c_row18_col5\" class=\"data row18 col5\" >13</td>\n",
-       "      <td id=\"T_c0e9c_row18_col6\" class=\"data row18 col6\" >12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row19\" class=\"row_heading level0 row19\" >claude-2.1</th>\n",
-       "      <td id=\"T_c0e9c_row19_col0\" class=\"data row19 col0\" >1096</td>\n",
-       "      <td id=\"T_c0e9c_row19_col1\" class=\"data row19 col1\" >15.733507</td>\n",
-       "      <td id=\"T_c0e9c_row19_col2\" class=\"data row19 col2\" >27.394210</td>\n",
-       "      <td id=\"T_c0e9c_row19_col3\" class=\"data row19 col3\" >11.660703</td>\n",
-       "      <td id=\"T_c0e9c_row19_col4\" class=\"data row19 col4\" >29</td>\n",
-       "      <td id=\"T_c0e9c_row19_col5\" class=\"data row19 col5\" >18</td>\n",
-       "      <td id=\"T_c0e9c_row19_col6\" class=\"data row19 col6\" >11</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row20\" class=\"row_heading level0 row20\" >xwinlm-70b-v0.1</th>\n",
-       "      <td id=\"T_c0e9c_row20_col0\" class=\"data row20 col0\" >1775</td>\n",
-       "      <td id=\"T_c0e9c_row20_col1\" class=\"data row20 col1\" >21.812957</td>\n",
-       "      <td id=\"T_c0e9c_row20_col2\" class=\"data row20 col2\" >27.644496</td>\n",
-       "      <td id=\"T_c0e9c_row20_col3\" class=\"data row20 col3\" >5.831539</td>\n",
-       "      <td id=\"T_c0e9c_row20_col4\" class=\"data row20 col4\" >16</td>\n",
-       "      <td id=\"T_c0e9c_row20_col5\" class=\"data row20 col5\" >16</td>\n",
-       "      <td id=\"T_c0e9c_row20_col6\" class=\"data row20 col6\" >0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row21\" class=\"row_heading level0 row21\" >gemini-pro</th>\n",
-       "      <td id=\"T_c0e9c_row21_col0\" class=\"data row21 col0\" >1456</td>\n",
-       "      <td id=\"T_c0e9c_row21_col1\" class=\"data row21 col1\" >18.177645</td>\n",
-       "      <td id=\"T_c0e9c_row21_col2\" class=\"data row21 col2\" >27.849057</td>\n",
-       "      <td id=\"T_c0e9c_row21_col3\" class=\"data row21 col3\" >9.671412</td>\n",
-       "      <td id=\"T_c0e9c_row21_col4\" class=\"data row21 col4\" >21</td>\n",
-       "      <td id=\"T_c0e9c_row21_col5\" class=\"data row21 col5\" >15</td>\n",
-       "      <td id=\"T_c0e9c_row21_col6\" class=\"data row21 col6\" >6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row22\" class=\"row_heading level0 row22\" >Mixtral-8x7B-Instruct-v0.1</th>\n",
-       "      <td id=\"T_c0e9c_row22_col0\" class=\"data row22 col0\" >1465</td>\n",
-       "      <td id=\"T_c0e9c_row22_col1\" class=\"data row22 col1\" >18.255318</td>\n",
-       "      <td id=\"T_c0e9c_row22_col2\" class=\"data row22 col2\" >27.849703</td>\n",
-       "      <td id=\"T_c0e9c_row22_col3\" class=\"data row22 col3\" >9.594386</td>\n",
-       "      <td id=\"T_c0e9c_row22_col4\" class=\"data row22 col4\" >20</td>\n",
-       "      <td id=\"T_c0e9c_row22_col5\" class=\"data row22 col5\" >14</td>\n",
-       "      <td id=\"T_c0e9c_row22_col6\" class=\"data row22 col6\" >6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row23\" class=\"row_heading level0 row23\" >evo-v2-7b</th>\n",
-       "      <td id=\"T_c0e9c_row23_col0\" class=\"data row23 col0\" >1754</td>\n",
-       "      <td id=\"T_c0e9c_row23_col1\" class=\"data row23 col1\" >20.834113</td>\n",
-       "      <td id=\"T_c0e9c_row23_col2\" class=\"data row23 col2\" >26.807884</td>\n",
-       "      <td id=\"T_c0e9c_row23_col3\" class=\"data row23 col3\" >5.973771</td>\n",
-       "      <td id=\"T_c0e9c_row23_col4\" class=\"data row23 col4\" >18</td>\n",
-       "      <td id=\"T_c0e9c_row23_col5\" class=\"data row23 col5\" >20</td>\n",
-       "      <td id=\"T_c0e9c_row23_col6\" class=\"data row23 col6\" >-2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row24\" class=\"row_heading level0 row24\" >Mixtral-8x7B-Instruct-v0.1_verbose</th>\n",
-       "      <td id=\"T_c0e9c_row24_col0\" class=\"data row24 col0\" >2083</td>\n",
-       "      <td id=\"T_c0e9c_row24_col1\" class=\"data row24 col1\" >24.614063</td>\n",
-       "      <td id=\"T_c0e9c_row24_col2\" class=\"data row24 col2\" >23.777507</td>\n",
-       "      <td id=\"T_c0e9c_row24_col3\" class=\"data row24 col3\" >-0.836556</td>\n",
-       "      <td id=\"T_c0e9c_row24_col4\" class=\"data row24 col4\" >9</td>\n",
-       "      <td id=\"T_c0e9c_row24_col5\" class=\"data row24 col5\" >26</td>\n",
-       "      <td id=\"T_c0e9c_row24_col6\" class=\"data row24 col6\" >-17</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row25\" class=\"row_heading level0 row25\" >Mixtral-8x7B-Instruct-v0.1_concise</th>\n",
-       "      <td id=\"T_c0e9c_row25_col0\" class=\"data row25 col0\" >910</td>\n",
-       "      <td id=\"T_c0e9c_row25_col1\" class=\"data row25 col1\" >13.744040</td>\n",
-       "      <td id=\"T_c0e9c_row25_col2\" class=\"data row25 col2\" >24.932748</td>\n",
-       "      <td id=\"T_c0e9c_row25_col3\" class=\"data row25 col3\" >11.188708</td>\n",
-       "      <td id=\"T_c0e9c_row25_col4\" class=\"data row25 col4\" >39</td>\n",
-       "      <td id=\"T_c0e9c_row25_col5\" class=\"data row25 col5\" >23</td>\n",
-       "      <td id=\"T_c0e9c_row25_col6\" class=\"data row25 col6\" >16</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row26\" class=\"row_heading level0 row26\" >gpt-3.5-turbo-16k-0613</th>\n",
-       "      <td id=\"T_c0e9c_row26_col0\" class=\"data row26 col0\" >1328</td>\n",
-       "      <td id=\"T_c0e9c_row26_col1\" class=\"data row26 col1\" >14.132391</td>\n",
-       "      <td id=\"T_c0e9c_row26_col2\" class=\"data row26 col2\" >22.859543</td>\n",
-       "      <td id=\"T_c0e9c_row26_col3\" class=\"data row26 col3\" >8.727152</td>\n",
-       "      <td id=\"T_c0e9c_row26_col4\" class=\"data row26 col4\" >34</td>\n",
-       "      <td id=\"T_c0e9c_row26_col5\" class=\"data row26 col5\" >27</td>\n",
-       "      <td id=\"T_c0e9c_row26_col6\" class=\"data row26 col6\" >7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row27\" class=\"row_heading level0 row27\" >gpt-3.5-turbo-0613</th>\n",
-       "      <td id=\"T_c0e9c_row27_col0\" class=\"data row27 col0\" >1331</td>\n",
-       "      <td id=\"T_c0e9c_row27_col1\" class=\"data row27 col1\" >14.095799</td>\n",
-       "      <td id=\"T_c0e9c_row27_col2\" class=\"data row27 col2\" >22.774144</td>\n",
-       "      <td id=\"T_c0e9c_row27_col3\" class=\"data row27 col3\" >8.678345</td>\n",
-       "      <td id=\"T_c0e9c_row27_col4\" class=\"data row27 col4\" >35</td>\n",
-       "      <td id=\"T_c0e9c_row27_col5\" class=\"data row27 col5\" >28</td>\n",
-       "      <td id=\"T_c0e9c_row27_col6\" class=\"data row27 col6\" >7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row28\" class=\"row_heading level0 row28\" >gpt-3.5-turbo-1106_verbose</th>\n",
-       "      <td id=\"T_c0e9c_row28_col0\" class=\"data row28 col0\" >1058</td>\n",
-       "      <td id=\"T_c0e9c_row28_col1\" class=\"data row28 col1\" >12.763170</td>\n",
-       "      <td id=\"T_c0e9c_row28_col2\" class=\"data row28 col2\" >22.434952</td>\n",
-       "      <td id=\"T_c0e9c_row28_col3\" class=\"data row28 col3\" >9.671782</td>\n",
-       "      <td id=\"T_c0e9c_row28_col4\" class=\"data row28 col4\" >43</td>\n",
-       "      <td id=\"T_c0e9c_row28_col5\" class=\"data row28 col5\" >29</td>\n",
-       "      <td id=\"T_c0e9c_row28_col6\" class=\"data row28 col6\" >14</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row29\" class=\"row_heading level0 row29\" >gpt4_0613_concise</th>\n",
-       "      <td id=\"T_c0e9c_row29_col0\" class=\"data row29 col0\" >627</td>\n",
-       "      <td id=\"T_c0e9c_row29_col1\" class=\"data row29 col1\" >9.400321</td>\n",
-       "      <td id=\"T_c0e9c_row29_col2\" class=\"data row29 col2\" >17.766751</td>\n",
-       "      <td id=\"T_c0e9c_row29_col3\" class=\"data row29 col3\" >8.366430</td>\n",
-       "      <td id=\"T_c0e9c_row29_col4\" class=\"data row29 col4\" >61</td>\n",
-       "      <td id=\"T_c0e9c_row29_col5\" class=\"data row29 col5\" >42</td>\n",
-       "      <td id=\"T_c0e9c_row29_col6\" class=\"data row29 col6\" >19</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row30\" class=\"row_heading level0 row30\" >pairrm-tulu-2-70b</th>\n",
-       "      <td id=\"T_c0e9c_row30_col0\" class=\"data row30 col0\" >1607</td>\n",
-       "      <td id=\"T_c0e9c_row30_col1\" class=\"data row30 col1\" >18.638963</td>\n",
-       "      <td id=\"T_c0e9c_row30_col2\" class=\"data row30 col2\" >26.379740</td>\n",
-       "      <td id=\"T_c0e9c_row30_col3\" class=\"data row30 col3\" >7.740777</td>\n",
-       "      <td id=\"T_c0e9c_row30_col4\" class=\"data row30 col4\" >19</td>\n",
-       "      <td id=\"T_c0e9c_row30_col5\" class=\"data row30 col5\" >22</td>\n",
-       "      <td id=\"T_c0e9c_row30_col6\" class=\"data row30 col6\" >-3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row31\" class=\"row_heading level0 row31\" >tulu-2-dpo-70b</th>\n",
-       "      <td id=\"T_c0e9c_row31_col0\" class=\"data row31 col0\" >1418</td>\n",
-       "      <td id=\"T_c0e9c_row31_col1\" class=\"data row31 col1\" >15.982854</td>\n",
-       "      <td id=\"T_c0e9c_row31_col2\" class=\"data row31 col2\" >24.913121</td>\n",
-       "      <td id=\"T_c0e9c_row31_col3\" class=\"data row31 col3\" >8.930267</td>\n",
-       "      <td id=\"T_c0e9c_row31_col4\" class=\"data row31 col4\" >27</td>\n",
-       "      <td id=\"T_c0e9c_row31_col5\" class=\"data row31 col5\" >24</td>\n",
-       "      <td id=\"T_c0e9c_row31_col6\" class=\"data row31 col6\" >3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row32\" class=\"row_heading level0 row32\" >Mistral-7B-ReMax-v0.1</th>\n",
-       "      <td id=\"T_c0e9c_row32_col0\" class=\"data row32 col0\" >1478</td>\n",
-       "      <td id=\"T_c0e9c_row32_col1\" class=\"data row32 col1\" >15.999331</td>\n",
-       "      <td id=\"T_c0e9c_row32_col2\" class=\"data row32 col2\" >24.256479</td>\n",
-       "      <td id=\"T_c0e9c_row32_col3\" class=\"data row32 col3\" >8.257148</td>\n",
-       "      <td id=\"T_c0e9c_row32_col4\" class=\"data row32 col4\" >26</td>\n",
-       "      <td id=\"T_c0e9c_row32_col5\" class=\"data row32 col5\" >25</td>\n",
-       "      <td id=\"T_c0e9c_row32_col6\" class=\"data row32 col6\" >1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row33\" class=\"row_heading level0 row33\" >gpt-3.5-turbo-1106</th>\n",
-       "      <td id=\"T_c0e9c_row33_col0\" class=\"data row33 col0\" >796</td>\n",
-       "      <td id=\"T_c0e9c_row33_col1\" class=\"data row33 col1\" >9.177965</td>\n",
-       "      <td id=\"T_c0e9c_row33_col2\" class=\"data row33 col2\" >16.971183</td>\n",
-       "      <td id=\"T_c0e9c_row33_col3\" class=\"data row33 col3\" >7.793218</td>\n",
-       "      <td id=\"T_c0e9c_row33_col4\" class=\"data row33 col4\" >64</td>\n",
-       "      <td id=\"T_c0e9c_row33_col5\" class=\"data row33 col5\" >49</td>\n",
-       "      <td id=\"T_c0e9c_row33_col6\" class=\"data row33 col6\" >15</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row34\" class=\"row_heading level0 row34\" >LMCocktail-10.7B-v1</th>\n",
-       "      <td id=\"T_c0e9c_row34_col0\" class=\"data row34 col0\" >1203</td>\n",
-       "      <td id=\"T_c0e9c_row34_col1\" class=\"data row34 col1\" >13.153431</td>\n",
-       "      <td id=\"T_c0e9c_row34_col2\" class=\"data row34 col2\" >22.215803</td>\n",
-       "      <td id=\"T_c0e9c_row34_col3\" class=\"data row34 col3\" >9.062372</td>\n",
-       "      <td id=\"T_c0e9c_row34_col4\" class=\"data row34 col4\" >40</td>\n",
-       "      <td id=\"T_c0e9c_row34_col5\" class=\"data row34 col5\" >30</td>\n",
-       "      <td id=\"T_c0e9c_row34_col6\" class=\"data row34 col6\" >10</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row35\" class=\"row_heading level0 row35\" >internlm2-chat-20b-ppo</th>\n",
-       "      <td id=\"T_c0e9c_row35_col0\" class=\"data row35 col0\" >2373</td>\n",
-       "      <td id=\"T_c0e9c_row35_col1\" class=\"data row35 col1\" >21.749155</td>\n",
-       "      <td id=\"T_c0e9c_row35_col2\" class=\"data row35 col2\" >14.939076</td>\n",
-       "      <td id=\"T_c0e9c_row35_col3\" class=\"data row35 col3\" >-6.810079</td>\n",
-       "      <td id=\"T_c0e9c_row35_col4\" class=\"data row35 col4\" >17</td>\n",
-       "      <td id=\"T_c0e9c_row35_col5\" class=\"data row35 col5\" >60</td>\n",
-       "      <td id=\"T_c0e9c_row35_col6\" class=\"data row35 col6\" >-43</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row36\" class=\"row_heading level0 row36\" >claude-2.1_concise</th>\n",
-       "      <td id=\"T_c0e9c_row36_col0\" class=\"data row36 col0\" >573</td>\n",
-       "      <td id=\"T_c0e9c_row36_col1\" class=\"data row36 col1\" >9.227125</td>\n",
-       "      <td id=\"T_c0e9c_row36_col2\" class=\"data row36 col2\" >17.538143</td>\n",
-       "      <td id=\"T_c0e9c_row36_col3\" class=\"data row36 col3\" >8.311018</td>\n",
-       "      <td id=\"T_c0e9c_row36_col4\" class=\"data row36 col4\" >63</td>\n",
-       "      <td id=\"T_c0e9c_row36_col5\" class=\"data row36 col5\" >46</td>\n",
-       "      <td id=\"T_c0e9c_row36_col6\" class=\"data row36 col6\" >17</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row37\" class=\"row_heading level0 row37\" >gpt-3.5-turbo-0301</th>\n",
-       "      <td id=\"T_c0e9c_row37_col0\" class=\"data row37 col0\" >827</td>\n",
-       "      <td id=\"T_c0e9c_row37_col1\" class=\"data row37 col1\" >9.622453</td>\n",
-       "      <td id=\"T_c0e9c_row37_col2\" class=\"data row37 col2\" >17.707654</td>\n",
-       "      <td id=\"T_c0e9c_row37_col3\" class=\"data row37 col3\" >8.085200</td>\n",
-       "      <td id=\"T_c0e9c_row37_col4\" class=\"data row37 col4\" >58</td>\n",
-       "      <td id=\"T_c0e9c_row37_col5\" class=\"data row37 col5\" >43</td>\n",
-       "      <td id=\"T_c0e9c_row37_col6\" class=\"data row37 col6\" >15</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row38\" class=\"row_heading level0 row38\" >xwinlm-13b-v0.1</th>\n",
-       "      <td id=\"T_c0e9c_row38_col0\" class=\"data row38 col0\" >1894</td>\n",
-       "      <td id=\"T_c0e9c_row38_col1\" class=\"data row38 col1\" >17.427935</td>\n",
-       "      <td id=\"T_c0e9c_row38_col2\" class=\"data row38 col2\" >20.107837</td>\n",
-       "      <td id=\"T_c0e9c_row38_col3\" class=\"data row38 col3\" >2.679903</td>\n",
-       "      <td id=\"T_c0e9c_row38_col4\" class=\"data row38 col4\" >22</td>\n",
-       "      <td id=\"T_c0e9c_row38_col5\" class=\"data row38 col5\" >34</td>\n",
-       "      <td id=\"T_c0e9c_row38_col6\" class=\"data row38 col6\" >-12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row39\" class=\"row_heading level0 row39\" >deepseek-llm-67b-chat</th>\n",
-       "      <td id=\"T_c0e9c_row39_col0\" class=\"data row39 col0\" >1151</td>\n",
-       "      <td id=\"T_c0e9c_row39_col1\" class=\"data row39 col1\" >12.093422</td>\n",
-       "      <td id=\"T_c0e9c_row39_col2\" class=\"data row39 col2\" >20.744121</td>\n",
-       "      <td id=\"T_c0e9c_row39_col3\" class=\"data row39 col3\" >8.650699</td>\n",
-       "      <td id=\"T_c0e9c_row39_col4\" class=\"data row39 col4\" >46</td>\n",
-       "      <td id=\"T_c0e9c_row39_col5\" class=\"data row39 col5\" >33</td>\n",
-       "      <td id=\"T_c0e9c_row39_col6\" class=\"data row39 col6\" >13</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row40\" class=\"row_heading level0 row40\" >gpt35_turbo_instruct</th>\n",
-       "      <td id=\"T_c0e9c_row40_col0\" class=\"data row40 col0\" >1018</td>\n",
-       "      <td id=\"T_c0e9c_row40_col1\" class=\"data row40 col1\" >8.462447</td>\n",
-       "      <td id=\"T_c0e9c_row40_col2\" class=\"data row40 col2\" >15.014996</td>\n",
-       "      <td id=\"T_c0e9c_row40_col3\" class=\"data row40 col3\" >6.552549</td>\n",
-       "      <td id=\"T_c0e9c_row40_col4\" class=\"data row40 col4\" >68</td>\n",
-       "      <td id=\"T_c0e9c_row40_col5\" class=\"data row40 col5\" >57</td>\n",
-       "      <td id=\"T_c0e9c_row40_col6\" class=\"data row40 col6\" >11</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row41\" class=\"row_heading level0 row41\" >wizardlm-70b</th>\n",
-       "      <td id=\"T_c0e9c_row41_col0\" class=\"data row41 col0\" >1545</td>\n",
-       "      <td id=\"T_c0e9c_row41_col1\" class=\"data row41 col1\" >14.383896</td>\n",
-       "      <td id=\"T_c0e9c_row41_col2\" class=\"data row41 col2\" >21.076106</td>\n",
-       "      <td id=\"T_c0e9c_row41_col3\" class=\"data row41 col3\" >6.692210</td>\n",
-       "      <td id=\"T_c0e9c_row41_col4\" class=\"data row41 col4\" >32</td>\n",
-       "      <td id=\"T_c0e9c_row41_col5\" class=\"data row41 col5\" >32</td>\n",
-       "      <td id=\"T_c0e9c_row41_col6\" class=\"data row41 col6\" >0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row42\" class=\"row_heading level0 row42\" >vicuna-33b-v1.3</th>\n",
-       "      <td id=\"T_c0e9c_row42_col0\" class=\"data row42 col0\" >1479</td>\n",
-       "      <td id=\"T_c0e9c_row42_col1\" class=\"data row42 col1\" >12.705948</td>\n",
-       "      <td id=\"T_c0e9c_row42_col2\" class=\"data row42 col2\" >19.254076</td>\n",
-       "      <td id=\"T_c0e9c_row42_col3\" class=\"data row42 col3\" >6.548128</td>\n",
-       "      <td id=\"T_c0e9c_row42_col4\" class=\"data row42 col4\" >44</td>\n",
-       "      <td id=\"T_c0e9c_row42_col5\" class=\"data row42 col5\" >39</td>\n",
-       "      <td id=\"T_c0e9c_row42_col6\" class=\"data row42 col6\" >5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row43\" class=\"row_heading level0 row43\" >pairrm-tulu-2-13b</th>\n",
-       "      <td id=\"T_c0e9c_row43_col0\" class=\"data row43 col0\" >1454</td>\n",
-       "      <td id=\"T_c0e9c_row43_col1\" class=\"data row43 col1\" >13.831901</td>\n",
-       "      <td id=\"T_c0e9c_row43_col2\" class=\"data row43 col2\" >21.210973</td>\n",
-       "      <td id=\"T_c0e9c_row43_col3\" class=\"data row43 col3\" >7.379072</td>\n",
-       "      <td id=\"T_c0e9c_row43_col4\" class=\"data row43 col4\" >38</td>\n",
-       "      <td id=\"T_c0e9c_row43_col5\" class=\"data row43 col5\" >31</td>\n",
-       "      <td id=\"T_c0e9c_row43_col6\" class=\"data row43 col6\" >7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row44\" class=\"row_heading level0 row44\" >Mistral-7B-Instruct-v0.2</th>\n",
-       "      <td id=\"T_c0e9c_row44_col0\" class=\"data row44 col0\" >1676</td>\n",
-       "      <td id=\"T_c0e9c_row44_col1\" class=\"data row44 col1\" >14.722773</td>\n",
-       "      <td id=\"T_c0e9c_row44_col2\" class=\"data row44 col2\" >19.973105</td>\n",
-       "      <td id=\"T_c0e9c_row44_col3\" class=\"data row44 col3\" >5.250332</td>\n",
-       "      <td id=\"T_c0e9c_row44_col4\" class=\"data row44 col4\" >31</td>\n",
-       "      <td id=\"T_c0e9c_row44_col5\" class=\"data row44 col5\" >35</td>\n",
-       "      <td id=\"T_c0e9c_row44_col6\" class=\"data row44 col6\" >-4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row45\" class=\"row_heading level0 row45\" >evo-7b</th>\n",
-       "      <td id=\"T_c0e9c_row45_col0\" class=\"data row45 col0\" >1774</td>\n",
-       "      <td id=\"T_c0e9c_row45_col1\" class=\"data row45 col1\" >15.577437</td>\n",
-       "      <td id=\"T_c0e9c_row45_col2\" class=\"data row45 col2\" >19.756415</td>\n",
-       "      <td id=\"T_c0e9c_row45_col3\" class=\"data row45 col3\" >4.178978</td>\n",
-       "      <td id=\"T_c0e9c_row45_col4\" class=\"data row45 col4\" >30</td>\n",
-       "      <td id=\"T_c0e9c_row45_col5\" class=\"data row45 col5\" >36</td>\n",
-       "      <td id=\"T_c0e9c_row45_col6\" class=\"data row45 col6\" >-6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row46\" class=\"row_heading level0 row46\" >humpback-llama2-70b</th>\n",
-       "      <td id=\"T_c0e9c_row46_col0\" class=\"data row46 col0\" >1107</td>\n",
-       "      <td id=\"T_c0e9c_row46_col1\" class=\"data row46 col1\" >10.121772</td>\n",
-       "      <td id=\"T_c0e9c_row46_col2\" class=\"data row46 col2\" >17.572810</td>\n",
-       "      <td id=\"T_c0e9c_row46_col3\" class=\"data row46 col3\" >7.451039</td>\n",
-       "      <td id=\"T_c0e9c_row46_col4\" class=\"data row46 col4\" >56</td>\n",
-       "      <td id=\"T_c0e9c_row46_col5\" class=\"data row46 col5\" >45</td>\n",
-       "      <td id=\"T_c0e9c_row46_col6\" class=\"data row46 col6\" >11</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row47\" class=\"row_heading level0 row47\" >OpenHermes-2.5-Mistral-7B</th>\n",
-       "      <td id=\"T_c0e9c_row47_col0\" class=\"data row47 col0\" >1107</td>\n",
-       "      <td id=\"T_c0e9c_row47_col1\" class=\"data row47 col1\" >10.340416</td>\n",
-       "      <td id=\"T_c0e9c_row47_col2\" class=\"data row47 col2\" >17.952407</td>\n",
-       "      <td id=\"T_c0e9c_row47_col3\" class=\"data row47 col3\" >7.611992</td>\n",
-       "      <td id=\"T_c0e9c_row47_col4\" class=\"data row47 col4\" >55</td>\n",
-       "      <td id=\"T_c0e9c_row47_col5\" class=\"data row47 col5\" >41</td>\n",
-       "      <td id=\"T_c0e9c_row47_col6\" class=\"data row47 col6\" >14</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row48\" class=\"row_heading level0 row48\" >deita-7b-v1.0</th>\n",
-       "      <td id=\"T_c0e9c_row48_col0\" class=\"data row48 col0\" >1417</td>\n",
-       "      <td id=\"T_c0e9c_row48_col1\" class=\"data row48 col1\" >12.646639</td>\n",
-       "      <td id=\"T_c0e9c_row48_col2\" class=\"data row48 col2\" >19.721522</td>\n",
-       "      <td id=\"T_c0e9c_row48_col3\" class=\"data row48 col3\" >7.074882</td>\n",
-       "      <td id=\"T_c0e9c_row48_col4\" class=\"data row48 col4\" >45</td>\n",
-       "      <td id=\"T_c0e9c_row48_col5\" class=\"data row48 col5\" >37</td>\n",
-       "      <td id=\"T_c0e9c_row48_col6\" class=\"data row48 col6\" >8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row49\" class=\"row_heading level0 row49\" >jina-chat</th>\n",
-       "      <td id=\"T_c0e9c_row49_col0\" class=\"data row49 col0\" >676</td>\n",
-       "      <td id=\"T_c0e9c_row49_col1\" class=\"data row49 col1\" >7.786130</td>\n",
-       "      <td id=\"T_c0e9c_row49_col2\" class=\"data row49 col2\" >14.633052</td>\n",
-       "      <td id=\"T_c0e9c_row49_col3\" class=\"data row49 col3\" >6.846921</td>\n",
-       "      <td id=\"T_c0e9c_row49_col4\" class=\"data row49 col4\" >74</td>\n",
-       "      <td id=\"T_c0e9c_row49_col5\" class=\"data row49 col5\" >61</td>\n",
-       "      <td id=\"T_c0e9c_row49_col6\" class=\"data row49 col6\" >13</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row50\" class=\"row_heading level0 row50\" >gpt-3.5-turbo-1106_concise</th>\n",
-       "      <td id=\"T_c0e9c_row50_col0\" class=\"data row50 col0\" >431</td>\n",
-       "      <td id=\"T_c0e9c_row50_col1\" class=\"data row50 col1\" >7.415865</td>\n",
-       "      <td id=\"T_c0e9c_row50_col2\" class=\"data row50 col2\" >14.270598</td>\n",
-       "      <td id=\"T_c0e9c_row50_col3\" class=\"data row50 col3\" >6.854733</td>\n",
-       "      <td id=\"T_c0e9c_row50_col4\" class=\"data row50 col4\" >82</td>\n",
-       "      <td id=\"T_c0e9c_row50_col5\" class=\"data row50 col5\" >62</td>\n",
-       "      <td id=\"T_c0e9c_row50_col6\" class=\"data row50 col6\" >20</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row51\" class=\"row_heading level0 row51\" >causallm-14b</th>\n",
-       "      <td id=\"T_c0e9c_row51_col0\" class=\"data row51 col0\" >1391</td>\n",
-       "      <td id=\"T_c0e9c_row51_col1\" class=\"data row51 col1\" >11.146161</td>\n",
-       "      <td id=\"T_c0e9c_row51_col2\" class=\"data row51 col2\" >17.577840</td>\n",
-       "      <td id=\"T_c0e9c_row51_col3\" class=\"data row51 col3\" >6.431679</td>\n",
-       "      <td id=\"T_c0e9c_row51_col4\" class=\"data row51 col4\" >51</td>\n",
-       "      <td id=\"T_c0e9c_row51_col5\" class=\"data row51 col5\" >44</td>\n",
-       "      <td id=\"T_c0e9c_row51_col6\" class=\"data row51 col6\" >7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row52\" class=\"row_heading level0 row52\" >pairrm-zephyr-7b-beta</th>\n",
-       "      <td id=\"T_c0e9c_row52_col0\" class=\"data row52 col0\" >1487</td>\n",
-       "      <td id=\"T_c0e9c_row52_col1\" class=\"data row52 col1\" >12.841278</td>\n",
-       "      <td id=\"T_c0e9c_row52_col2\" class=\"data row52 col2\" >19.383394</td>\n",
-       "      <td id=\"T_c0e9c_row52_col3\" class=\"data row52 col3\" >6.542116</td>\n",
-       "      <td id=\"T_c0e9c_row52_col4\" class=\"data row52 col4\" >42</td>\n",
-       "      <td id=\"T_c0e9c_row52_col5\" class=\"data row52 col5\" >38</td>\n",
-       "      <td id=\"T_c0e9c_row52_col6\" class=\"data row52 col6\" >4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row53\" class=\"row_heading level0 row53\" >Starling-LM-7B-alpha</th>\n",
-       "      <td id=\"T_c0e9c_row53_col0\" class=\"data row53 col0\" >1895</td>\n",
-       "      <td id=\"T_c0e9c_row53_col1\" class=\"data row53 col1\" >14.245924</td>\n",
-       "      <td id=\"T_c0e9c_row53_col2\" class=\"data row53 col2\" >16.422615</td>\n",
-       "      <td id=\"T_c0e9c_row53_col3\" class=\"data row53 col3\" >2.176692</td>\n",
-       "      <td id=\"T_c0e9c_row53_col4\" class=\"data row53 col4\" >33</td>\n",
-       "      <td id=\"T_c0e9c_row53_col5\" class=\"data row53 col5\" >54</td>\n",
-       "      <td id=\"T_c0e9c_row53_col6\" class=\"data row53 col6\" >-21</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row54\" class=\"row_heading level0 row54\" >llama-2-70b-chat-hf</th>\n",
-       "      <td id=\"T_c0e9c_row54_col0\" class=\"data row54 col0\" >1790</td>\n",
-       "      <td id=\"T_c0e9c_row54_col1\" class=\"data row54 col1\" >13.888258</td>\n",
-       "      <td id=\"T_c0e9c_row54_col2\" class=\"data row54 col2\" >17.406987</td>\n",
-       "      <td id=\"T_c0e9c_row54_col3\" class=\"data row54 col3\" >3.518729</td>\n",
-       "      <td id=\"T_c0e9c_row54_col4\" class=\"data row54 col4\" >36</td>\n",
-       "      <td id=\"T_c0e9c_row54_col5\" class=\"data row54 col5\" >47</td>\n",
-       "      <td id=\"T_c0e9c_row54_col6\" class=\"data row54 col6\" >-11</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row55\" class=\"row_heading level0 row55\" >openchat-v3.1-13b</th>\n",
-       "      <td id=\"T_c0e9c_row55_col0\" class=\"data row55 col0\" >1484</td>\n",
-       "      <td id=\"T_c0e9c_row55_col1\" class=\"data row55 col1\" >11.082230</td>\n",
-       "      <td id=\"T_c0e9c_row55_col2\" class=\"data row55 col2\" >16.752762</td>\n",
-       "      <td id=\"T_c0e9c_row55_col3\" class=\"data row55 col3\" >5.670531</td>\n",
-       "      <td id=\"T_c0e9c_row55_col4\" class=\"data row55 col4\" >52</td>\n",
-       "      <td id=\"T_c0e9c_row55_col5\" class=\"data row55 col5\" >51</td>\n",
-       "      <td id=\"T_c0e9c_row55_col6\" class=\"data row55 col6\" >1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row56\" class=\"row_heading level0 row56\" >wizardlm-13b-v1.2</th>\n",
-       "      <td id=\"T_c0e9c_row56_col0\" class=\"data row56 col0\" >1635</td>\n",
-       "      <td id=\"T_c0e9c_row56_col1\" class=\"data row56 col1\" >12.027480</td>\n",
-       "      <td id=\"T_c0e9c_row56_col2\" class=\"data row56 col2\" >16.740614</td>\n",
-       "      <td id=\"T_c0e9c_row56_col3\" class=\"data row56 col3\" >4.713134</td>\n",
-       "      <td id=\"T_c0e9c_row56_col4\" class=\"data row56 col4\" >47</td>\n",
-       "      <td id=\"T_c0e9c_row56_col5\" class=\"data row56 col5\" >52</td>\n",
-       "      <td id=\"T_c0e9c_row56_col6\" class=\"data row56 col6\" >-5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row57\" class=\"row_heading level0 row57\" >ultralm-13b-v2.0-best-of-16</th>\n",
-       "      <td id=\"T_c0e9c_row57_col0\" class=\"data row57 col0\" >1720</td>\n",
-       "      <td id=\"T_c0e9c_row57_col1\" class=\"data row57 col1\" >13.853373</td>\n",
-       "      <td id=\"T_c0e9c_row57_col2\" class=\"data row57 col2\" >18.253509</td>\n",
-       "      <td id=\"T_c0e9c_row57_col3\" class=\"data row57 col3\" >4.400135</td>\n",
-       "      <td id=\"T_c0e9c_row57_col4\" class=\"data row57 col4\" >37</td>\n",
-       "      <td id=\"T_c0e9c_row57_col5\" class=\"data row57 col5\" >40</td>\n",
-       "      <td id=\"T_c0e9c_row57_col6\" class=\"data row57 col6\" >-3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row58\" class=\"row_heading level0 row58\" >wizardlm-13b-v1.1</th>\n",
-       "      <td id=\"T_c0e9c_row58_col0\" class=\"data row58 col0\" >1525</td>\n",
-       "      <td id=\"T_c0e9c_row58_col1\" class=\"data row58 col1\" >11.233910</td>\n",
-       "      <td id=\"T_c0e9c_row58_col2\" class=\"data row58 col2\" >16.634963</td>\n",
-       "      <td id=\"T_c0e9c_row58_col3\" class=\"data row58 col3\" >5.401054</td>\n",
-       "      <td id=\"T_c0e9c_row58_col4\" class=\"data row58 col4\" >50</td>\n",
-       "      <td id=\"T_c0e9c_row58_col5\" class=\"data row58 col5\" >53</td>\n",
-       "      <td id=\"T_c0e9c_row58_col6\" class=\"data row58 col6\" >-3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row59\" class=\"row_heading level0 row59\" >zephyr-7b-beta</th>\n",
-       "      <td id=\"T_c0e9c_row59_col0\" class=\"data row59 col0\" >1444</td>\n",
-       "      <td id=\"T_c0e9c_row59_col1\" class=\"data row59 col1\" >10.992886</td>\n",
-       "      <td id=\"T_c0e9c_row59_col2\" class=\"data row59 col2\" >16.935617</td>\n",
-       "      <td id=\"T_c0e9c_row59_col3\" class=\"data row59 col3\" >5.942731</td>\n",
-       "      <td id=\"T_c0e9c_row59_col4\" class=\"data row59 col4\" >53</td>\n",
-       "      <td id=\"T_c0e9c_row59_col5\" class=\"data row59 col5\" >50</td>\n",
-       "      <td id=\"T_c0e9c_row59_col6\" class=\"data row59 col6\" >3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row60\" class=\"row_heading level0 row60\" >dolphin-2.2.1-mistral-7b</th>\n",
-       "      <td id=\"T_c0e9c_row60_col0\" class=\"data row60 col0\" >1130</td>\n",
-       "      <td id=\"T_c0e9c_row60_col1\" class=\"data row60 col1\" >9.039800</td>\n",
-       "      <td id=\"T_c0e9c_row60_col2\" class=\"data row60 col2\" >15.597487</td>\n",
-       "      <td id=\"T_c0e9c_row60_col3\" class=\"data row60 col3\" >6.557688</td>\n",
-       "      <td id=\"T_c0e9c_row60_col4\" class=\"data row60 col4\" >66</td>\n",
-       "      <td id=\"T_c0e9c_row60_col5\" class=\"data row60 col5\" >56</td>\n",
-       "      <td id=\"T_c0e9c_row60_col6\" class=\"data row60 col6\" >10</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row61\" class=\"row_heading level0 row61\" >humpback-llama-65b</th>\n",
-       "      <td id=\"T_c0e9c_row61_col0\" class=\"data row61 col0\" >1232</td>\n",
-       "      <td id=\"T_c0e9c_row61_col1\" class=\"data row61 col1\" >9.425139</td>\n",
-       "      <td id=\"T_c0e9c_row61_col2\" class=\"data row61 col2\" >15.772346</td>\n",
-       "      <td id=\"T_c0e9c_row61_col3\" class=\"data row61 col3\" >6.347206</td>\n",
-       "      <td id=\"T_c0e9c_row61_col4\" class=\"data row61 col4\" >60</td>\n",
-       "      <td id=\"T_c0e9c_row61_col5\" class=\"data row61 col5\" >55</td>\n",
-       "      <td id=\"T_c0e9c_row61_col6\" class=\"data row61 col6\" >5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row62\" class=\"row_heading level0 row62\" >openbuddy-llama2-70b-v10.1</th>\n",
-       "      <td id=\"T_c0e9c_row62_col0\" class=\"data row62 col0\" >1077</td>\n",
-       "      <td id=\"T_c0e9c_row62_col1\" class=\"data row62 col1\" >8.096422</td>\n",
-       "      <td id=\"T_c0e9c_row62_col2\" class=\"data row62 col2\" >14.165353</td>\n",
-       "      <td id=\"T_c0e9c_row62_col3\" class=\"data row62 col3\" >6.068931</td>\n",
-       "      <td id=\"T_c0e9c_row62_col4\" class=\"data row62 col4\" >72</td>\n",
-       "      <td id=\"T_c0e9c_row62_col5\" class=\"data row62 col5\" >64</td>\n",
-       "      <td id=\"T_c0e9c_row62_col6\" class=\"data row62 col6\" >8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row63\" class=\"row_heading level0 row63\" >openbuddy-llama-65b-v8</th>\n",
-       "      <td id=\"T_c0e9c_row63_col0\" class=\"data row63 col0\" >1162</td>\n",
-       "      <td id=\"T_c0e9c_row63_col1\" class=\"data row63 col1\" >8.770650</td>\n",
-       "      <td id=\"T_c0e9c_row63_col2\" class=\"data row63 col2\" >14.997012</td>\n",
-       "      <td id=\"T_c0e9c_row63_col3\" class=\"data row63 col3\" >6.226362</td>\n",
-       "      <td id=\"T_c0e9c_row63_col4\" class=\"data row63 col4\" >67</td>\n",
-       "      <td id=\"T_c0e9c_row63_col5\" class=\"data row63 col5\" >58</td>\n",
-       "      <td id=\"T_c0e9c_row63_col6\" class=\"data row63 col6\" >9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row64\" class=\"row_heading level0 row64\" >Qwen-14B-Chat</th>\n",
-       "      <td id=\"T_c0e9c_row64_col0\" class=\"data row64 col0\" >1013</td>\n",
-       "      <td id=\"T_c0e9c_row64_col1\" class=\"data row64 col1\" >7.502333</td>\n",
-       "      <td id=\"T_c0e9c_row64_col2\" class=\"data row64 col2\" >13.326422</td>\n",
-       "      <td id=\"T_c0e9c_row64_col3\" class=\"data row64 col3\" >5.824088</td>\n",
-       "      <td id=\"T_c0e9c_row64_col4\" class=\"data row64 col4\" >79</td>\n",
-       "      <td id=\"T_c0e9c_row64_col5\" class=\"data row64 col5\" >70</td>\n",
-       "      <td id=\"T_c0e9c_row64_col6\" class=\"data row64 col6\" >9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row65\" class=\"row_heading level0 row65\" >gpt4_gamed</th>\n",
-       "      <td id=\"T_c0e9c_row65_col0\" class=\"data row65 col0\" >68</td>\n",
-       "      <td id=\"T_c0e9c_row65_col1\" class=\"data row65 col1\" >3.738337</td>\n",
-       "      <td id=\"T_c0e9c_row65_col2\" class=\"data row65 col2\" >7.337086</td>\n",
-       "      <td id=\"T_c0e9c_row65_col3\" class=\"data row65 col3\" >3.598749</td>\n",
-       "      <td id=\"T_c0e9c_row65_col4\" class=\"data row65 col4\" >110</td>\n",
-       "      <td id=\"T_c0e9c_row65_col5\" class=\"data row65 col5\" >109</td>\n",
-       "      <td id=\"T_c0e9c_row65_col6\" class=\"data row65 col6\" >1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row66\" class=\"row_heading level0 row66\" >cut-13b</th>\n",
-       "      <td id=\"T_c0e9c_row66_col0\" class=\"data row66 col0\" >1637</td>\n",
-       "      <td id=\"T_c0e9c_row66_col1\" class=\"data row66 col1\" >10.779089</td>\n",
-       "      <td id=\"T_c0e9c_row66_col2\" class=\"data row66 col2\" >14.984761</td>\n",
-       "      <td id=\"T_c0e9c_row66_col3\" class=\"data row66 col3\" >4.205672</td>\n",
-       "      <td id=\"T_c0e9c_row66_col4\" class=\"data row66 col4\" >54</td>\n",
-       "      <td id=\"T_c0e9c_row66_col5\" class=\"data row66 col5\" >59</td>\n",
-       "      <td id=\"T_c0e9c_row66_col6\" class=\"data row66 col6\" >-5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row67\" class=\"row_heading level0 row67\" >openchat-v2-w-13b</th>\n",
-       "      <td id=\"T_c0e9c_row67_col0\" class=\"data row67 col0\" >1566</td>\n",
-       "      <td id=\"T_c0e9c_row67_col1\" class=\"data row67 col1\" >9.615344</td>\n",
-       "      <td id=\"T_c0e9c_row67_col2\" class=\"data row67 col2\" >13.929201</td>\n",
-       "      <td id=\"T_c0e9c_row67_col3\" class=\"data row67 col3\" >4.313857</td>\n",
-       "      <td id=\"T_c0e9c_row67_col4\" class=\"data row67 col4\" >59</td>\n",
-       "      <td id=\"T_c0e9c_row67_col5\" class=\"data row67 col5\" >66</td>\n",
-       "      <td id=\"T_c0e9c_row67_col6\" class=\"data row67 col6\" >-7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row68\" class=\"row_heading level0 row68\" >tulu-2-dpo-13b</th>\n",
-       "      <td id=\"T_c0e9c_row68_col0\" class=\"data row68 col0\" >1614</td>\n",
-       "      <td id=\"T_c0e9c_row68_col1\" class=\"data row68 col1\" >10.119788</td>\n",
-       "      <td id=\"T_c0e9c_row68_col2\" class=\"data row68 col2\" >14.263755</td>\n",
-       "      <td id=\"T_c0e9c_row68_col3\" class=\"data row68 col3\" >4.143966</td>\n",
-       "      <td id=\"T_c0e9c_row68_col4\" class=\"data row68 col4\" >57</td>\n",
-       "      <td id=\"T_c0e9c_row68_col5\" class=\"data row68 col5\" >63</td>\n",
-       "      <td id=\"T_c0e9c_row68_col6\" class=\"data row68 col6\" >-6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row69\" class=\"row_heading level0 row69\" >claude2-alpaca-13b</th>\n",
-       "      <td id=\"T_c0e9c_row69_col0\" class=\"data row69 col0\" >1127</td>\n",
-       "      <td id=\"T_c0e9c_row69_col1\" class=\"data row69 col1\" >7.437351</td>\n",
-       "      <td id=\"T_c0e9c_row69_col2\" class=\"data row69 col2\" >12.843132</td>\n",
-       "      <td id=\"T_c0e9c_row69_col3\" class=\"data row69 col3\" >5.405781</td>\n",
-       "      <td id=\"T_c0e9c_row69_col4\" class=\"data row69 col4\" >81</td>\n",
-       "      <td id=\"T_c0e9c_row69_col5\" class=\"data row69 col5\" >72</td>\n",
-       "      <td id=\"T_c0e9c_row69_col6\" class=\"data row69 col6\" >9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row70\" class=\"row_heading level0 row70\" >minotaur-13b</th>\n",
-       "      <td id=\"T_c0e9c_row70_col0\" class=\"data row70 col0\" >881</td>\n",
-       "      <td id=\"T_c0e9c_row70_col1\" class=\"data row70 col1\" >5.738964</td>\n",
-       "      <td id=\"T_c0e9c_row70_col2\" class=\"data row70 col2\" >10.465746</td>\n",
-       "      <td id=\"T_c0e9c_row70_col3\" class=\"data row70 col3\" >4.726782</td>\n",
-       "      <td id=\"T_c0e9c_row70_col4\" class=\"data row70 col4\" >98</td>\n",
-       "      <td id=\"T_c0e9c_row70_col5\" class=\"data row70 col5\" >90</td>\n",
-       "      <td id=\"T_c0e9c_row70_col6\" class=\"data row70 col6\" >8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row71\" class=\"row_heading level0 row71\" >airoboros-65b</th>\n",
-       "      <td id=\"T_c0e9c_row71_col0\" class=\"data row71 col0\" >1512</td>\n",
-       "      <td id=\"T_c0e9c_row71_col1\" class=\"data row71 col1\" >9.388950</td>\n",
-       "      <td id=\"T_c0e9c_row71_col2\" class=\"data row71 col2\" >13.996237</td>\n",
-       "      <td id=\"T_c0e9c_row71_col3\" class=\"data row71 col3\" >4.607287</td>\n",
-       "      <td id=\"T_c0e9c_row71_col4\" class=\"data row71 col4\" >62</td>\n",
-       "      <td id=\"T_c0e9c_row71_col5\" class=\"data row71 col5\" >65</td>\n",
-       "      <td id=\"T_c0e9c_row71_col6\" class=\"data row71 col6\" >-3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row72\" class=\"row_heading level0 row72\" >cohere</th>\n",
-       "      <td id=\"T_c0e9c_row72_col0\" class=\"data row72 col0\" >1983</td>\n",
-       "      <td id=\"T_c0e9c_row72_col1\" class=\"data row72 col1\" >12.901455</td>\n",
-       "      <td id=\"T_c0e9c_row72_col2\" class=\"data row72 col2\" >13.751717</td>\n",
-       "      <td id=\"T_c0e9c_row72_col3\" class=\"data row72 col3\" >0.850262</td>\n",
-       "      <td id=\"T_c0e9c_row72_col4\" class=\"data row72 col4\" >41</td>\n",
-       "      <td id=\"T_c0e9c_row72_col5\" class=\"data row72 col5\" >67</td>\n",
-       "      <td id=\"T_c0e9c_row72_col6\" class=\"data row72 col6\" >-26</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row73\" class=\"row_heading level0 row73\" >vicuna-13b-v1.3</th>\n",
-       "      <td id=\"T_c0e9c_row73_col0\" class=\"data row73 col0\" >1132</td>\n",
-       "      <td id=\"T_c0e9c_row73_col1\" class=\"data row73 col1\" >7.137240</td>\n",
-       "      <td id=\"T_c0e9c_row73_col2\" class=\"data row73 col2\" >12.307993</td>\n",
-       "      <td id=\"T_c0e9c_row73_col3\" class=\"data row73 col3\" >5.170753</td>\n",
-       "      <td id=\"T_c0e9c_row73_col4\" class=\"data row73 col4\" >85</td>\n",
-       "      <td id=\"T_c0e9c_row73_col5\" class=\"data row73 col5\" >73</td>\n",
-       "      <td id=\"T_c0e9c_row73_col6\" class=\"data row73 col6\" >12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row74\" class=\"row_heading level0 row74\" >xwinlm-7b-v0.1</th>\n",
-       "      <td id=\"T_c0e9c_row74_col0\" class=\"data row74 col0\" >1894</td>\n",
-       "      <td id=\"T_c0e9c_row74_col1\" class=\"data row74 col1\" >11.245652</td>\n",
-       "      <td id=\"T_c0e9c_row74_col2\" class=\"data row74 col2\" >12.974901</td>\n",
-       "      <td id=\"T_c0e9c_row74_col3\" class=\"data row74 col3\" >1.729250</td>\n",
-       "      <td id=\"T_c0e9c_row74_col4\" class=\"data row74 col4\" >49</td>\n",
-       "      <td id=\"T_c0e9c_row74_col5\" class=\"data row74 col5\" >71</td>\n",
-       "      <td id=\"T_c0e9c_row74_col6\" class=\"data row74 col6\" >-22</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row75\" class=\"row_heading level0 row75\" >airoboros-33b</th>\n",
-       "      <td id=\"T_c0e9c_row75_col0\" class=\"data row75 col0\" >1514</td>\n",
-       "      <td id=\"T_c0e9c_row75_col1\" class=\"data row75 col1\" >9.053160</td>\n",
-       "      <td id=\"T_c0e9c_row75_col2\" class=\"data row75 col2\" >13.481911</td>\n",
-       "      <td id=\"T_c0e9c_row75_col3\" class=\"data row75 col3\" >4.428750</td>\n",
-       "      <td id=\"T_c0e9c_row75_col4\" class=\"data row75 col4\" >65</td>\n",
-       "      <td id=\"T_c0e9c_row75_col5\" class=\"data row75 col5\" >69</td>\n",
-       "      <td id=\"T_c0e9c_row75_col6\" class=\"data row75 col6\" >-4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row76\" class=\"row_heading level0 row76\" >platolm-7b</th>\n",
-       "      <td id=\"T_c0e9c_row76_col0\" class=\"data row76 col0\" >1344</td>\n",
-       "      <td id=\"T_c0e9c_row76_col1\" class=\"data row76 col1\" >6.320828</td>\n",
-       "      <td id=\"T_c0e9c_row76_col2\" class=\"data row76 col2\" >10.160933</td>\n",
-       "      <td id=\"T_c0e9c_row76_col3\" class=\"data row76 col3\" >3.840105</td>\n",
-       "      <td id=\"T_c0e9c_row76_col4\" class=\"data row76 col4\" >91</td>\n",
-       "      <td id=\"T_c0e9c_row76_col5\" class=\"data row76 col5\" >96</td>\n",
-       "      <td id=\"T_c0e9c_row76_col6\" class=\"data row76 col6\" >-5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row77\" class=\"row_heading level0 row77\" >vicuna-13b-v1.5</th>\n",
-       "      <td id=\"T_c0e9c_row77_col0\" class=\"data row77 col0\" >1061</td>\n",
-       "      <td id=\"T_c0e9c_row77_col1\" class=\"data row77 col1\" >6.722122</td>\n",
-       "      <td id=\"T_c0e9c_row77_col2\" class=\"data row77 col2\" >11.807463</td>\n",
-       "      <td id=\"T_c0e9c_row77_col3\" class=\"data row77 col3\" >5.085341</td>\n",
-       "      <td id=\"T_c0e9c_row77_col4\" class=\"data row77 col4\" >88</td>\n",
-       "      <td id=\"T_c0e9c_row77_col5\" class=\"data row77 col5\" >78</td>\n",
-       "      <td id=\"T_c0e9c_row77_col6\" class=\"data row77 col6\" >10</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row78\" class=\"row_heading level0 row78\" >gemma-7b-it</th>\n",
-       "      <td id=\"T_c0e9c_row78_col0\" class=\"data row78 col0\" >1115</td>\n",
-       "      <td id=\"T_c0e9c_row78_col1\" class=\"data row78 col1\" >6.937294</td>\n",
-       "      <td id=\"T_c0e9c_row78_col2\" class=\"data row78 col2\" >12.018539</td>\n",
-       "      <td id=\"T_c0e9c_row78_col3\" class=\"data row78 col3\" >5.081245</td>\n",
-       "      <td id=\"T_c0e9c_row78_col4\" class=\"data row78 col4\" >86</td>\n",
-       "      <td id=\"T_c0e9c_row78_col5\" class=\"data row78 col5\" >77</td>\n",
-       "      <td id=\"T_c0e9c_row78_col6\" class=\"data row78 col6\" >9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row79\" class=\"row_heading level0 row79\" >openchat-v2-13b</th>\n",
-       "      <td id=\"T_c0e9c_row79_col0\" class=\"data row79 col0\" >1564</td>\n",
-       "      <td id=\"T_c0e9c_row79_col1\" class=\"data row79 col1\" >8.435076</td>\n",
-       "      <td id=\"T_c0e9c_row79_col2\" class=\"data row79 col2\" >12.232876</td>\n",
-       "      <td id=\"T_c0e9c_row79_col3\" class=\"data row79 col3\" >3.797800</td>\n",
-       "      <td id=\"T_c0e9c_row79_col4\" class=\"data row79 col4\" >69</td>\n",
-       "      <td id=\"T_c0e9c_row79_col5\" class=\"data row79 col5\" >74</td>\n",
-       "      <td id=\"T_c0e9c_row79_col6\" class=\"data row79 col6\" >-5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row80\" class=\"row_heading level0 row80\" >zephyr-7b-alpha</th>\n",
-       "      <td id=\"T_c0e9c_row80_col0\" class=\"data row80 col0\" >1302</td>\n",
-       "      <td id=\"T_c0e9c_row80_col1\" class=\"data row80 col1\" >8.352664</td>\n",
-       "      <td id=\"T_c0e9c_row80_col2\" class=\"data row80 col2\" >13.642872</td>\n",
-       "      <td id=\"T_c0e9c_row80_col3\" class=\"data row80 col3\" >5.290208</td>\n",
-       "      <td id=\"T_c0e9c_row80_col4\" class=\"data row80 col4\" >70</td>\n",
-       "      <td id=\"T_c0e9c_row80_col5\" class=\"data row80 col5\" >68</td>\n",
-       "      <td id=\"T_c0e9c_row80_col6\" class=\"data row80 col6\" >2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row81\" class=\"row_heading level0 row81\" >openbuddy-llama-30b-v7.1</th>\n",
-       "      <td id=\"T_c0e9c_row81_col0\" class=\"data row81 col0\" >968</td>\n",
-       "      <td id=\"T_c0e9c_row81_col1\" class=\"data row81 col1\" >6.130015</td>\n",
-       "      <td id=\"T_c0e9c_row81_col2\" class=\"data row81 col2\" >10.994608</td>\n",
-       "      <td id=\"T_c0e9c_row81_col3\" class=\"data row81 col3\" >4.864593</td>\n",
-       "      <td id=\"T_c0e9c_row81_col4\" class=\"data row81 col4\" >94</td>\n",
-       "      <td id=\"T_c0e9c_row81_col5\" class=\"data row81 col5\" >85</td>\n",
-       "      <td id=\"T_c0e9c_row81_col6\" class=\"data row81 col6\" >9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row82\" class=\"row_heading level0 row82\" >ultralm-13b-best-of-16</th>\n",
-       "      <td id=\"T_c0e9c_row82_col0\" class=\"data row82 col0\" >1980</td>\n",
-       "      <td id=\"T_c0e9c_row82_col1\" class=\"data row82 col1\" >11.307315</td>\n",
-       "      <td id=\"T_c0e9c_row82_col2\" class=\"data row82 col2\" >12.086284</td>\n",
-       "      <td id=\"T_c0e9c_row82_col3\" class=\"data row82 col3\" >0.778969</td>\n",
-       "      <td id=\"T_c0e9c_row82_col4\" class=\"data row82 col4\" >48</td>\n",
-       "      <td id=\"T_c0e9c_row82_col5\" class=\"data row82 col5\" >76</td>\n",
-       "      <td id=\"T_c0e9c_row82_col6\" class=\"data row82 col6\" >-28</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row83\" class=\"row_heading level0 row83\" >oasst-sft-llama-33b</th>\n",
-       "      <td id=\"T_c0e9c_row83_col0\" class=\"data row83 col0\" >748</td>\n",
-       "      <td id=\"T_c0e9c_row83_col1\" class=\"data row83 col1\" >4.770391</td>\n",
-       "      <td id=\"T_c0e9c_row83_col2\" class=\"data row83 col2\" >8.882374</td>\n",
-       "      <td id=\"T_c0e9c_row83_col3\" class=\"data row83 col3\" >4.111983</td>\n",
-       "      <td id=\"T_c0e9c_row83_col4\" class=\"data row83 col4\" >104</td>\n",
-       "      <td id=\"T_c0e9c_row83_col5\" class=\"data row83 col5\" >100</td>\n",
-       "      <td id=\"T_c0e9c_row83_col6\" class=\"data row83 col6\" >4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row84\" class=\"row_heading level0 row84\" >wizardlm-13b</th>\n",
-       "      <td id=\"T_c0e9c_row84_col0\" class=\"data row84 col0\" >985</td>\n",
-       "      <td id=\"T_c0e9c_row84_col1\" class=\"data row84 col1\" >5.878153</td>\n",
-       "      <td id=\"T_c0e9c_row84_col2\" class=\"data row84 col2\" >10.505375</td>\n",
-       "      <td id=\"T_c0e9c_row84_col3\" class=\"data row84 col3\" >4.627223</td>\n",
-       "      <td id=\"T_c0e9c_row84_col4\" class=\"data row84 col4\" >96</td>\n",
-       "      <td id=\"T_c0e9c_row84_col5\" class=\"data row84 col5\" >89</td>\n",
-       "      <td id=\"T_c0e9c_row84_col6\" class=\"data row84 col6\" >7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row85\" class=\"row_heading level0 row85\" >nous-hermes-13b</th>\n",
-       "      <td id=\"T_c0e9c_row85_col0\" class=\"data row85 col0\" >844</td>\n",
-       "      <td id=\"T_c0e9c_row85_col1\" class=\"data row85 col1\" >5.411879</td>\n",
-       "      <td id=\"T_c0e9c_row85_col2\" class=\"data row85 col2\" >9.931736</td>\n",
-       "      <td id=\"T_c0e9c_row85_col3\" class=\"data row85 col3\" >4.519857</td>\n",
-       "      <td id=\"T_c0e9c_row85_col4\" class=\"data row85 col4\" >99</td>\n",
-       "      <td id=\"T_c0e9c_row85_col5\" class=\"data row85 col5\" >98</td>\n",
-       "      <td id=\"T_c0e9c_row85_col6\" class=\"data row85 col6\" >1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row86\" class=\"row_heading level0 row86\" >vicuna-13b</th>\n",
-       "      <td id=\"T_c0e9c_row86_col0\" class=\"data row86 col0\" >1037</td>\n",
-       "      <td id=\"T_c0e9c_row86_col1\" class=\"data row86 col1\" >5.831103</td>\n",
-       "      <td id=\"T_c0e9c_row86_col2\" class=\"data row86 col2\" >10.301157</td>\n",
-       "      <td id=\"T_c0e9c_row86_col3\" class=\"data row86 col3\" >4.470054</td>\n",
-       "      <td id=\"T_c0e9c_row86_col4\" class=\"data row86 col4\" >97</td>\n",
-       "      <td id=\"T_c0e9c_row86_col5\" class=\"data row86 col5\" >94</td>\n",
-       "      <td id=\"T_c0e9c_row86_col6\" class=\"data row86 col6\" >3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row87\" class=\"row_heading level0 row87\" >tulu-2-dpo-7b</th>\n",
-       "      <td id=\"T_c0e9c_row87_col0\" class=\"data row87 col0\" >1663</td>\n",
-       "      <td id=\"T_c0e9c_row87_col1\" class=\"data row87 col1\" >8.197515</td>\n",
-       "      <td id=\"T_c0e9c_row87_col2\" class=\"data row87 col2\" >11.213437</td>\n",
-       "      <td id=\"T_c0e9c_row87_col3\" class=\"data row87 col3\" >3.015921</td>\n",
-       "      <td id=\"T_c0e9c_row87_col4\" class=\"data row87 col4\" >71</td>\n",
-       "      <td id=\"T_c0e9c_row87_col5\" class=\"data row87 col5\" >82</td>\n",
-       "      <td id=\"T_c0e9c_row87_col6\" class=\"data row87 col6\" >-11</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row88\" class=\"row_heading level0 row88\" >openbuddy-llama2-13b-v11.1</th>\n",
-       "      <td id=\"T_c0e9c_row88_col0\" class=\"data row88 col0\" >1057</td>\n",
-       "      <td id=\"T_c0e9c_row88_col1\" class=\"data row88 col1\" >6.174716</td>\n",
-       "      <td id=\"T_c0e9c_row88_col2\" class=\"data row88 col2\" >10.856472</td>\n",
-       "      <td id=\"T_c0e9c_row88_col3\" class=\"data row88 col3\" >4.681755</td>\n",
-       "      <td id=\"T_c0e9c_row88_col4\" class=\"data row88 col4\" >93</td>\n",
-       "      <td id=\"T_c0e9c_row88_col5\" class=\"data row88 col5\" >86</td>\n",
-       "      <td id=\"T_c0e9c_row88_col6\" class=\"data row88 col6\" >7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row89\" class=\"row_heading level0 row89\" >ultralm-13b-v2.0</th>\n",
-       "      <td id=\"T_c0e9c_row89_col0\" class=\"data row89 col0\" >1399</td>\n",
-       "      <td id=\"T_c0e9c_row89_col1\" class=\"data row89 col1\" >7.504623</td>\n",
-       "      <td id=\"T_c0e9c_row89_col2\" class=\"data row89 col2\" >11.794791</td>\n",
-       "      <td id=\"T_c0e9c_row89_col3\" class=\"data row89 col3\" >4.290168</td>\n",
-       "      <td id=\"T_c0e9c_row89_col4\" class=\"data row89 col4\" >78</td>\n",
-       "      <td id=\"T_c0e9c_row89_col5\" class=\"data row89 col5\" >79</td>\n",
-       "      <td id=\"T_c0e9c_row89_col6\" class=\"data row89 col6\" >-1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row90\" class=\"row_heading level0 row90\" >text_davinci_001</th>\n",
-       "      <td id=\"T_c0e9c_row90_col0\" class=\"data row90 col0\" >296</td>\n",
-       "      <td id=\"T_c0e9c_row90_col1\" class=\"data row90 col1\" >2.764005</td>\n",
-       "      <td id=\"T_c0e9c_row90_col2\" class=\"data row90 col2\" >5.366913</td>\n",
-       "      <td id=\"T_c0e9c_row90_col3\" class=\"data row90 col3\" >2.602908</td>\n",
-       "      <td id=\"T_c0e9c_row90_col4\" class=\"data row90 col4\" >120</td>\n",
-       "      <td id=\"T_c0e9c_row90_col5\" class=\"data row90 col5\" >118</td>\n",
-       "      <td id=\"T_c0e9c_row90_col6\" class=\"data row90 col6\" >2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row91\" class=\"row_heading level0 row91\" >openbuddy-falcon-40b-v9</th>\n",
-       "      <td id=\"T_c0e9c_row91_col0\" class=\"data row91 col0\" >1089</td>\n",
-       "      <td id=\"T_c0e9c_row91_col1\" class=\"data row91 col1\" >5.955743</td>\n",
-       "      <td id=\"T_c0e9c_row91_col2\" class=\"data row91 col2\" >10.388464</td>\n",
-       "      <td id=\"T_c0e9c_row91_col3\" class=\"data row91 col3\" >4.432722</td>\n",
-       "      <td id=\"T_c0e9c_row91_col4\" class=\"data row91 col4\" >95</td>\n",
-       "      <td id=\"T_c0e9c_row91_col5\" class=\"data row91 col5\" >92</td>\n",
-       "      <td id=\"T_c0e9c_row91_col6\" class=\"data row91 col6\" >3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row92\" class=\"row_heading level0 row92\" >openchat-13b</th>\n",
-       "      <td id=\"T_c0e9c_row92_col0\" class=\"data row92 col0\" >1632</td>\n",
-       "      <td id=\"T_c0e9c_row92_col1\" class=\"data row92 col1\" >8.022386</td>\n",
-       "      <td id=\"T_c0e9c_row92_col2\" class=\"data row92 col2\" >11.186416</td>\n",
-       "      <td id=\"T_c0e9c_row92_col3\" class=\"data row92 col3\" >3.164030</td>\n",
-       "      <td id=\"T_c0e9c_row92_col4\" class=\"data row92 col4\" >73</td>\n",
-       "      <td id=\"T_c0e9c_row92_col5\" class=\"data row92 col5\" >83</td>\n",
-       "      <td id=\"T_c0e9c_row92_col6\" class=\"data row92 col6\" >-10</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row93\" class=\"row_heading level0 row93\" >llama-2-13b-chat-hf</th>\n",
-       "      <td id=\"T_c0e9c_row93_col0\" class=\"data row93 col0\" >1513</td>\n",
-       "      <td id=\"T_c0e9c_row93_col1\" class=\"data row93 col1\" >7.702310</td>\n",
-       "      <td id=\"T_c0e9c_row93_col2\" class=\"data row93 col2\" >11.476089</td>\n",
-       "      <td id=\"T_c0e9c_row93_col3\" class=\"data row93 col3\" >3.773779</td>\n",
-       "      <td id=\"T_c0e9c_row93_col4\" class=\"data row93 col4\" >76</td>\n",
-       "      <td id=\"T_c0e9c_row93_col5\" class=\"data row93 col5\" >80</td>\n",
-       "      <td id=\"T_c0e9c_row93_col6\" class=\"data row93 col6\" >-4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row94\" class=\"row_heading level0 row94\" >guanaco-65b</th>\n",
-       "      <td id=\"T_c0e9c_row94_col0\" class=\"data row94 col0\" >1249</td>\n",
-       "      <td id=\"T_c0e9c_row94_col1\" class=\"data row94 col1\" >6.858495</td>\n",
-       "      <td id=\"T_c0e9c_row94_col2\" class=\"data row94 col2\" >11.412787</td>\n",
-       "      <td id=\"T_c0e9c_row94_col3\" class=\"data row94 col3\" >4.554293</td>\n",
-       "      <td id=\"T_c0e9c_row94_col4\" class=\"data row94 col4\" >87</td>\n",
-       "      <td id=\"T_c0e9c_row94_col5\" class=\"data row94 col5\" >81</td>\n",
-       "      <td id=\"T_c0e9c_row94_col6\" class=\"data row94 col6\" >6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row95\" class=\"row_heading level0 row95\" >opencoderplus-15b</th>\n",
-       "      <td id=\"T_c0e9c_row95_col0\" class=\"data row95 col0\" >1628</td>\n",
-       "      <td id=\"T_c0e9c_row95_col1\" class=\"data row95 col1\" >7.406222</td>\n",
-       "      <td id=\"T_c0e9c_row95_col2\" class=\"data row95 col2\" >10.352214</td>\n",
-       "      <td id=\"T_c0e9c_row95_col3\" class=\"data row95 col3\" >2.945992</td>\n",
-       "      <td id=\"T_c0e9c_row95_col4\" class=\"data row95 col4\" >83</td>\n",
-       "      <td id=\"T_c0e9c_row95_col5\" class=\"data row95 col5\" >93</td>\n",
-       "      <td id=\"T_c0e9c_row95_col6\" class=\"data row95 col6\" >-10</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row96\" class=\"row_heading level0 row96\" >oasst-rlhf-llama-33b</th>\n",
-       "      <td id=\"T_c0e9c_row96_col0\" class=\"data row96 col0\" >1079</td>\n",
-       "      <td id=\"T_c0e9c_row96_col1\" class=\"data row96 col1\" >6.296435</td>\n",
-       "      <td id=\"T_c0e9c_row96_col2\" class=\"data row96 col2\" >11.010603</td>\n",
-       "      <td id=\"T_c0e9c_row96_col3\" class=\"data row96 col3\" >4.714168</td>\n",
-       "      <td id=\"T_c0e9c_row96_col4\" class=\"data row96 col4\" >92</td>\n",
-       "      <td id=\"T_c0e9c_row96_col5\" class=\"data row96 col5\" >84</td>\n",
-       "      <td id=\"T_c0e9c_row96_col6\" class=\"data row96 col6\" >8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row97\" class=\"row_heading level0 row97\" >openchat8192-13b</th>\n",
-       "      <td id=\"T_c0e9c_row97_col0\" class=\"data row97 col0\" >1664</td>\n",
-       "      <td id=\"T_c0e9c_row97_col1\" class=\"data row97 col1\" >7.472767</td>\n",
-       "      <td id=\"T_c0e9c_row97_col2\" class=\"data row97 col2\" >10.215584</td>\n",
-       "      <td id=\"T_c0e9c_row97_col3\" class=\"data row97 col3\" >2.742818</td>\n",
-       "      <td id=\"T_c0e9c_row97_col4\" class=\"data row97 col4\" >80</td>\n",
-       "      <td id=\"T_c0e9c_row97_col5\" class=\"data row97 col5\" >95</td>\n",
-       "      <td id=\"T_c0e9c_row97_col6\" class=\"data row97 col6\" >-15</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row98\" class=\"row_heading level0 row98\" >phi-2-dpo</th>\n",
-       "      <td id=\"T_c0e9c_row98_col0\" class=\"data row98 col0\" >1687</td>\n",
-       "      <td id=\"T_c0e9c_row98_col1\" class=\"data row98 col1\" >7.757096</td>\n",
-       "      <td id=\"T_c0e9c_row98_col2\" class=\"data row98 col2\" >10.448610</td>\n",
-       "      <td id=\"T_c0e9c_row98_col3\" class=\"data row98 col3\" >2.691514</td>\n",
-       "      <td id=\"T_c0e9c_row98_col4\" class=\"data row98 col4\" >75</td>\n",
-       "      <td id=\"T_c0e9c_row98_col5\" class=\"data row98 col5\" >91</td>\n",
-       "      <td id=\"T_c0e9c_row98_col6\" class=\"data row98 col6\" >-16</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row99\" class=\"row_heading level0 row99\" >minichat-1.5-3b</th>\n",
-       "      <td id=\"T_c0e9c_row99_col0\" class=\"data row99 col0\" >1545</td>\n",
-       "      <td id=\"T_c0e9c_row99_col1\" class=\"data row99 col1\" >6.553443</td>\n",
-       "      <td id=\"T_c0e9c_row99_col2\" class=\"data row99 col2\" >9.602479</td>\n",
-       "      <td id=\"T_c0e9c_row99_col3\" class=\"data row99 col3\" >3.049036</td>\n",
-       "      <td id=\"T_c0e9c_row99_col4\" class=\"data row99 col4\" >90</td>\n",
-       "      <td id=\"T_c0e9c_row99_col5\" class=\"data row99 col5\" >99</td>\n",
-       "      <td id=\"T_c0e9c_row99_col6\" class=\"data row99 col6\" >-9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row100\" class=\"row_heading level0 row100\" >vicuna-7b-v1.5</th>\n",
-       "      <td id=\"T_c0e9c_row100_col0\" class=\"data row100 col0\" >1083</td>\n",
-       "      <td id=\"T_c0e9c_row100_col1\" class=\"data row100 col1\" >4.797494</td>\n",
-       "      <td id=\"T_c0e9c_row100_col2\" class=\"data row100 col2\" >8.380940</td>\n",
-       "      <td id=\"T_c0e9c_row100_col3\" class=\"data row100 col3\" >3.583446</td>\n",
-       "      <td id=\"T_c0e9c_row100_col4\" class=\"data row100 col4\" >103</td>\n",
-       "      <td id=\"T_c0e9c_row100_col5\" class=\"data row100 col5\" >102</td>\n",
-       "      <td id=\"T_c0e9c_row100_col6\" class=\"data row100 col6\" >1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row101\" class=\"row_heading level0 row101\" >llama-2-chat-7b-evol70k-neft</th>\n",
-       "      <td id=\"T_c0e9c_row101_col0\" class=\"data row101 col0\" >1612</td>\n",
-       "      <td id=\"T_c0e9c_row101_col1\" class=\"data row101 col1\" >7.602384</td>\n",
-       "      <td id=\"T_c0e9c_row101_col2\" class=\"data row101 col2\" >10.728139</td>\n",
-       "      <td id=\"T_c0e9c_row101_col3\" class=\"data row101 col3\" >3.125755</td>\n",
-       "      <td id=\"T_c0e9c_row101_col4\" class=\"data row101 col4\" >77</td>\n",
-       "      <td id=\"T_c0e9c_row101_col5\" class=\"data row101 col5\" >87</td>\n",
-       "      <td id=\"T_c0e9c_row101_col6\" class=\"data row101 col6\" >-10</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row102\" class=\"row_heading level0 row102\" >recycled-wizardlm-7b-v2.0</th>\n",
-       "      <td id=\"T_c0e9c_row102_col0\" class=\"data row102 col0\" >1583</td>\n",
-       "      <td id=\"T_c0e9c_row102_col1\" class=\"data row102 col1\" >7.337129</td>\n",
-       "      <td id=\"T_c0e9c_row102_col2\" class=\"data row102 col2\" >10.528500</td>\n",
-       "      <td id=\"T_c0e9c_row102_col3\" class=\"data row102 col3\" >3.191370</td>\n",
-       "      <td id=\"T_c0e9c_row102_col4\" class=\"data row102 col4\" >84</td>\n",
-       "      <td id=\"T_c0e9c_row102_col5\" class=\"data row102 col5\" >88</td>\n",
-       "      <td id=\"T_c0e9c_row102_col6\" class=\"data row102 col6\" >-4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row103\" class=\"row_heading level0 row103\" >vicuna-7b-v1.3</th>\n",
-       "      <td id=\"T_c0e9c_row103_col0\" class=\"data row103 col0\" >1110</td>\n",
-       "      <td id=\"T_c0e9c_row103_col1\" class=\"data row103 col1\" >4.642512</td>\n",
-       "      <td id=\"T_c0e9c_row103_col2\" class=\"data row103 col2\" >8.053655</td>\n",
-       "      <td id=\"T_c0e9c_row103_col3\" class=\"data row103 col3\" >3.411143</td>\n",
-       "      <td id=\"T_c0e9c_row103_col4\" class=\"data row103 col4\" >105</td>\n",
-       "      <td id=\"T_c0e9c_row103_col5\" class=\"data row103 col5\" >105</td>\n",
-       "      <td id=\"T_c0e9c_row103_col6\" class=\"data row103 col6\" >0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row104\" class=\"row_heading level0 row104\" >alpaca-farm-ppo-sim-gpt4-20k</th>\n",
-       "      <td id=\"T_c0e9c_row104_col0\" class=\"data row104 col0\" >511</td>\n",
-       "      <td id=\"T_c0e9c_row104_col1\" class=\"data row104 col1\" >3.450342</td>\n",
-       "      <td id=\"T_c0e9c_row104_col2\" class=\"data row104 col2\" >6.596308</td>\n",
-       "      <td id=\"T_c0e9c_row104_col3\" class=\"data row104 col3\" >3.145966</td>\n",
-       "      <td id=\"T_c0e9c_row104_col4\" class=\"data row104 col4\" >113</td>\n",
-       "      <td id=\"T_c0e9c_row104_col5\" class=\"data row104 col5\" >111</td>\n",
-       "      <td id=\"T_c0e9c_row104_col6\" class=\"data row104 col6\" >2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row105\" class=\"row_heading level0 row105\" >ultralm-13b</th>\n",
-       "      <td id=\"T_c0e9c_row105_col0\" class=\"data row105 col0\" >1087</td>\n",
-       "      <td id=\"T_c0e9c_row105_col1\" class=\"data row105 col1\" >5.074590</td>\n",
-       "      <td id=\"T_c0e9c_row105_col2\" class=\"data row105 col2\" >8.856011</td>\n",
-       "      <td id=\"T_c0e9c_row105_col3\" class=\"data row105 col3\" >3.781421</td>\n",
-       "      <td id=\"T_c0e9c_row105_col4\" class=\"data row105 col4\" >100</td>\n",
-       "      <td id=\"T_c0e9c_row105_col5\" class=\"data row105 col5\" >101</td>\n",
-       "      <td id=\"T_c0e9c_row105_col6\" class=\"data row105 col6\" >-1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row106\" class=\"row_heading level0 row106\" >baize-v2-13b</th>\n",
-       "      <td id=\"T_c0e9c_row106_col0\" class=\"data row106 col0\" >930</td>\n",
-       "      <td id=\"T_c0e9c_row106_col1\" class=\"data row106 col1\" >4.590545</td>\n",
-       "      <td id=\"T_c0e9c_row106_col2\" class=\"data row106 col2\" >8.296129</td>\n",
-       "      <td id=\"T_c0e9c_row106_col3\" class=\"data row106 col3\" >3.705584</td>\n",
-       "      <td id=\"T_c0e9c_row106_col4\" class=\"data row106 col4\" >106</td>\n",
-       "      <td id=\"T_c0e9c_row106_col5\" class=\"data row106 col5\" >103</td>\n",
-       "      <td id=\"T_c0e9c_row106_col6\" class=\"data row106 col6\" >3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row107\" class=\"row_heading level0 row107\" >recycled-wizardlm-7b-v1.0</th>\n",
-       "      <td id=\"T_c0e9c_row107_col0\" class=\"data row107 col0\" >1494</td>\n",
-       "      <td id=\"T_c0e9c_row107_col1\" class=\"data row107 col1\" >6.632750</td>\n",
-       "      <td id=\"T_c0e9c_row107_col2\" class=\"data row107 col2\" >9.977369</td>\n",
-       "      <td id=\"T_c0e9c_row107_col3\" class=\"data row107 col3\" >3.344619</td>\n",
-       "      <td id=\"T_c0e9c_row107_col4\" class=\"data row107 col4\" >89</td>\n",
-       "      <td id=\"T_c0e9c_row107_col5\" class=\"data row107 col5\" >97</td>\n",
-       "      <td id=\"T_c0e9c_row107_col6\" class=\"data row107 col6\" >-8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row108\" class=\"row_heading level0 row108\" >alpaca-7b_verbose</th>\n",
-       "      <td id=\"T_c0e9c_row108_col0\" class=\"data row108 col0\" >537</td>\n",
-       "      <td id=\"T_c0e9c_row108_col1\" class=\"data row108 col1\" >2.933102</td>\n",
-       "      <td id=\"T_c0e9c_row108_col2\" class=\"data row108 col2\" >5.594285</td>\n",
-       "      <td id=\"T_c0e9c_row108_col3\" class=\"data row108 col3\" >2.661184</td>\n",
-       "      <td id=\"T_c0e9c_row108_col4\" class=\"data row108 col4\" >118</td>\n",
-       "      <td id=\"T_c0e9c_row108_col5\" class=\"data row108 col5\" >116</td>\n",
-       "      <td id=\"T_c0e9c_row108_col6\" class=\"data row108 col6\" >2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row109\" class=\"row_heading level0 row109\" >alpaca-farm-ppo-human</th>\n",
-       "      <td id=\"T_c0e9c_row109_col0\" class=\"data row109 col0\" >803</td>\n",
-       "      <td id=\"T_c0e9c_row109_col1\" class=\"data row109 col1\" >4.100427</td>\n",
-       "      <td id=\"T_c0e9c_row109_col2\" class=\"data row109 col2\" >7.574137</td>\n",
-       "      <td id=\"T_c0e9c_row109_col3\" class=\"data row109 col3\" >3.473710</td>\n",
-       "      <td id=\"T_c0e9c_row109_col4\" class=\"data row109 col4\" >108</td>\n",
-       "      <td id=\"T_c0e9c_row109_col5\" class=\"data row109 col5\" >106</td>\n",
-       "      <td id=\"T_c0e9c_row109_col6\" class=\"data row109 col6\" >2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row110\" class=\"row_heading level0 row110\" >vicuna-7b</th>\n",
-       "      <td id=\"T_c0e9c_row110_col0\" class=\"data row110 col0\" >1044</td>\n",
-       "      <td id=\"T_c0e9c_row110_col1\" class=\"data row110 col1\" >4.162611</td>\n",
-       "      <td id=\"T_c0e9c_row110_col2\" class=\"data row110 col2\" >7.341539</td>\n",
-       "      <td id=\"T_c0e9c_row110_col3\" class=\"data row110 col3\" >3.178928</td>\n",
-       "      <td id=\"T_c0e9c_row110_col4\" class=\"data row110 col4\" >107</td>\n",
-       "      <td id=\"T_c0e9c_row110_col5\" class=\"data row110 col5\" >108</td>\n",
-       "      <td id=\"T_c0e9c_row110_col6\" class=\"data row110 col6\" >-1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row111\" class=\"row_heading level0 row111\" >alpaca-7b</th>\n",
-       "      <td id=\"T_c0e9c_row111_col0\" class=\"data row111 col0\" >396</td>\n",
-       "      <td id=\"T_c0e9c_row111_col1\" class=\"data row111 col1\" >2.591451</td>\n",
-       "      <td id=\"T_c0e9c_row111_col2\" class=\"data row111 col2\" >4.999603</td>\n",
-       "      <td id=\"T_c0e9c_row111_col3\" class=\"data row111 col3\" >2.408152</td>\n",
-       "      <td id=\"T_c0e9c_row111_col4\" class=\"data row111 col4\" >122</td>\n",
-       "      <td id=\"T_c0e9c_row111_col5\" class=\"data row111 col5\" >119</td>\n",
-       "      <td id=\"T_c0e9c_row111_col6\" class=\"data row111 col6\" >3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row112\" class=\"row_heading level0 row112\" >phi-2-sft</th>\n",
-       "      <td id=\"T_c0e9c_row112_col0\" class=\"data row112 col0\" >1068</td>\n",
-       "      <td id=\"T_c0e9c_row112_col1\" class=\"data row112 col1\" >3.977568</td>\n",
-       "      <td id=\"T_c0e9c_row112_col2\" class=\"data row112 col2\" >6.974659</td>\n",
-       "      <td id=\"T_c0e9c_row112_col3\" class=\"data row112 col3\" >2.997091</td>\n",
-       "      <td id=\"T_c0e9c_row112_col4\" class=\"data row112 col4\" >109</td>\n",
-       "      <td id=\"T_c0e9c_row112_col5\" class=\"data row112 col5\" >110</td>\n",
-       "      <td id=\"T_c0e9c_row112_col6\" class=\"data row112 col6\" >-1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row113\" class=\"row_heading level0 row113\" >minichat-3b</th>\n",
-       "      <td id=\"T_c0e9c_row113_col0\" class=\"data row113 col0\" >868</td>\n",
-       "      <td id=\"T_c0e9c_row113_col1\" class=\"data row113 col1\" >3.007151</td>\n",
-       "      <td id=\"T_c0e9c_row113_col2\" class=\"data row113 col2\" >5.496370</td>\n",
-       "      <td id=\"T_c0e9c_row113_col3\" class=\"data row113 col3\" >2.489219</td>\n",
-       "      <td id=\"T_c0e9c_row113_col4\" class=\"data row113 col4\" >117</td>\n",
-       "      <td id=\"T_c0e9c_row113_col5\" class=\"data row113 col5\" >117</td>\n",
-       "      <td id=\"T_c0e9c_row113_col6\" class=\"data row113 col6\" >0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row114\" class=\"row_heading level0 row114\" >guanaco-33b</th>\n",
-       "      <td id=\"T_c0e9c_row114_col0\" class=\"data row114 col0\" >1311</td>\n",
-       "      <td id=\"T_c0e9c_row114_col1\" class=\"data row114 col1\" >5.002494</td>\n",
-       "      <td id=\"T_c0e9c_row114_col2\" class=\"data row114 col2\" >8.143736</td>\n",
-       "      <td id=\"T_c0e9c_row114_col3\" class=\"data row114 col3\" >3.141242</td>\n",
-       "      <td id=\"T_c0e9c_row114_col4\" class=\"data row114 col4\" >101</td>\n",
-       "      <td id=\"T_c0e9c_row114_col5\" class=\"data row114 col5\" >104</td>\n",
-       "      <td id=\"T_c0e9c_row114_col6\" class=\"data row114 col6\" >-3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row115\" class=\"row_heading level0 row115\" >falcon-40b-instruct</th>\n",
-       "      <td id=\"T_c0e9c_row115_col0\" class=\"data row115 col0\" >662</td>\n",
-       "      <td id=\"T_c0e9c_row115_col1\" class=\"data row115 col1\" >3.342919</td>\n",
-       "      <td id=\"T_c0e9c_row115_col2\" class=\"data row115 col2\" >6.293075</td>\n",
-       "      <td id=\"T_c0e9c_row115_col3\" class=\"data row115 col3\" >2.950156</td>\n",
-       "      <td id=\"T_c0e9c_row115_col4\" class=\"data row115 col4\" >116</td>\n",
-       "      <td id=\"T_c0e9c_row115_col5\" class=\"data row115 col5\" >112</td>\n",
-       "      <td id=\"T_c0e9c_row115_col6\" class=\"data row115 col6\" >4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row116\" class=\"row_heading level0 row116\" >gemma-2b-it</th>\n",
-       "      <td id=\"T_c0e9c_row116_col0\" class=\"data row116 col0\" >1041</td>\n",
-       "      <td id=\"T_c0e9c_row116_col1\" class=\"data row116 col1\" >3.401971</td>\n",
-       "      <td id=\"T_c0e9c_row116_col2\" class=\"data row116 col2\" >6.004253</td>\n",
-       "      <td id=\"T_c0e9c_row116_col3\" class=\"data row116 col3\" >2.602282</td>\n",
-       "      <td id=\"T_c0e9c_row116_col4\" class=\"data row116 col4\" >115</td>\n",
-       "      <td id=\"T_c0e9c_row116_col5\" class=\"data row116 col5\" >114</td>\n",
-       "      <td id=\"T_c0e9c_row116_col6\" class=\"data row116 col6\" >1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row117\" class=\"row_heading level0 row117\" >llama-2-7b-chat-hf</th>\n",
-       "      <td id=\"T_c0e9c_row117_col0\" class=\"data row117 col0\" >1479</td>\n",
-       "      <td id=\"T_c0e9c_row117_col1\" class=\"data row117 col1\" >4.961340</td>\n",
-       "      <td id=\"T_c0e9c_row117_col2\" class=\"data row117 col2\" >7.518212</td>\n",
-       "      <td id=\"T_c0e9c_row117_col3\" class=\"data row117 col3\" >2.556872</td>\n",
-       "      <td id=\"T_c0e9c_row117_col4\" class=\"data row117 col4\" >102</td>\n",
-       "      <td id=\"T_c0e9c_row117_col5\" class=\"data row117 col5\" >107</td>\n",
-       "      <td id=\"T_c0e9c_row117_col6\" class=\"data row117 col6\" >-5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row118\" class=\"row_heading level0 row118\" >openbuddy-falcon-7b-v6</th>\n",
-       "      <td id=\"T_c0e9c_row118_col0\" class=\"data row118 col0\" >1152</td>\n",
-       "      <td id=\"T_c0e9c_row118_col1\" class=\"data row118 col1\" >3.521174</td>\n",
-       "      <td id=\"T_c0e9c_row118_col2\" class=\"data row118 col2\" >6.038229</td>\n",
-       "      <td id=\"T_c0e9c_row118_col3\" class=\"data row118 col3\" >2.517055</td>\n",
-       "      <td id=\"T_c0e9c_row118_col4\" class=\"data row118 col4\" >111</td>\n",
-       "      <td id=\"T_c0e9c_row118_col5\" class=\"data row118 col5\" >113</td>\n",
-       "      <td id=\"T_c0e9c_row118_col6\" class=\"data row118 col6\" >-2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row119\" class=\"row_heading level0 row119\" >alpaca-7b_concise</th>\n",
-       "      <td id=\"T_c0e9c_row119_col0\" class=\"data row119 col0\" >351</td>\n",
-       "      <td id=\"T_c0e9c_row119_col1\" class=\"data row119 col1\" >1.991176</td>\n",
-       "      <td id=\"T_c0e9c_row119_col2\" class=\"data row119 col2\" >3.853242</td>\n",
-       "      <td id=\"T_c0e9c_row119_col3\" class=\"data row119 col3\" >1.862066</td>\n",
-       "      <td id=\"T_c0e9c_row119_col4\" class=\"data row119 col4\" >127</td>\n",
-       "      <td id=\"T_c0e9c_row119_col5\" class=\"data row119 col5\" >126</td>\n",
-       "      <td id=\"T_c0e9c_row119_col6\" class=\"data row119 col6\" >1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row120\" class=\"row_heading level0 row120\" >phi-2</th>\n",
-       "      <td id=\"T_c0e9c_row120_col0\" class=\"data row120 col0\" >626</td>\n",
-       "      <td id=\"T_c0e9c_row120_col1\" class=\"data row120 col1\" >2.350210</td>\n",
-       "      <td id=\"T_c0e9c_row120_col2\" class=\"data row120 col2\" >4.442420</td>\n",
-       "      <td id=\"T_c0e9c_row120_col3\" class=\"data row120 col3\" >2.092211</td>\n",
-       "      <td id=\"T_c0e9c_row120_col4\" class=\"data row120 col4\" >124</td>\n",
-       "      <td id=\"T_c0e9c_row120_col5\" class=\"data row120 col5\" >123</td>\n",
-       "      <td id=\"T_c0e9c_row120_col6\" class=\"data row120 col6\" >1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row121\" class=\"row_heading level0 row121\" >baize-v2-7b</th>\n",
-       "      <td id=\"T_c0e9c_row121_col0\" class=\"data row121 col0\" >1127</td>\n",
-       "      <td id=\"T_c0e9c_row121_col1\" class=\"data row121 col1\" >3.404815</td>\n",
-       "      <td id=\"T_c0e9c_row121_col2\" class=\"data row121 col2\" >5.879578</td>\n",
-       "      <td id=\"T_c0e9c_row121_col3\" class=\"data row121 col3\" >2.474763</td>\n",
-       "      <td id=\"T_c0e9c_row121_col4\" class=\"data row121 col4\" >114</td>\n",
-       "      <td id=\"T_c0e9c_row121_col5\" class=\"data row121 col5\" >115</td>\n",
-       "      <td id=\"T_c0e9c_row121_col6\" class=\"data row121 col6\" >-1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row122\" class=\"row_heading level0 row122\" >chatglm2-6b</th>\n",
-       "      <td id=\"T_c0e9c_row122_col0\" class=\"data row122 col0\" >1027</td>\n",
-       "      <td id=\"T_c0e9c_row122_col1\" class=\"data row122 col1\" >2.762185</td>\n",
-       "      <td id=\"T_c0e9c_row122_col2\" class=\"data row122 col2\" >4.890945</td>\n",
-       "      <td id=\"T_c0e9c_row122_col3\" class=\"data row122 col3\" >2.128760</td>\n",
-       "      <td id=\"T_c0e9c_row122_col4\" class=\"data row122 col4\" >121</td>\n",
-       "      <td id=\"T_c0e9c_row122_col5\" class=\"data row122 col5\" >120</td>\n",
-       "      <td id=\"T_c0e9c_row122_col6\" class=\"data row122 col6\" >1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row123\" class=\"row_heading level0 row123\" >pythia-12b-mix-sft</th>\n",
-       "      <td id=\"T_c0e9c_row123_col0\" class=\"data row123 col0\" >913</td>\n",
-       "      <td id=\"T_c0e9c_row123_col1\" class=\"data row123 col1\" >2.578090</td>\n",
-       "      <td id=\"T_c0e9c_row123_col2\" class=\"data row123 col2\" >4.674240</td>\n",
-       "      <td id=\"T_c0e9c_row123_col3\" class=\"data row123 col3\" >2.096149</td>\n",
-       "      <td id=\"T_c0e9c_row123_col4\" class=\"data row123 col4\" >123</td>\n",
-       "      <td id=\"T_c0e9c_row123_col5\" class=\"data row123 col5\" >121</td>\n",
-       "      <td id=\"T_c0e9c_row123_col6\" class=\"data row123 col6\" >2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row124\" class=\"row_heading level0 row124\" >falcon-7b-instruct</th>\n",
-       "      <td id=\"T_c0e9c_row124_col0\" class=\"data row124 col0\" >478</td>\n",
-       "      <td id=\"T_c0e9c_row124_col1\" class=\"data row124 col1\" >2.146618</td>\n",
-       "      <td id=\"T_c0e9c_row124_col2\" class=\"data row124 col2\" >4.115462</td>\n",
-       "      <td id=\"T_c0e9c_row124_col3\" class=\"data row124 col3\" >1.968845</td>\n",
-       "      <td id=\"T_c0e9c_row124_col4\" class=\"data row124 col4\" >125</td>\n",
-       "      <td id=\"T_c0e9c_row124_col5\" class=\"data row124 col5\" >125</td>\n",
-       "      <td id=\"T_c0e9c_row124_col6\" class=\"data row124 col6\" >0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row125\" class=\"row_heading level0 row125\" >oasst-sft-pythia-12b</th>\n",
-       "      <td id=\"T_c0e9c_row125_col0\" class=\"data row125 col0\" >726</td>\n",
-       "      <td id=\"T_c0e9c_row125_col1\" class=\"data row125 col1\" >1.790114</td>\n",
-       "      <td id=\"T_c0e9c_row125_col2\" class=\"data row125 col2\" >3.343088</td>\n",
-       "      <td id=\"T_c0e9c_row125_col3\" class=\"data row125 col3\" >1.552974</td>\n",
-       "      <td id=\"T_c0e9c_row125_col4\" class=\"data row125 col4\" >128</td>\n",
-       "      <td id=\"T_c0e9c_row125_col5\" class=\"data row125 col5\" >127</td>\n",
-       "      <td id=\"T_c0e9c_row125_col6\" class=\"data row125 col6\" >1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row126\" class=\"row_heading level0 row126\" >guanaco-13b</th>\n",
-       "      <td id=\"T_c0e9c_row126_col0\" class=\"data row126 col0\" >1774</td>\n",
-       "      <td id=\"T_c0e9c_row126_col1\" class=\"data row126 col1\" >3.469597</td>\n",
-       "      <td id=\"T_c0e9c_row126_col2\" class=\"data row126 col2\" >4.400390</td>\n",
-       "      <td id=\"T_c0e9c_row126_col3\" class=\"data row126 col3\" >0.930793</td>\n",
-       "      <td id=\"T_c0e9c_row126_col4\" class=\"data row126 col4\" >112</td>\n",
-       "      <td id=\"T_c0e9c_row126_col5\" class=\"data row126 col5\" >124</td>\n",
-       "      <td id=\"T_c0e9c_row126_col6\" class=\"data row126 col6\" >-12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row127\" class=\"row_heading level0 row127\" >guanaco-7b</th>\n",
-       "      <td id=\"T_c0e9c_row127_col0\" class=\"data row127 col0\" >1364</td>\n",
-       "      <td id=\"T_c0e9c_row127_col1\" class=\"data row127 col1\" >2.880002</td>\n",
-       "      <td id=\"T_c0e9c_row127_col2\" class=\"data row127 col2\" >4.592913</td>\n",
-       "      <td id=\"T_c0e9c_row127_col3\" class=\"data row127 col3\" >1.712911</td>\n",
-       "      <td id=\"T_c0e9c_row127_col4\" class=\"data row127 col4\" >119</td>\n",
-       "      <td id=\"T_c0e9c_row127_col5\" class=\"data row127 col5\" >122</td>\n",
-       "      <td id=\"T_c0e9c_row127_col6\" class=\"data row127 col6\" >-3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_c0e9c_level0_row128\" class=\"row_heading level0 row128\" >baichuan-13b-chat</th>\n",
-       "      <td id=\"T_c0e9c_row128_col0\" class=\"data row128 col0\" >1727</td>\n",
-       "      <td id=\"T_c0e9c_row128_col1\" class=\"data row128 col1\" >1.992146</td>\n",
-       "      <td id=\"T_c0e9c_row128_col2\" class=\"data row128 col2\" >2.612329</td>\n",
-       "      <td id=\"T_c0e9c_row128_col3\" class=\"data row128 col3\" >0.620183</td>\n",
-       "      <td id=\"T_c0e9c_row128_col4\" class=\"data row128 col4\" >126</td>\n",
-       "      <td id=\"T_c0e9c_row128_col5\" class=\"data row128 col5\" >128</td>\n",
-       "      <td id=\"T_c0e9c_row128_col6\" class=\"data row128 col6\" >-2</td>\n",
+       "      <th id=\"T_059fc_level0_row0\" class=\"row_heading level0 row0\" >gpt4_1106_preview_verbose</th>\n",
+       "      <td id=\"T_059fc_row0_col0\" class=\"data row0 col0\" >2402</td>\n",
+       "      <td id=\"T_059fc_row0_col1\" class=\"data row0 col1\" >64.303601</td>\n",
+       "      <td id=\"T_059fc_row0_col2\" class=\"data row0 col2\" >42.502532</td>\n",
+       "      <td id=\"T_059fc_row0_col3\" class=\"data row0 col3\" >-21.801069</td>\n",
+       "      <td id=\"T_059fc_row0_col4\" class=\"data row0 col4\" >0</td>\n",
+       "      <td id=\"T_059fc_row0_col5\" class=\"data row0 col5\" >2</td>\n",
+       "      <td id=\"T_059fc_row0_col6\" class=\"data row0 col6\" >-2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row1\" class=\"row_heading level0 row1\" >gpt4_1106_preview</th>\n",
+       "      <td id=\"T_059fc_row1_col0\" class=\"data row1 col0\" >2049</td>\n",
+       "      <td id=\"T_059fc_row1_col1\" class=\"data row1 col1\" >50.000000</td>\n",
+       "      <td id=\"T_059fc_row1_col2\" class=\"data row1 col2\" >50.000000</td>\n",
+       "      <td id=\"T_059fc_row1_col3\" class=\"data row1 col3\" >0.000000</td>\n",
+       "      <td id=\"T_059fc_row1_col4\" class=\"data row1 col4\" >1</td>\n",
+       "      <td id=\"T_059fc_row1_col5\" class=\"data row1 col5\" >0</td>\n",
+       "      <td id=\"T_059fc_row1_col6\" class=\"data row1 col6\" >1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row2\" class=\"row_heading level0 row2\" >gpt4_1106_preview_concise</th>\n",
+       "      <td id=\"T_059fc_row2_col0\" class=\"data row2 col0\" >1136</td>\n",
+       "      <td id=\"T_059fc_row2_col1\" class=\"data row2 col1\" >22.920194</td>\n",
+       "      <td id=\"T_059fc_row2_col2\" class=\"data row2 col2\" >39.481617</td>\n",
+       "      <td id=\"T_059fc_row2_col3\" class=\"data row2 col3\" >16.561423</td>\n",
+       "      <td id=\"T_059fc_row2_col4\" class=\"data row2 col4\" >14</td>\n",
+       "      <td id=\"T_059fc_row2_col5\" class=\"data row2 col5\" >4</td>\n",
+       "      <td id=\"T_059fc_row2_col6\" class=\"data row2 col6\" >10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row3\" class=\"row_heading level0 row3\" >claude-3-opus-20240229</th>\n",
+       "      <td id=\"T_059fc_row3_col0\" class=\"data row3 col0\" >1388</td>\n",
+       "      <td id=\"T_059fc_row3_col1\" class=\"data row3 col1\" >29.041764</td>\n",
+       "      <td id=\"T_059fc_row3_col2\" class=\"data row3 col2\" >45.857774</td>\n",
+       "      <td id=\"T_059fc_row3_col3\" class=\"data row3 col3\" >16.816010</td>\n",
+       "      <td id=\"T_059fc_row3_col4\" class=\"data row3 col4\" >7</td>\n",
+       "      <td id=\"T_059fc_row3_col5\" class=\"data row3 col5\" >1</td>\n",
+       "      <td id=\"T_059fc_row3_col6\" class=\"data row3 col6\" >6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row4\" class=\"row_heading level0 row4\" >gpt4</th>\n",
+       "      <td id=\"T_059fc_row4_col0\" class=\"data row4 col0\" >1365</td>\n",
+       "      <td id=\"T_059fc_row4_col1\" class=\"data row4 col1\" >23.576789</td>\n",
+       "      <td id=\"T_059fc_row4_col2\" class=\"data row4 col2\" >37.584082</td>\n",
+       "      <td id=\"T_059fc_row4_col3\" class=\"data row4 col3\" >14.007293</td>\n",
+       "      <td id=\"T_059fc_row4_col4\" class=\"data row4 col4\" >12</td>\n",
+       "      <td id=\"T_059fc_row4_col5\" class=\"data row4 col5\" >7</td>\n",
+       "      <td id=\"T_059fc_row4_col6\" class=\"data row4 col6\" >5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row5\" class=\"row_heading level0 row5\" >Qwen1.5-72B-Chat</th>\n",
+       "      <td id=\"T_059fc_row5_col0\" class=\"data row5 col0\" >1549</td>\n",
+       "      <td id=\"T_059fc_row5_col1\" class=\"data row5 col1\" >26.498283</td>\n",
+       "      <td id=\"T_059fc_row5_col2\" class=\"data row5 col2\" >38.743595</td>\n",
+       "      <td id=\"T_059fc_row5_col3\" class=\"data row5 col3\" >12.245311</td>\n",
+       "      <td id=\"T_059fc_row5_col4\" class=\"data row5 col4\" >8</td>\n",
+       "      <td id=\"T_059fc_row5_col5\" class=\"data row5 col5\" >5</td>\n",
+       "      <td id=\"T_059fc_row5_col6\" class=\"data row5 col6\" >3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row6\" class=\"row_heading level0 row6\" >gpt4_0314</th>\n",
+       "      <td id=\"T_059fc_row6_col0\" class=\"data row6 col0\" >1371</td>\n",
+       "      <td id=\"T_059fc_row6_col1\" class=\"data row6 col1\" >22.073259</td>\n",
+       "      <td id=\"T_059fc_row6_col2\" class=\"data row6 col2\" >35.101286</td>\n",
+       "      <td id=\"T_059fc_row6_col3\" class=\"data row6 col3\" >13.028027</td>\n",
+       "      <td id=\"T_059fc_row6_col4\" class=\"data row6 col4\" >15</td>\n",
+       "      <td id=\"T_059fc_row6_col5\" class=\"data row6 col5\" >9</td>\n",
+       "      <td id=\"T_059fc_row6_col6\" class=\"data row6 col6\" >6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row7\" class=\"row_heading level0 row7\" >claude-3-sonnet-20240229</th>\n",
+       "      <td id=\"T_059fc_row7_col0\" class=\"data row7 col0\" >1420</td>\n",
+       "      <td id=\"T_059fc_row7_col1\" class=\"data row7 col1\" >25.556325</td>\n",
+       "      <td id=\"T_059fc_row7_col2\" class=\"data row7 col2\" >39.800482</td>\n",
+       "      <td id=\"T_059fc_row7_col3\" class=\"data row7 col3\" >14.244157</td>\n",
+       "      <td id=\"T_059fc_row7_col4\" class=\"data row7 col4\" >9</td>\n",
+       "      <td id=\"T_059fc_row7_col5\" class=\"data row7 col5\" >3</td>\n",
+       "      <td id=\"T_059fc_row7_col6\" class=\"data row7 col6\" >6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row8\" class=\"row_heading level0 row8\" >gpt4_0613_verbose</th>\n",
+       "      <td id=\"T_059fc_row8_col0\" class=\"data row8 col0\" >1473</td>\n",
+       "      <td id=\"T_059fc_row8_col1\" class=\"data row8 col1\" >23.237360</td>\n",
+       "      <td id=\"T_059fc_row8_col2\" class=\"data row8 col2\" >35.315026</td>\n",
+       "      <td id=\"T_059fc_row8_col3\" class=\"data row8 col3\" >12.077666</td>\n",
+       "      <td id=\"T_059fc_row8_col4\" class=\"data row8 col4\" >13</td>\n",
+       "      <td id=\"T_059fc_row8_col5\" class=\"data row8 col5\" >8</td>\n",
+       "      <td id=\"T_059fc_row8_col6\" class=\"data row8 col6\" >5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row9\" class=\"row_heading level0 row9\" >mistral-large-2402</th>\n",
+       "      <td id=\"T_059fc_row9_col0\" class=\"data row9 col0\" >1362</td>\n",
+       "      <td id=\"T_059fc_row9_col1\" class=\"data row9 col1\" >21.438776</td>\n",
+       "      <td id=\"T_059fc_row9_col2\" class=\"data row9 col2\" >34.217386</td>\n",
+       "      <td id=\"T_059fc_row9_col3\" class=\"data row9 col3\" >12.778610</td>\n",
+       "      <td id=\"T_059fc_row9_col4\" class=\"data row9 col4\" >19</td>\n",
+       "      <td id=\"T_059fc_row9_col5\" class=\"data row9 col5\" >10</td>\n",
+       "      <td id=\"T_059fc_row9_col6\" class=\"data row9 col6\" >9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row10\" class=\"row_heading level0 row10\" >claude-2.1_verbose</th>\n",
+       "      <td id=\"T_059fc_row10_col0\" class=\"data row10 col0\" >1414</td>\n",
+       "      <td id=\"T_059fc_row10_col1\" class=\"data row10 col1\" >24.354071</td>\n",
+       "      <td id=\"T_059fc_row10_col2\" class=\"data row10 col2\" >38.028529</td>\n",
+       "      <td id=\"T_059fc_row10_col3\" class=\"data row10 col3\" >13.674458</td>\n",
+       "      <td id=\"T_059fc_row10_col4\" class=\"data row10 col4\" >11</td>\n",
+       "      <td id=\"T_059fc_row10_col5\" class=\"data row10 col5\" >6</td>\n",
+       "      <td id=\"T_059fc_row10_col6\" class=\"data row10 col6\" >5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row11\" class=\"row_heading level0 row11\" >gpt4_0613</th>\n",
+       "      <td id=\"T_059fc_row11_col0\" class=\"data row11 col0\" >1140</td>\n",
+       "      <td id=\"T_059fc_row11_col1\" class=\"data row11 col1\" >15.755038</td>\n",
+       "      <td id=\"T_059fc_row11_col2\" class=\"data row11 col2\" >27.108937</td>\n",
+       "      <td id=\"T_059fc_row11_col3\" class=\"data row11 col3\" >11.353899</td>\n",
+       "      <td id=\"T_059fc_row11_col4\" class=\"data row11 col4\" >30</td>\n",
+       "      <td id=\"T_059fc_row11_col5\" class=\"data row11 col5\" >20</td>\n",
+       "      <td id=\"T_059fc_row11_col6\" class=\"data row11 col6\" >10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row12\" class=\"row_heading level0 row12\" >Snorkel-Mistral-PairRM-DPO-best-of-16</th>\n",
+       "      <td id=\"T_059fc_row12_col0\" class=\"data row12 col0\" >2616</td>\n",
+       "      <td id=\"T_059fc_row12_col1\" class=\"data row12 col1\" >34.860133</td>\n",
+       "      <td id=\"T_059fc_row12_col2\" class=\"data row12 col2\" >16.971563</td>\n",
+       "      <td id=\"T_059fc_row12_col3\" class=\"data row12 col3\" >-17.888570</td>\n",
+       "      <td id=\"T_059fc_row12_col4\" class=\"data row12 col4\" >2</td>\n",
+       "      <td id=\"T_059fc_row12_col5\" class=\"data row12 col5\" >50</td>\n",
+       "      <td id=\"T_059fc_row12_col6\" class=\"data row12 col6\" >-48</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row13\" class=\"row_heading level0 row13\" >Contextual-KTO-Mistral-PairRM</th>\n",
+       "      <td id=\"T_059fc_row13_col0\" class=\"data row13 col0\" >2521</td>\n",
+       "      <td id=\"T_059fc_row13_col1\" class=\"data row13 col1\" >33.227355</td>\n",
+       "      <td id=\"T_059fc_row13_col2\" class=\"data row13 col2\" >18.613504</td>\n",
+       "      <td id=\"T_059fc_row13_col3\" class=\"data row13 col3\" >-14.613851</td>\n",
+       "      <td id=\"T_059fc_row13_col4\" class=\"data row13 col4\" >3</td>\n",
+       "      <td id=\"T_059fc_row13_col5\" class=\"data row13 col5\" >41</td>\n",
+       "      <td id=\"T_059fc_row13_col6\" class=\"data row13 col6\" >-38</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row14\" class=\"row_heading level0 row14\" >pairrm-Yi-34B-Chat</th>\n",
+       "      <td id=\"T_059fc_row14_col0\" class=\"data row14 col0\" >2195</td>\n",
+       "      <td id=\"T_059fc_row14_col1\" class=\"data row14 col1\" >31.241283</td>\n",
+       "      <td id=\"T_059fc_row14_col2\" class=\"data row14 col2\" >26.712191</td>\n",
+       "      <td id=\"T_059fc_row14_col3\" class=\"data row14 col3\" >-4.529092</td>\n",
+       "      <td id=\"T_059fc_row14_col4\" class=\"data row14 col4\" >4</td>\n",
+       "      <td id=\"T_059fc_row14_col5\" class=\"data row14 col5\" >22</td>\n",
+       "      <td id=\"T_059fc_row14_col6\" class=\"data row14 col6\" >-18</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row15\" class=\"row_heading level0 row15\" >mistral-medium</th>\n",
+       "      <td id=\"T_059fc_row15_col0\" class=\"data row15 col0\" >1500</td>\n",
+       "      <td id=\"T_059fc_row15_col1\" class=\"data row15 col1\" >21.855773</td>\n",
+       "      <td id=\"T_059fc_row15_col2\" class=\"data row15 col2\" >32.778640</td>\n",
+       "      <td id=\"T_059fc_row15_col3\" class=\"data row15 col3\" >10.922867</td>\n",
+       "      <td id=\"T_059fc_row15_col4\" class=\"data row15 col4\" >16</td>\n",
+       "      <td id=\"T_059fc_row15_col5\" class=\"data row15 col5\" >11</td>\n",
+       "      <td id=\"T_059fc_row15_col6\" class=\"data row15 col6\" >5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row16\" class=\"row_heading level0 row16\" >claude-2</th>\n",
+       "      <td id=\"T_059fc_row16_col0\" class=\"data row16 col0\" >1069</td>\n",
+       "      <td id=\"T_059fc_row16_col1\" class=\"data row16 col1\" >17.188240</td>\n",
+       "      <td id=\"T_059fc_row16_col2\" class=\"data row16 col2\" >30.132118</td>\n",
+       "      <td id=\"T_059fc_row16_col3\" class=\"data row16 col3\" >12.943878</td>\n",
+       "      <td id=\"T_059fc_row16_col4\" class=\"data row16 col4\" >25</td>\n",
+       "      <td id=\"T_059fc_row16_col5\" class=\"data row16 col5\" >12</td>\n",
+       "      <td id=\"T_059fc_row16_col6\" class=\"data row16 col6\" >13</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row17\" class=\"row_heading level0 row17\" >claude</th>\n",
+       "      <td id=\"T_059fc_row17_col0\" class=\"data row17 col0\" >1082</td>\n",
+       "      <td id=\"T_059fc_row17_col1\" class=\"data row17 col1\" >16.985344</td>\n",
+       "      <td id=\"T_059fc_row17_col2\" class=\"data row17 col2\" >29.679901</td>\n",
+       "      <td id=\"T_059fc_row17_col3\" class=\"data row17 col3\" >12.694557</td>\n",
+       "      <td id=\"T_059fc_row17_col4\" class=\"data row17 col4\" >26</td>\n",
+       "      <td id=\"T_059fc_row17_col5\" class=\"data row17 col5\" >13</td>\n",
+       "      <td id=\"T_059fc_row17_col6\" class=\"data row17 col6\" >13</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row18\" class=\"row_heading level0 row18\" >Yi-34B-Chat</th>\n",
+       "      <td id=\"T_059fc_row18_col0\" class=\"data row18 col0\" >2123</td>\n",
+       "      <td id=\"T_059fc_row18_col1\" class=\"data row18 col1\" >29.659947</td>\n",
+       "      <td id=\"T_059fc_row18_col2\" class=\"data row18 col2\" >27.469108</td>\n",
+       "      <td id=\"T_059fc_row18_col3\" class=\"data row18 col3\" >-2.190839</td>\n",
+       "      <td id=\"T_059fc_row18_col4\" class=\"data row18 col4\" >6</td>\n",
+       "      <td id=\"T_059fc_row18_col5\" class=\"data row18 col5\" >18</td>\n",
+       "      <td id=\"T_059fc_row18_col6\" class=\"data row18 col6\" >-12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row19\" class=\"row_heading level0 row19\" >Snorkel-Mistral-PairRM-DPO</th>\n",
+       "      <td id=\"T_059fc_row19_col0\" class=\"data row19 col0\" >2736</td>\n",
+       "      <td id=\"T_059fc_row19_col1\" class=\"data row19 col1\" >30.220053</td>\n",
+       "      <td id=\"T_059fc_row19_col2\" class=\"data row19 col2\" >12.207351</td>\n",
+       "      <td id=\"T_059fc_row19_col3\" class=\"data row19 col3\" >-18.012701</td>\n",
+       "      <td id=\"T_059fc_row19_col4\" class=\"data row19 col4\" >5</td>\n",
+       "      <td id=\"T_059fc_row19_col5\" class=\"data row19 col5\" >77</td>\n",
+       "      <td id=\"T_059fc_row19_col6\" class=\"data row19 col6\" >-72</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row20\" class=\"row_heading level0 row20\" >claude-instant-1.2</th>\n",
+       "      <td id=\"T_059fc_row20_col0\" class=\"data row20 col0\" >1112</td>\n",
+       "      <td id=\"T_059fc_row20_col1\" class=\"data row20 col1\" >16.127400</td>\n",
+       "      <td id=\"T_059fc_row20_col2\" class=\"data row20 col2\" >27.962345</td>\n",
+       "      <td id=\"T_059fc_row20_col3\" class=\"data row20 col3\" >11.834945</td>\n",
+       "      <td id=\"T_059fc_row20_col4\" class=\"data row20 col4\" >27</td>\n",
+       "      <td id=\"T_059fc_row20_col5\" class=\"data row20 col5\" >14</td>\n",
+       "      <td id=\"T_059fc_row20_col6\" class=\"data row20 col6\" >13</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row21\" class=\"row_heading level0 row21\" >claude-2.1</th>\n",
+       "      <td id=\"T_059fc_row21_col0\" class=\"data row21 col0\" >1096</td>\n",
+       "      <td id=\"T_059fc_row21_col1\" class=\"data row21 col1\" >15.733507</td>\n",
+       "      <td id=\"T_059fc_row21_col2\" class=\"data row21 col2\" >27.394210</td>\n",
+       "      <td id=\"T_059fc_row21_col3\" class=\"data row21 col3\" >11.660703</td>\n",
+       "      <td id=\"T_059fc_row21_col4\" class=\"data row21 col4\" >31</td>\n",
+       "      <td id=\"T_059fc_row21_col5\" class=\"data row21 col5\" >19</td>\n",
+       "      <td id=\"T_059fc_row21_col6\" class=\"data row21 col6\" >12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row22\" class=\"row_heading level0 row22\" >xwinlm-70b-v0.1</th>\n",
+       "      <td id=\"T_059fc_row22_col0\" class=\"data row22 col0\" >1775</td>\n",
+       "      <td id=\"T_059fc_row22_col1\" class=\"data row22 col1\" >21.812957</td>\n",
+       "      <td id=\"T_059fc_row22_col2\" class=\"data row22 col2\" >27.644496</td>\n",
+       "      <td id=\"T_059fc_row22_col3\" class=\"data row22 col3\" >5.831539</td>\n",
+       "      <td id=\"T_059fc_row22_col4\" class=\"data row22 col4\" >17</td>\n",
+       "      <td id=\"T_059fc_row22_col5\" class=\"data row22 col5\" >17</td>\n",
+       "      <td id=\"T_059fc_row22_col6\" class=\"data row22 col6\" >0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row23\" class=\"row_heading level0 row23\" >gemini-pro</th>\n",
+       "      <td id=\"T_059fc_row23_col0\" class=\"data row23 col0\" >1456</td>\n",
+       "      <td id=\"T_059fc_row23_col1\" class=\"data row23 col1\" >18.177645</td>\n",
+       "      <td id=\"T_059fc_row23_col2\" class=\"data row23 col2\" >27.849057</td>\n",
+       "      <td id=\"T_059fc_row23_col3\" class=\"data row23 col3\" >9.671412</td>\n",
+       "      <td id=\"T_059fc_row23_col4\" class=\"data row23 col4\" >23</td>\n",
+       "      <td id=\"T_059fc_row23_col5\" class=\"data row23 col5\" >16</td>\n",
+       "      <td id=\"T_059fc_row23_col6\" class=\"data row23 col6\" >7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row24\" class=\"row_heading level0 row24\" >Mixtral-8x7B-Instruct-v0.1</th>\n",
+       "      <td id=\"T_059fc_row24_col0\" class=\"data row24 col0\" >1465</td>\n",
+       "      <td id=\"T_059fc_row24_col1\" class=\"data row24 col1\" >18.255318</td>\n",
+       "      <td id=\"T_059fc_row24_col2\" class=\"data row24 col2\" >27.849703</td>\n",
+       "      <td id=\"T_059fc_row24_col3\" class=\"data row24 col3\" >9.594386</td>\n",
+       "      <td id=\"T_059fc_row24_col4\" class=\"data row24 col4\" >22</td>\n",
+       "      <td id=\"T_059fc_row24_col5\" class=\"data row24 col5\" >15</td>\n",
+       "      <td id=\"T_059fc_row24_col6\" class=\"data row24 col6\" >7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row25\" class=\"row_heading level0 row25\" >evo-v2-7b</th>\n",
+       "      <td id=\"T_059fc_row25_col0\" class=\"data row25 col0\" >1754</td>\n",
+       "      <td id=\"T_059fc_row25_col1\" class=\"data row25 col1\" >20.834113</td>\n",
+       "      <td id=\"T_059fc_row25_col2\" class=\"data row25 col2\" >26.807884</td>\n",
+       "      <td id=\"T_059fc_row25_col3\" class=\"data row25 col3\" >5.973771</td>\n",
+       "      <td id=\"T_059fc_row25_col4\" class=\"data row25 col4\" >20</td>\n",
+       "      <td id=\"T_059fc_row25_col5\" class=\"data row25 col5\" >21</td>\n",
+       "      <td id=\"T_059fc_row25_col6\" class=\"data row25 col6\" >-1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row26\" class=\"row_heading level0 row26\" >Mixtral-8x7B-Instruct-v0.1_verbose</th>\n",
+       "      <td id=\"T_059fc_row26_col0\" class=\"data row26 col0\" >2083</td>\n",
+       "      <td id=\"T_059fc_row26_col1\" class=\"data row26 col1\" >24.614063</td>\n",
+       "      <td id=\"T_059fc_row26_col2\" class=\"data row26 col2\" >23.777507</td>\n",
+       "      <td id=\"T_059fc_row26_col3\" class=\"data row26 col3\" >-0.836556</td>\n",
+       "      <td id=\"T_059fc_row26_col4\" class=\"data row26 col4\" >10</td>\n",
+       "      <td id=\"T_059fc_row26_col5\" class=\"data row26 col5\" >27</td>\n",
+       "      <td id=\"T_059fc_row26_col6\" class=\"data row26 col6\" >-17</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row27\" class=\"row_heading level0 row27\" >Mixtral-8x7B-Instruct-v0.1_concise</th>\n",
+       "      <td id=\"T_059fc_row27_col0\" class=\"data row27 col0\" >910</td>\n",
+       "      <td id=\"T_059fc_row27_col1\" class=\"data row27 col1\" >13.744040</td>\n",
+       "      <td id=\"T_059fc_row27_col2\" class=\"data row27 col2\" >24.932748</td>\n",
+       "      <td id=\"T_059fc_row27_col3\" class=\"data row27 col3\" >11.188708</td>\n",
+       "      <td id=\"T_059fc_row27_col4\" class=\"data row27 col4\" >41</td>\n",
+       "      <td id=\"T_059fc_row27_col5\" class=\"data row27 col5\" >24</td>\n",
+       "      <td id=\"T_059fc_row27_col6\" class=\"data row27 col6\" >17</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row28\" class=\"row_heading level0 row28\" >gpt-3.5-turbo-16k-0613</th>\n",
+       "      <td id=\"T_059fc_row28_col0\" class=\"data row28 col0\" >1328</td>\n",
+       "      <td id=\"T_059fc_row28_col1\" class=\"data row28 col1\" >14.132391</td>\n",
+       "      <td id=\"T_059fc_row28_col2\" class=\"data row28 col2\" >22.859543</td>\n",
+       "      <td id=\"T_059fc_row28_col3\" class=\"data row28 col3\" >8.727152</td>\n",
+       "      <td id=\"T_059fc_row28_col4\" class=\"data row28 col4\" >36</td>\n",
+       "      <td id=\"T_059fc_row28_col5\" class=\"data row28 col5\" >28</td>\n",
+       "      <td id=\"T_059fc_row28_col6\" class=\"data row28 col6\" >8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row29\" class=\"row_heading level0 row29\" >gpt-3.5-turbo-0613</th>\n",
+       "      <td id=\"T_059fc_row29_col0\" class=\"data row29 col0\" >1331</td>\n",
+       "      <td id=\"T_059fc_row29_col1\" class=\"data row29 col1\" >14.095799</td>\n",
+       "      <td id=\"T_059fc_row29_col2\" class=\"data row29 col2\" >22.774144</td>\n",
+       "      <td id=\"T_059fc_row29_col3\" class=\"data row29 col3\" >8.678345</td>\n",
+       "      <td id=\"T_059fc_row29_col4\" class=\"data row29 col4\" >37</td>\n",
+       "      <td id=\"T_059fc_row29_col5\" class=\"data row29 col5\" >29</td>\n",
+       "      <td id=\"T_059fc_row29_col6\" class=\"data row29 col6\" >8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row30\" class=\"row_heading level0 row30\" >gpt-3.5-turbo-1106_verbose</th>\n",
+       "      <td id=\"T_059fc_row30_col0\" class=\"data row30 col0\" >1058</td>\n",
+       "      <td id=\"T_059fc_row30_col1\" class=\"data row30 col1\" >12.763170</td>\n",
+       "      <td id=\"T_059fc_row30_col2\" class=\"data row30 col2\" >22.434952</td>\n",
+       "      <td id=\"T_059fc_row30_col3\" class=\"data row30 col3\" >9.671782</td>\n",
+       "      <td id=\"T_059fc_row30_col4\" class=\"data row30 col4\" >45</td>\n",
+       "      <td id=\"T_059fc_row30_col5\" class=\"data row30 col5\" >30</td>\n",
+       "      <td id=\"T_059fc_row30_col6\" class=\"data row30 col6\" >15</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row31\" class=\"row_heading level0 row31\" >gpt4_0613_concise</th>\n",
+       "      <td id=\"T_059fc_row31_col0\" class=\"data row31 col0\" >627</td>\n",
+       "      <td id=\"T_059fc_row31_col1\" class=\"data row31 col1\" >9.400321</td>\n",
+       "      <td id=\"T_059fc_row31_col2\" class=\"data row31 col2\" >17.766751</td>\n",
+       "      <td id=\"T_059fc_row31_col3\" class=\"data row31 col3\" >8.366430</td>\n",
+       "      <td id=\"T_059fc_row31_col4\" class=\"data row31 col4\" >63</td>\n",
+       "      <td id=\"T_059fc_row31_col5\" class=\"data row31 col5\" >44</td>\n",
+       "      <td id=\"T_059fc_row31_col6\" class=\"data row31 col6\" >19</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row32\" class=\"row_heading level0 row32\" >pairrm-tulu-2-70b</th>\n",
+       "      <td id=\"T_059fc_row32_col0\" class=\"data row32 col0\" >1607</td>\n",
+       "      <td id=\"T_059fc_row32_col1\" class=\"data row32 col1\" >18.638963</td>\n",
+       "      <td id=\"T_059fc_row32_col2\" class=\"data row32 col2\" >26.379740</td>\n",
+       "      <td id=\"T_059fc_row32_col3\" class=\"data row32 col3\" >7.740777</td>\n",
+       "      <td id=\"T_059fc_row32_col4\" class=\"data row32 col4\" >21</td>\n",
+       "      <td id=\"T_059fc_row32_col5\" class=\"data row32 col5\" >23</td>\n",
+       "      <td id=\"T_059fc_row32_col6\" class=\"data row32 col6\" >-2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row33\" class=\"row_heading level0 row33\" >tulu-2-dpo-70b</th>\n",
+       "      <td id=\"T_059fc_row33_col0\" class=\"data row33 col0\" >1418</td>\n",
+       "      <td id=\"T_059fc_row33_col1\" class=\"data row33 col1\" >15.982854</td>\n",
+       "      <td id=\"T_059fc_row33_col2\" class=\"data row33 col2\" >24.913121</td>\n",
+       "      <td id=\"T_059fc_row33_col3\" class=\"data row33 col3\" >8.930267</td>\n",
+       "      <td id=\"T_059fc_row33_col4\" class=\"data row33 col4\" >29</td>\n",
+       "      <td id=\"T_059fc_row33_col5\" class=\"data row33 col5\" >25</td>\n",
+       "      <td id=\"T_059fc_row33_col6\" class=\"data row33 col6\" >4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row34\" class=\"row_heading level0 row34\" >Mistral-7B-ReMax-v0.1</th>\n",
+       "      <td id=\"T_059fc_row34_col0\" class=\"data row34 col0\" >1478</td>\n",
+       "      <td id=\"T_059fc_row34_col1\" class=\"data row34 col1\" >15.999331</td>\n",
+       "      <td id=\"T_059fc_row34_col2\" class=\"data row34 col2\" >24.256479</td>\n",
+       "      <td id=\"T_059fc_row34_col3\" class=\"data row34 col3\" >8.257148</td>\n",
+       "      <td id=\"T_059fc_row34_col4\" class=\"data row34 col4\" >28</td>\n",
+       "      <td id=\"T_059fc_row34_col5\" class=\"data row34 col5\" >26</td>\n",
+       "      <td id=\"T_059fc_row34_col6\" class=\"data row34 col6\" >2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row35\" class=\"row_heading level0 row35\" >gpt-3.5-turbo-1106</th>\n",
+       "      <td id=\"T_059fc_row35_col0\" class=\"data row35 col0\" >796</td>\n",
+       "      <td id=\"T_059fc_row35_col1\" class=\"data row35 col1\" >9.177965</td>\n",
+       "      <td id=\"T_059fc_row35_col2\" class=\"data row35 col2\" >16.971183</td>\n",
+       "      <td id=\"T_059fc_row35_col3\" class=\"data row35 col3\" >7.793218</td>\n",
+       "      <td id=\"T_059fc_row35_col4\" class=\"data row35 col4\" >66</td>\n",
+       "      <td id=\"T_059fc_row35_col5\" class=\"data row35 col5\" >51</td>\n",
+       "      <td id=\"T_059fc_row35_col6\" class=\"data row35 col6\" >15</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row36\" class=\"row_heading level0 row36\" >LMCocktail-10.7B-v1</th>\n",
+       "      <td id=\"T_059fc_row36_col0\" class=\"data row36 col0\" >1203</td>\n",
+       "      <td id=\"T_059fc_row36_col1\" class=\"data row36 col1\" >13.153431</td>\n",
+       "      <td id=\"T_059fc_row36_col2\" class=\"data row36 col2\" >22.215803</td>\n",
+       "      <td id=\"T_059fc_row36_col3\" class=\"data row36 col3\" >9.062372</td>\n",
+       "      <td id=\"T_059fc_row36_col4\" class=\"data row36 col4\" >42</td>\n",
+       "      <td id=\"T_059fc_row36_col5\" class=\"data row36 col5\" >31</td>\n",
+       "      <td id=\"T_059fc_row36_col6\" class=\"data row36 col6\" >11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row37\" class=\"row_heading level0 row37\" >internlm2-chat-20b-ppo</th>\n",
+       "      <td id=\"T_059fc_row37_col0\" class=\"data row37 col0\" >2373</td>\n",
+       "      <td id=\"T_059fc_row37_col1\" class=\"data row37 col1\" >21.749155</td>\n",
+       "      <td id=\"T_059fc_row37_col2\" class=\"data row37 col2\" >14.939076</td>\n",
+       "      <td id=\"T_059fc_row37_col3\" class=\"data row37 col3\" >-6.810079</td>\n",
+       "      <td id=\"T_059fc_row37_col4\" class=\"data row37 col4\" >18</td>\n",
+       "      <td id=\"T_059fc_row37_col5\" class=\"data row37 col5\" >62</td>\n",
+       "      <td id=\"T_059fc_row37_col6\" class=\"data row37 col6\" >-44</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row38\" class=\"row_heading level0 row38\" >claude-2.1_concise</th>\n",
+       "      <td id=\"T_059fc_row38_col0\" class=\"data row38 col0\" >573</td>\n",
+       "      <td id=\"T_059fc_row38_col1\" class=\"data row38 col1\" >9.227125</td>\n",
+       "      <td id=\"T_059fc_row38_col2\" class=\"data row38 col2\" >17.538143</td>\n",
+       "      <td id=\"T_059fc_row38_col3\" class=\"data row38 col3\" >8.311018</td>\n",
+       "      <td id=\"T_059fc_row38_col4\" class=\"data row38 col4\" >65</td>\n",
+       "      <td id=\"T_059fc_row38_col5\" class=\"data row38 col5\" >48</td>\n",
+       "      <td id=\"T_059fc_row38_col6\" class=\"data row38 col6\" >17</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row39\" class=\"row_heading level0 row39\" >gpt-3.5-turbo-0301</th>\n",
+       "      <td id=\"T_059fc_row39_col0\" class=\"data row39 col0\" >827</td>\n",
+       "      <td id=\"T_059fc_row39_col1\" class=\"data row39 col1\" >9.622453</td>\n",
+       "      <td id=\"T_059fc_row39_col2\" class=\"data row39 col2\" >17.707654</td>\n",
+       "      <td id=\"T_059fc_row39_col3\" class=\"data row39 col3\" >8.085200</td>\n",
+       "      <td id=\"T_059fc_row39_col4\" class=\"data row39 col4\" >60</td>\n",
+       "      <td id=\"T_059fc_row39_col5\" class=\"data row39 col5\" >45</td>\n",
+       "      <td id=\"T_059fc_row39_col6\" class=\"data row39 col6\" >15</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row40\" class=\"row_heading level0 row40\" >xwinlm-13b-v0.1</th>\n",
+       "      <td id=\"T_059fc_row40_col0\" class=\"data row40 col0\" >1894</td>\n",
+       "      <td id=\"T_059fc_row40_col1\" class=\"data row40 col1\" >17.427935</td>\n",
+       "      <td id=\"T_059fc_row40_col2\" class=\"data row40 col2\" >20.107837</td>\n",
+       "      <td id=\"T_059fc_row40_col3\" class=\"data row40 col3\" >2.679903</td>\n",
+       "      <td id=\"T_059fc_row40_col4\" class=\"data row40 col4\" >24</td>\n",
+       "      <td id=\"T_059fc_row40_col5\" class=\"data row40 col5\" >35</td>\n",
+       "      <td id=\"T_059fc_row40_col6\" class=\"data row40 col6\" >-11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row41\" class=\"row_heading level0 row41\" >deepseek-llm-67b-chat</th>\n",
+       "      <td id=\"T_059fc_row41_col0\" class=\"data row41 col0\" >1151</td>\n",
+       "      <td id=\"T_059fc_row41_col1\" class=\"data row41 col1\" >12.093422</td>\n",
+       "      <td id=\"T_059fc_row41_col2\" class=\"data row41 col2\" >20.744121</td>\n",
+       "      <td id=\"T_059fc_row41_col3\" class=\"data row41 col3\" >8.650699</td>\n",
+       "      <td id=\"T_059fc_row41_col4\" class=\"data row41 col4\" >48</td>\n",
+       "      <td id=\"T_059fc_row41_col5\" class=\"data row41 col5\" >34</td>\n",
+       "      <td id=\"T_059fc_row41_col6\" class=\"data row41 col6\" >14</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row42\" class=\"row_heading level0 row42\" >gpt35_turbo_instruct</th>\n",
+       "      <td id=\"T_059fc_row42_col0\" class=\"data row42 col0\" >1018</td>\n",
+       "      <td id=\"T_059fc_row42_col1\" class=\"data row42 col1\" >8.462447</td>\n",
+       "      <td id=\"T_059fc_row42_col2\" class=\"data row42 col2\" >15.014996</td>\n",
+       "      <td id=\"T_059fc_row42_col3\" class=\"data row42 col3\" >6.552549</td>\n",
+       "      <td id=\"T_059fc_row42_col4\" class=\"data row42 col4\" >70</td>\n",
+       "      <td id=\"T_059fc_row42_col5\" class=\"data row42 col5\" >59</td>\n",
+       "      <td id=\"T_059fc_row42_col6\" class=\"data row42 col6\" >11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row43\" class=\"row_heading level0 row43\" >wizardlm-70b</th>\n",
+       "      <td id=\"T_059fc_row43_col0\" class=\"data row43 col0\" >1545</td>\n",
+       "      <td id=\"T_059fc_row43_col1\" class=\"data row43 col1\" >14.383896</td>\n",
+       "      <td id=\"T_059fc_row43_col2\" class=\"data row43 col2\" >21.076106</td>\n",
+       "      <td id=\"T_059fc_row43_col3\" class=\"data row43 col3\" >6.692210</td>\n",
+       "      <td id=\"T_059fc_row43_col4\" class=\"data row43 col4\" >34</td>\n",
+       "      <td id=\"T_059fc_row43_col5\" class=\"data row43 col5\" >33</td>\n",
+       "      <td id=\"T_059fc_row43_col6\" class=\"data row43 col6\" >1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row44\" class=\"row_heading level0 row44\" >vicuna-33b-v1.3</th>\n",
+       "      <td id=\"T_059fc_row44_col0\" class=\"data row44 col0\" >1479</td>\n",
+       "      <td id=\"T_059fc_row44_col1\" class=\"data row44 col1\" >12.705948</td>\n",
+       "      <td id=\"T_059fc_row44_col2\" class=\"data row44 col2\" >19.254076</td>\n",
+       "      <td id=\"T_059fc_row44_col3\" class=\"data row44 col3\" >6.548128</td>\n",
+       "      <td id=\"T_059fc_row44_col4\" class=\"data row44 col4\" >46</td>\n",
+       "      <td id=\"T_059fc_row44_col5\" class=\"data row44 col5\" >40</td>\n",
+       "      <td id=\"T_059fc_row44_col6\" class=\"data row44 col6\" >6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row45\" class=\"row_heading level0 row45\" >pairrm-tulu-2-13b</th>\n",
+       "      <td id=\"T_059fc_row45_col0\" class=\"data row45 col0\" >1454</td>\n",
+       "      <td id=\"T_059fc_row45_col1\" class=\"data row45 col1\" >13.831901</td>\n",
+       "      <td id=\"T_059fc_row45_col2\" class=\"data row45 col2\" >21.210973</td>\n",
+       "      <td id=\"T_059fc_row45_col3\" class=\"data row45 col3\" >7.379072</td>\n",
+       "      <td id=\"T_059fc_row45_col4\" class=\"data row45 col4\" >40</td>\n",
+       "      <td id=\"T_059fc_row45_col5\" class=\"data row45 col5\" >32</td>\n",
+       "      <td id=\"T_059fc_row45_col6\" class=\"data row45 col6\" >8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row46\" class=\"row_heading level0 row46\" >Mistral-7B-Instruct-v0.2</th>\n",
+       "      <td id=\"T_059fc_row46_col0\" class=\"data row46 col0\" >1676</td>\n",
+       "      <td id=\"T_059fc_row46_col1\" class=\"data row46 col1\" >14.722773</td>\n",
+       "      <td id=\"T_059fc_row46_col2\" class=\"data row46 col2\" >19.973105</td>\n",
+       "      <td id=\"T_059fc_row46_col3\" class=\"data row46 col3\" >5.250332</td>\n",
+       "      <td id=\"T_059fc_row46_col4\" class=\"data row46 col4\" >33</td>\n",
+       "      <td id=\"T_059fc_row46_col5\" class=\"data row46 col5\" >36</td>\n",
+       "      <td id=\"T_059fc_row46_col6\" class=\"data row46 col6\" >-3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row47\" class=\"row_heading level0 row47\" >evo-7b</th>\n",
+       "      <td id=\"T_059fc_row47_col0\" class=\"data row47 col0\" >1774</td>\n",
+       "      <td id=\"T_059fc_row47_col1\" class=\"data row47 col1\" >15.577437</td>\n",
+       "      <td id=\"T_059fc_row47_col2\" class=\"data row47 col2\" >19.756415</td>\n",
+       "      <td id=\"T_059fc_row47_col3\" class=\"data row47 col3\" >4.178978</td>\n",
+       "      <td id=\"T_059fc_row47_col4\" class=\"data row47 col4\" >32</td>\n",
+       "      <td id=\"T_059fc_row47_col5\" class=\"data row47 col5\" >37</td>\n",
+       "      <td id=\"T_059fc_row47_col6\" class=\"data row47 col6\" >-5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row48\" class=\"row_heading level0 row48\" >humpback-llama2-70b</th>\n",
+       "      <td id=\"T_059fc_row48_col0\" class=\"data row48 col0\" >1107</td>\n",
+       "      <td id=\"T_059fc_row48_col1\" class=\"data row48 col1\" >10.121772</td>\n",
+       "      <td id=\"T_059fc_row48_col2\" class=\"data row48 col2\" >17.572810</td>\n",
+       "      <td id=\"T_059fc_row48_col3\" class=\"data row48 col3\" >7.451039</td>\n",
+       "      <td id=\"T_059fc_row48_col4\" class=\"data row48 col4\" >58</td>\n",
+       "      <td id=\"T_059fc_row48_col5\" class=\"data row48 col5\" >47</td>\n",
+       "      <td id=\"T_059fc_row48_col6\" class=\"data row48 col6\" >11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row49\" class=\"row_heading level0 row49\" >OpenHermes-2.5-Mistral-7B</th>\n",
+       "      <td id=\"T_059fc_row49_col0\" class=\"data row49 col0\" >1107</td>\n",
+       "      <td id=\"T_059fc_row49_col1\" class=\"data row49 col1\" >10.340416</td>\n",
+       "      <td id=\"T_059fc_row49_col2\" class=\"data row49 col2\" >17.952407</td>\n",
+       "      <td id=\"T_059fc_row49_col3\" class=\"data row49 col3\" >7.611992</td>\n",
+       "      <td id=\"T_059fc_row49_col4\" class=\"data row49 col4\" >57</td>\n",
+       "      <td id=\"T_059fc_row49_col5\" class=\"data row49 col5\" >43</td>\n",
+       "      <td id=\"T_059fc_row49_col6\" class=\"data row49 col6\" >14</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row50\" class=\"row_heading level0 row50\" >deita-7b-v1.0</th>\n",
+       "      <td id=\"T_059fc_row50_col0\" class=\"data row50 col0\" >1417</td>\n",
+       "      <td id=\"T_059fc_row50_col1\" class=\"data row50 col1\" >12.646639</td>\n",
+       "      <td id=\"T_059fc_row50_col2\" class=\"data row50 col2\" >19.721522</td>\n",
+       "      <td id=\"T_059fc_row50_col3\" class=\"data row50 col3\" >7.074882</td>\n",
+       "      <td id=\"T_059fc_row50_col4\" class=\"data row50 col4\" >47</td>\n",
+       "      <td id=\"T_059fc_row50_col5\" class=\"data row50 col5\" >38</td>\n",
+       "      <td id=\"T_059fc_row50_col6\" class=\"data row50 col6\" >9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row51\" class=\"row_heading level0 row51\" >jina-chat</th>\n",
+       "      <td id=\"T_059fc_row51_col0\" class=\"data row51 col0\" >676</td>\n",
+       "      <td id=\"T_059fc_row51_col1\" class=\"data row51 col1\" >7.786130</td>\n",
+       "      <td id=\"T_059fc_row51_col2\" class=\"data row51 col2\" >14.633052</td>\n",
+       "      <td id=\"T_059fc_row51_col3\" class=\"data row51 col3\" >6.846921</td>\n",
+       "      <td id=\"T_059fc_row51_col4\" class=\"data row51 col4\" >76</td>\n",
+       "      <td id=\"T_059fc_row51_col5\" class=\"data row51 col5\" >63</td>\n",
+       "      <td id=\"T_059fc_row51_col6\" class=\"data row51 col6\" >13</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row52\" class=\"row_heading level0 row52\" >gpt-3.5-turbo-1106_concise</th>\n",
+       "      <td id=\"T_059fc_row52_col0\" class=\"data row52 col0\" >431</td>\n",
+       "      <td id=\"T_059fc_row52_col1\" class=\"data row52 col1\" >7.415865</td>\n",
+       "      <td id=\"T_059fc_row52_col2\" class=\"data row52 col2\" >14.270598</td>\n",
+       "      <td id=\"T_059fc_row52_col3\" class=\"data row52 col3\" >6.854733</td>\n",
+       "      <td id=\"T_059fc_row52_col4\" class=\"data row52 col4\" >84</td>\n",
+       "      <td id=\"T_059fc_row52_col5\" class=\"data row52 col5\" >64</td>\n",
+       "      <td id=\"T_059fc_row52_col6\" class=\"data row52 col6\" >20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row53\" class=\"row_heading level0 row53\" >causallm-14b</th>\n",
+       "      <td id=\"T_059fc_row53_col0\" class=\"data row53 col0\" >1391</td>\n",
+       "      <td id=\"T_059fc_row53_col1\" class=\"data row53 col1\" >11.146161</td>\n",
+       "      <td id=\"T_059fc_row53_col2\" class=\"data row53 col2\" >17.577840</td>\n",
+       "      <td id=\"T_059fc_row53_col3\" class=\"data row53 col3\" >6.431679</td>\n",
+       "      <td id=\"T_059fc_row53_col4\" class=\"data row53 col4\" >53</td>\n",
+       "      <td id=\"T_059fc_row53_col5\" class=\"data row53 col5\" >46</td>\n",
+       "      <td id=\"T_059fc_row53_col6\" class=\"data row53 col6\" >7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row54\" class=\"row_heading level0 row54\" >pairrm-zephyr-7b-beta</th>\n",
+       "      <td id=\"T_059fc_row54_col0\" class=\"data row54 col0\" >1487</td>\n",
+       "      <td id=\"T_059fc_row54_col1\" class=\"data row54 col1\" >12.841278</td>\n",
+       "      <td id=\"T_059fc_row54_col2\" class=\"data row54 col2\" >19.383394</td>\n",
+       "      <td id=\"T_059fc_row54_col3\" class=\"data row54 col3\" >6.542116</td>\n",
+       "      <td id=\"T_059fc_row54_col4\" class=\"data row54 col4\" >44</td>\n",
+       "      <td id=\"T_059fc_row54_col5\" class=\"data row54 col5\" >39</td>\n",
+       "      <td id=\"T_059fc_row54_col6\" class=\"data row54 col6\" >5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row55\" class=\"row_heading level0 row55\" >Starling-LM-7B-alpha</th>\n",
+       "      <td id=\"T_059fc_row55_col0\" class=\"data row55 col0\" >1895</td>\n",
+       "      <td id=\"T_059fc_row55_col1\" class=\"data row55 col1\" >14.245924</td>\n",
+       "      <td id=\"T_059fc_row55_col2\" class=\"data row55 col2\" >16.422615</td>\n",
+       "      <td id=\"T_059fc_row55_col3\" class=\"data row55 col3\" >2.176692</td>\n",
+       "      <td id=\"T_059fc_row55_col4\" class=\"data row55 col4\" >35</td>\n",
+       "      <td id=\"T_059fc_row55_col5\" class=\"data row55 col5\" >56</td>\n",
+       "      <td id=\"T_059fc_row55_col6\" class=\"data row55 col6\" >-21</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row56\" class=\"row_heading level0 row56\" >llama-2-70b-chat-hf</th>\n",
+       "      <td id=\"T_059fc_row56_col0\" class=\"data row56 col0\" >1790</td>\n",
+       "      <td id=\"T_059fc_row56_col1\" class=\"data row56 col1\" >13.888258</td>\n",
+       "      <td id=\"T_059fc_row56_col2\" class=\"data row56 col2\" >17.406987</td>\n",
+       "      <td id=\"T_059fc_row56_col3\" class=\"data row56 col3\" >3.518729</td>\n",
+       "      <td id=\"T_059fc_row56_col4\" class=\"data row56 col4\" >38</td>\n",
+       "      <td id=\"T_059fc_row56_col5\" class=\"data row56 col5\" >49</td>\n",
+       "      <td id=\"T_059fc_row56_col6\" class=\"data row56 col6\" >-11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row57\" class=\"row_heading level0 row57\" >openchat-v3.1-13b</th>\n",
+       "      <td id=\"T_059fc_row57_col0\" class=\"data row57 col0\" >1484</td>\n",
+       "      <td id=\"T_059fc_row57_col1\" class=\"data row57 col1\" >11.082230</td>\n",
+       "      <td id=\"T_059fc_row57_col2\" class=\"data row57 col2\" >16.752762</td>\n",
+       "      <td id=\"T_059fc_row57_col3\" class=\"data row57 col3\" >5.670531</td>\n",
+       "      <td id=\"T_059fc_row57_col4\" class=\"data row57 col4\" >54</td>\n",
+       "      <td id=\"T_059fc_row57_col5\" class=\"data row57 col5\" >53</td>\n",
+       "      <td id=\"T_059fc_row57_col6\" class=\"data row57 col6\" >1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row58\" class=\"row_heading level0 row58\" >wizardlm-13b-v1.2</th>\n",
+       "      <td id=\"T_059fc_row58_col0\" class=\"data row58 col0\" >1635</td>\n",
+       "      <td id=\"T_059fc_row58_col1\" class=\"data row58 col1\" >12.027480</td>\n",
+       "      <td id=\"T_059fc_row58_col2\" class=\"data row58 col2\" >16.740614</td>\n",
+       "      <td id=\"T_059fc_row58_col3\" class=\"data row58 col3\" >4.713134</td>\n",
+       "      <td id=\"T_059fc_row58_col4\" class=\"data row58 col4\" >49</td>\n",
+       "      <td id=\"T_059fc_row58_col5\" class=\"data row58 col5\" >54</td>\n",
+       "      <td id=\"T_059fc_row58_col6\" class=\"data row58 col6\" >-5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row59\" class=\"row_heading level0 row59\" >ultralm-13b-v2.0-best-of-16</th>\n",
+       "      <td id=\"T_059fc_row59_col0\" class=\"data row59 col0\" >1720</td>\n",
+       "      <td id=\"T_059fc_row59_col1\" class=\"data row59 col1\" >13.853373</td>\n",
+       "      <td id=\"T_059fc_row59_col2\" class=\"data row59 col2\" >18.253509</td>\n",
+       "      <td id=\"T_059fc_row59_col3\" class=\"data row59 col3\" >4.400135</td>\n",
+       "      <td id=\"T_059fc_row59_col4\" class=\"data row59 col4\" >39</td>\n",
+       "      <td id=\"T_059fc_row59_col5\" class=\"data row59 col5\" >42</td>\n",
+       "      <td id=\"T_059fc_row59_col6\" class=\"data row59 col6\" >-3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row60\" class=\"row_heading level0 row60\" >wizardlm-13b-v1.1</th>\n",
+       "      <td id=\"T_059fc_row60_col0\" class=\"data row60 col0\" >1525</td>\n",
+       "      <td id=\"T_059fc_row60_col1\" class=\"data row60 col1\" >11.233910</td>\n",
+       "      <td id=\"T_059fc_row60_col2\" class=\"data row60 col2\" >16.634963</td>\n",
+       "      <td id=\"T_059fc_row60_col3\" class=\"data row60 col3\" >5.401054</td>\n",
+       "      <td id=\"T_059fc_row60_col4\" class=\"data row60 col4\" >52</td>\n",
+       "      <td id=\"T_059fc_row60_col5\" class=\"data row60 col5\" >55</td>\n",
+       "      <td id=\"T_059fc_row60_col6\" class=\"data row60 col6\" >-3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row61\" class=\"row_heading level0 row61\" >zephyr-7b-beta</th>\n",
+       "      <td id=\"T_059fc_row61_col0\" class=\"data row61 col0\" >1444</td>\n",
+       "      <td id=\"T_059fc_row61_col1\" class=\"data row61 col1\" >10.992886</td>\n",
+       "      <td id=\"T_059fc_row61_col2\" class=\"data row61 col2\" >16.935617</td>\n",
+       "      <td id=\"T_059fc_row61_col3\" class=\"data row61 col3\" >5.942731</td>\n",
+       "      <td id=\"T_059fc_row61_col4\" class=\"data row61 col4\" >55</td>\n",
+       "      <td id=\"T_059fc_row61_col5\" class=\"data row61 col5\" >52</td>\n",
+       "      <td id=\"T_059fc_row61_col6\" class=\"data row61 col6\" >3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row62\" class=\"row_heading level0 row62\" >dolphin-2.2.1-mistral-7b</th>\n",
+       "      <td id=\"T_059fc_row62_col0\" class=\"data row62 col0\" >1130</td>\n",
+       "      <td id=\"T_059fc_row62_col1\" class=\"data row62 col1\" >9.039800</td>\n",
+       "      <td id=\"T_059fc_row62_col2\" class=\"data row62 col2\" >15.597487</td>\n",
+       "      <td id=\"T_059fc_row62_col3\" class=\"data row62 col3\" >6.557688</td>\n",
+       "      <td id=\"T_059fc_row62_col4\" class=\"data row62 col4\" >68</td>\n",
+       "      <td id=\"T_059fc_row62_col5\" class=\"data row62 col5\" >58</td>\n",
+       "      <td id=\"T_059fc_row62_col6\" class=\"data row62 col6\" >10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row63\" class=\"row_heading level0 row63\" >humpback-llama-65b</th>\n",
+       "      <td id=\"T_059fc_row63_col0\" class=\"data row63 col0\" >1232</td>\n",
+       "      <td id=\"T_059fc_row63_col1\" class=\"data row63 col1\" >9.425139</td>\n",
+       "      <td id=\"T_059fc_row63_col2\" class=\"data row63 col2\" >15.772346</td>\n",
+       "      <td id=\"T_059fc_row63_col3\" class=\"data row63 col3\" >6.347206</td>\n",
+       "      <td id=\"T_059fc_row63_col4\" class=\"data row63 col4\" >62</td>\n",
+       "      <td id=\"T_059fc_row63_col5\" class=\"data row63 col5\" >57</td>\n",
+       "      <td id=\"T_059fc_row63_col6\" class=\"data row63 col6\" >5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row64\" class=\"row_heading level0 row64\" >openbuddy-llama2-70b-v10.1</th>\n",
+       "      <td id=\"T_059fc_row64_col0\" class=\"data row64 col0\" >1077</td>\n",
+       "      <td id=\"T_059fc_row64_col1\" class=\"data row64 col1\" >8.096422</td>\n",
+       "      <td id=\"T_059fc_row64_col2\" class=\"data row64 col2\" >14.165353</td>\n",
+       "      <td id=\"T_059fc_row64_col3\" class=\"data row64 col3\" >6.068931</td>\n",
+       "      <td id=\"T_059fc_row64_col4\" class=\"data row64 col4\" >74</td>\n",
+       "      <td id=\"T_059fc_row64_col5\" class=\"data row64 col5\" >66</td>\n",
+       "      <td id=\"T_059fc_row64_col6\" class=\"data row64 col6\" >8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row65\" class=\"row_heading level0 row65\" >openbuddy-llama-65b-v8</th>\n",
+       "      <td id=\"T_059fc_row65_col0\" class=\"data row65 col0\" >1162</td>\n",
+       "      <td id=\"T_059fc_row65_col1\" class=\"data row65 col1\" >8.770650</td>\n",
+       "      <td id=\"T_059fc_row65_col2\" class=\"data row65 col2\" >14.997012</td>\n",
+       "      <td id=\"T_059fc_row65_col3\" class=\"data row65 col3\" >6.226362</td>\n",
+       "      <td id=\"T_059fc_row65_col4\" class=\"data row65 col4\" >69</td>\n",
+       "      <td id=\"T_059fc_row65_col5\" class=\"data row65 col5\" >60</td>\n",
+       "      <td id=\"T_059fc_row65_col6\" class=\"data row65 col6\" >9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row66\" class=\"row_heading level0 row66\" >Qwen-14B-Chat</th>\n",
+       "      <td id=\"T_059fc_row66_col0\" class=\"data row66 col0\" >1013</td>\n",
+       "      <td id=\"T_059fc_row66_col1\" class=\"data row66 col1\" >7.502333</td>\n",
+       "      <td id=\"T_059fc_row66_col2\" class=\"data row66 col2\" >13.326422</td>\n",
+       "      <td id=\"T_059fc_row66_col3\" class=\"data row66 col3\" >5.824088</td>\n",
+       "      <td id=\"T_059fc_row66_col4\" class=\"data row66 col4\" >81</td>\n",
+       "      <td id=\"T_059fc_row66_col5\" class=\"data row66 col5\" >72</td>\n",
+       "      <td id=\"T_059fc_row66_col6\" class=\"data row66 col6\" >9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row67\" class=\"row_heading level0 row67\" >gpt4_gamed</th>\n",
+       "      <td id=\"T_059fc_row67_col0\" class=\"data row67 col0\" >68</td>\n",
+       "      <td id=\"T_059fc_row67_col1\" class=\"data row67 col1\" >3.738337</td>\n",
+       "      <td id=\"T_059fc_row67_col2\" class=\"data row67 col2\" >7.337086</td>\n",
+       "      <td id=\"T_059fc_row67_col3\" class=\"data row67 col3\" >3.598749</td>\n",
+       "      <td id=\"T_059fc_row67_col4\" class=\"data row67 col4\" >112</td>\n",
+       "      <td id=\"T_059fc_row67_col5\" class=\"data row67 col5\" >111</td>\n",
+       "      <td id=\"T_059fc_row67_col6\" class=\"data row67 col6\" >1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row68\" class=\"row_heading level0 row68\" >cut-13b</th>\n",
+       "      <td id=\"T_059fc_row68_col0\" class=\"data row68 col0\" >1637</td>\n",
+       "      <td id=\"T_059fc_row68_col1\" class=\"data row68 col1\" >10.779089</td>\n",
+       "      <td id=\"T_059fc_row68_col2\" class=\"data row68 col2\" >14.984761</td>\n",
+       "      <td id=\"T_059fc_row68_col3\" class=\"data row68 col3\" >4.205672</td>\n",
+       "      <td id=\"T_059fc_row68_col4\" class=\"data row68 col4\" >56</td>\n",
+       "      <td id=\"T_059fc_row68_col5\" class=\"data row68 col5\" >61</td>\n",
+       "      <td id=\"T_059fc_row68_col6\" class=\"data row68 col6\" >-5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row69\" class=\"row_heading level0 row69\" >openchat-v2-w-13b</th>\n",
+       "      <td id=\"T_059fc_row69_col0\" class=\"data row69 col0\" >1566</td>\n",
+       "      <td id=\"T_059fc_row69_col1\" class=\"data row69 col1\" >9.615344</td>\n",
+       "      <td id=\"T_059fc_row69_col2\" class=\"data row69 col2\" >13.929201</td>\n",
+       "      <td id=\"T_059fc_row69_col3\" class=\"data row69 col3\" >4.313857</td>\n",
+       "      <td id=\"T_059fc_row69_col4\" class=\"data row69 col4\" >61</td>\n",
+       "      <td id=\"T_059fc_row69_col5\" class=\"data row69 col5\" >68</td>\n",
+       "      <td id=\"T_059fc_row69_col6\" class=\"data row69 col6\" >-7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row70\" class=\"row_heading level0 row70\" >tulu-2-dpo-13b</th>\n",
+       "      <td id=\"T_059fc_row70_col0\" class=\"data row70 col0\" >1614</td>\n",
+       "      <td id=\"T_059fc_row70_col1\" class=\"data row70 col1\" >10.119788</td>\n",
+       "      <td id=\"T_059fc_row70_col2\" class=\"data row70 col2\" >14.263755</td>\n",
+       "      <td id=\"T_059fc_row70_col3\" class=\"data row70 col3\" >4.143966</td>\n",
+       "      <td id=\"T_059fc_row70_col4\" class=\"data row70 col4\" >59</td>\n",
+       "      <td id=\"T_059fc_row70_col5\" class=\"data row70 col5\" >65</td>\n",
+       "      <td id=\"T_059fc_row70_col6\" class=\"data row70 col6\" >-6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row71\" class=\"row_heading level0 row71\" >claude2-alpaca-13b</th>\n",
+       "      <td id=\"T_059fc_row71_col0\" class=\"data row71 col0\" >1127</td>\n",
+       "      <td id=\"T_059fc_row71_col1\" class=\"data row71 col1\" >7.437351</td>\n",
+       "      <td id=\"T_059fc_row71_col2\" class=\"data row71 col2\" >12.843132</td>\n",
+       "      <td id=\"T_059fc_row71_col3\" class=\"data row71 col3\" >5.405781</td>\n",
+       "      <td id=\"T_059fc_row71_col4\" class=\"data row71 col4\" >83</td>\n",
+       "      <td id=\"T_059fc_row71_col5\" class=\"data row71 col5\" >74</td>\n",
+       "      <td id=\"T_059fc_row71_col6\" class=\"data row71 col6\" >9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row72\" class=\"row_heading level0 row72\" >minotaur-13b</th>\n",
+       "      <td id=\"T_059fc_row72_col0\" class=\"data row72 col0\" >881</td>\n",
+       "      <td id=\"T_059fc_row72_col1\" class=\"data row72 col1\" >5.738964</td>\n",
+       "      <td id=\"T_059fc_row72_col2\" class=\"data row72 col2\" >10.465746</td>\n",
+       "      <td id=\"T_059fc_row72_col3\" class=\"data row72 col3\" >4.726782</td>\n",
+       "      <td id=\"T_059fc_row72_col4\" class=\"data row72 col4\" >100</td>\n",
+       "      <td id=\"T_059fc_row72_col5\" class=\"data row72 col5\" >92</td>\n",
+       "      <td id=\"T_059fc_row72_col6\" class=\"data row72 col6\" >8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row73\" class=\"row_heading level0 row73\" >airoboros-65b</th>\n",
+       "      <td id=\"T_059fc_row73_col0\" class=\"data row73 col0\" >1512</td>\n",
+       "      <td id=\"T_059fc_row73_col1\" class=\"data row73 col1\" >9.388950</td>\n",
+       "      <td id=\"T_059fc_row73_col2\" class=\"data row73 col2\" >13.996237</td>\n",
+       "      <td id=\"T_059fc_row73_col3\" class=\"data row73 col3\" >4.607287</td>\n",
+       "      <td id=\"T_059fc_row73_col4\" class=\"data row73 col4\" >64</td>\n",
+       "      <td id=\"T_059fc_row73_col5\" class=\"data row73 col5\" >67</td>\n",
+       "      <td id=\"T_059fc_row73_col6\" class=\"data row73 col6\" >-3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row74\" class=\"row_heading level0 row74\" >cohere</th>\n",
+       "      <td id=\"T_059fc_row74_col0\" class=\"data row74 col0\" >1983</td>\n",
+       "      <td id=\"T_059fc_row74_col1\" class=\"data row74 col1\" >12.901455</td>\n",
+       "      <td id=\"T_059fc_row74_col2\" class=\"data row74 col2\" >13.751717</td>\n",
+       "      <td id=\"T_059fc_row74_col3\" class=\"data row74 col3\" >0.850262</td>\n",
+       "      <td id=\"T_059fc_row74_col4\" class=\"data row74 col4\" >43</td>\n",
+       "      <td id=\"T_059fc_row74_col5\" class=\"data row74 col5\" >69</td>\n",
+       "      <td id=\"T_059fc_row74_col6\" class=\"data row74 col6\" >-26</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row75\" class=\"row_heading level0 row75\" >vicuna-13b-v1.3</th>\n",
+       "      <td id=\"T_059fc_row75_col0\" class=\"data row75 col0\" >1132</td>\n",
+       "      <td id=\"T_059fc_row75_col1\" class=\"data row75 col1\" >7.137240</td>\n",
+       "      <td id=\"T_059fc_row75_col2\" class=\"data row75 col2\" >12.307993</td>\n",
+       "      <td id=\"T_059fc_row75_col3\" class=\"data row75 col3\" >5.170753</td>\n",
+       "      <td id=\"T_059fc_row75_col4\" class=\"data row75 col4\" >87</td>\n",
+       "      <td id=\"T_059fc_row75_col5\" class=\"data row75 col5\" >75</td>\n",
+       "      <td id=\"T_059fc_row75_col6\" class=\"data row75 col6\" >12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row76\" class=\"row_heading level0 row76\" >xwinlm-7b-v0.1</th>\n",
+       "      <td id=\"T_059fc_row76_col0\" class=\"data row76 col0\" >1894</td>\n",
+       "      <td id=\"T_059fc_row76_col1\" class=\"data row76 col1\" >11.245652</td>\n",
+       "      <td id=\"T_059fc_row76_col2\" class=\"data row76 col2\" >12.974901</td>\n",
+       "      <td id=\"T_059fc_row76_col3\" class=\"data row76 col3\" >1.729250</td>\n",
+       "      <td id=\"T_059fc_row76_col4\" class=\"data row76 col4\" >51</td>\n",
+       "      <td id=\"T_059fc_row76_col5\" class=\"data row76 col5\" >73</td>\n",
+       "      <td id=\"T_059fc_row76_col6\" class=\"data row76 col6\" >-22</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row77\" class=\"row_heading level0 row77\" >airoboros-33b</th>\n",
+       "      <td id=\"T_059fc_row77_col0\" class=\"data row77 col0\" >1514</td>\n",
+       "      <td id=\"T_059fc_row77_col1\" class=\"data row77 col1\" >9.053160</td>\n",
+       "      <td id=\"T_059fc_row77_col2\" class=\"data row77 col2\" >13.481911</td>\n",
+       "      <td id=\"T_059fc_row77_col3\" class=\"data row77 col3\" >4.428750</td>\n",
+       "      <td id=\"T_059fc_row77_col4\" class=\"data row77 col4\" >67</td>\n",
+       "      <td id=\"T_059fc_row77_col5\" class=\"data row77 col5\" >71</td>\n",
+       "      <td id=\"T_059fc_row77_col6\" class=\"data row77 col6\" >-4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row78\" class=\"row_heading level0 row78\" >platolm-7b</th>\n",
+       "      <td id=\"T_059fc_row78_col0\" class=\"data row78 col0\" >1344</td>\n",
+       "      <td id=\"T_059fc_row78_col1\" class=\"data row78 col1\" >6.320828</td>\n",
+       "      <td id=\"T_059fc_row78_col2\" class=\"data row78 col2\" >10.160933</td>\n",
+       "      <td id=\"T_059fc_row78_col3\" class=\"data row78 col3\" >3.840105</td>\n",
+       "      <td id=\"T_059fc_row78_col4\" class=\"data row78 col4\" >93</td>\n",
+       "      <td id=\"T_059fc_row78_col5\" class=\"data row78 col5\" >98</td>\n",
+       "      <td id=\"T_059fc_row78_col6\" class=\"data row78 col6\" >-5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row79\" class=\"row_heading level0 row79\" >vicuna-13b-v1.5</th>\n",
+       "      <td id=\"T_059fc_row79_col0\" class=\"data row79 col0\" >1061</td>\n",
+       "      <td id=\"T_059fc_row79_col1\" class=\"data row79 col1\" >6.722122</td>\n",
+       "      <td id=\"T_059fc_row79_col2\" class=\"data row79 col2\" >11.807463</td>\n",
+       "      <td id=\"T_059fc_row79_col3\" class=\"data row79 col3\" >5.085341</td>\n",
+       "      <td id=\"T_059fc_row79_col4\" class=\"data row79 col4\" >90</td>\n",
+       "      <td id=\"T_059fc_row79_col5\" class=\"data row79 col5\" >80</td>\n",
+       "      <td id=\"T_059fc_row79_col6\" class=\"data row79 col6\" >10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row80\" class=\"row_heading level0 row80\" >gemma-7b-it</th>\n",
+       "      <td id=\"T_059fc_row80_col0\" class=\"data row80 col0\" >1115</td>\n",
+       "      <td id=\"T_059fc_row80_col1\" class=\"data row80 col1\" >6.937294</td>\n",
+       "      <td id=\"T_059fc_row80_col2\" class=\"data row80 col2\" >12.018539</td>\n",
+       "      <td id=\"T_059fc_row80_col3\" class=\"data row80 col3\" >5.081245</td>\n",
+       "      <td id=\"T_059fc_row80_col4\" class=\"data row80 col4\" >88</td>\n",
+       "      <td id=\"T_059fc_row80_col5\" class=\"data row80 col5\" >79</td>\n",
+       "      <td id=\"T_059fc_row80_col6\" class=\"data row80 col6\" >9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row81\" class=\"row_heading level0 row81\" >openchat-v2-13b</th>\n",
+       "      <td id=\"T_059fc_row81_col0\" class=\"data row81 col0\" >1564</td>\n",
+       "      <td id=\"T_059fc_row81_col1\" class=\"data row81 col1\" >8.435076</td>\n",
+       "      <td id=\"T_059fc_row81_col2\" class=\"data row81 col2\" >12.232876</td>\n",
+       "      <td id=\"T_059fc_row81_col3\" class=\"data row81 col3\" >3.797800</td>\n",
+       "      <td id=\"T_059fc_row81_col4\" class=\"data row81 col4\" >71</td>\n",
+       "      <td id=\"T_059fc_row81_col5\" class=\"data row81 col5\" >76</td>\n",
+       "      <td id=\"T_059fc_row81_col6\" class=\"data row81 col6\" >-5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row82\" class=\"row_heading level0 row82\" >zephyr-7b-alpha</th>\n",
+       "      <td id=\"T_059fc_row82_col0\" class=\"data row82 col0\" >1302</td>\n",
+       "      <td id=\"T_059fc_row82_col1\" class=\"data row82 col1\" >8.352664</td>\n",
+       "      <td id=\"T_059fc_row82_col2\" class=\"data row82 col2\" >13.642872</td>\n",
+       "      <td id=\"T_059fc_row82_col3\" class=\"data row82 col3\" >5.290208</td>\n",
+       "      <td id=\"T_059fc_row82_col4\" class=\"data row82 col4\" >72</td>\n",
+       "      <td id=\"T_059fc_row82_col5\" class=\"data row82 col5\" >70</td>\n",
+       "      <td id=\"T_059fc_row82_col6\" class=\"data row82 col6\" >2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row83\" class=\"row_heading level0 row83\" >openbuddy-llama-30b-v7.1</th>\n",
+       "      <td id=\"T_059fc_row83_col0\" class=\"data row83 col0\" >968</td>\n",
+       "      <td id=\"T_059fc_row83_col1\" class=\"data row83 col1\" >6.130015</td>\n",
+       "      <td id=\"T_059fc_row83_col2\" class=\"data row83 col2\" >10.994608</td>\n",
+       "      <td id=\"T_059fc_row83_col3\" class=\"data row83 col3\" >4.864593</td>\n",
+       "      <td id=\"T_059fc_row83_col4\" class=\"data row83 col4\" >96</td>\n",
+       "      <td id=\"T_059fc_row83_col5\" class=\"data row83 col5\" >87</td>\n",
+       "      <td id=\"T_059fc_row83_col6\" class=\"data row83 col6\" >9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row84\" class=\"row_heading level0 row84\" >ultralm-13b-best-of-16</th>\n",
+       "      <td id=\"T_059fc_row84_col0\" class=\"data row84 col0\" >1980</td>\n",
+       "      <td id=\"T_059fc_row84_col1\" class=\"data row84 col1\" >11.307315</td>\n",
+       "      <td id=\"T_059fc_row84_col2\" class=\"data row84 col2\" >12.086284</td>\n",
+       "      <td id=\"T_059fc_row84_col3\" class=\"data row84 col3\" >0.778969</td>\n",
+       "      <td id=\"T_059fc_row84_col4\" class=\"data row84 col4\" >50</td>\n",
+       "      <td id=\"T_059fc_row84_col5\" class=\"data row84 col5\" >78</td>\n",
+       "      <td id=\"T_059fc_row84_col6\" class=\"data row84 col6\" >-28</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row85\" class=\"row_heading level0 row85\" >oasst-sft-llama-33b</th>\n",
+       "      <td id=\"T_059fc_row85_col0\" class=\"data row85 col0\" >748</td>\n",
+       "      <td id=\"T_059fc_row85_col1\" class=\"data row85 col1\" >4.770391</td>\n",
+       "      <td id=\"T_059fc_row85_col2\" class=\"data row85 col2\" >8.882374</td>\n",
+       "      <td id=\"T_059fc_row85_col3\" class=\"data row85 col3\" >4.111983</td>\n",
+       "      <td id=\"T_059fc_row85_col4\" class=\"data row85 col4\" >106</td>\n",
+       "      <td id=\"T_059fc_row85_col5\" class=\"data row85 col5\" >102</td>\n",
+       "      <td id=\"T_059fc_row85_col6\" class=\"data row85 col6\" >4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row86\" class=\"row_heading level0 row86\" >wizardlm-13b</th>\n",
+       "      <td id=\"T_059fc_row86_col0\" class=\"data row86 col0\" >985</td>\n",
+       "      <td id=\"T_059fc_row86_col1\" class=\"data row86 col1\" >5.878153</td>\n",
+       "      <td id=\"T_059fc_row86_col2\" class=\"data row86 col2\" >10.505375</td>\n",
+       "      <td id=\"T_059fc_row86_col3\" class=\"data row86 col3\" >4.627223</td>\n",
+       "      <td id=\"T_059fc_row86_col4\" class=\"data row86 col4\" >98</td>\n",
+       "      <td id=\"T_059fc_row86_col5\" class=\"data row86 col5\" >91</td>\n",
+       "      <td id=\"T_059fc_row86_col6\" class=\"data row86 col6\" >7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row87\" class=\"row_heading level0 row87\" >nous-hermes-13b</th>\n",
+       "      <td id=\"T_059fc_row87_col0\" class=\"data row87 col0\" >844</td>\n",
+       "      <td id=\"T_059fc_row87_col1\" class=\"data row87 col1\" >5.411879</td>\n",
+       "      <td id=\"T_059fc_row87_col2\" class=\"data row87 col2\" >9.931736</td>\n",
+       "      <td id=\"T_059fc_row87_col3\" class=\"data row87 col3\" >4.519857</td>\n",
+       "      <td id=\"T_059fc_row87_col4\" class=\"data row87 col4\" >101</td>\n",
+       "      <td id=\"T_059fc_row87_col5\" class=\"data row87 col5\" >100</td>\n",
+       "      <td id=\"T_059fc_row87_col6\" class=\"data row87 col6\" >1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row88\" class=\"row_heading level0 row88\" >vicuna-13b</th>\n",
+       "      <td id=\"T_059fc_row88_col0\" class=\"data row88 col0\" >1037</td>\n",
+       "      <td id=\"T_059fc_row88_col1\" class=\"data row88 col1\" >5.831103</td>\n",
+       "      <td id=\"T_059fc_row88_col2\" class=\"data row88 col2\" >10.301157</td>\n",
+       "      <td id=\"T_059fc_row88_col3\" class=\"data row88 col3\" >4.470054</td>\n",
+       "      <td id=\"T_059fc_row88_col4\" class=\"data row88 col4\" >99</td>\n",
+       "      <td id=\"T_059fc_row88_col5\" class=\"data row88 col5\" >96</td>\n",
+       "      <td id=\"T_059fc_row88_col6\" class=\"data row88 col6\" >3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row89\" class=\"row_heading level0 row89\" >tulu-2-dpo-7b</th>\n",
+       "      <td id=\"T_059fc_row89_col0\" class=\"data row89 col0\" >1663</td>\n",
+       "      <td id=\"T_059fc_row89_col1\" class=\"data row89 col1\" >8.197515</td>\n",
+       "      <td id=\"T_059fc_row89_col2\" class=\"data row89 col2\" >11.213437</td>\n",
+       "      <td id=\"T_059fc_row89_col3\" class=\"data row89 col3\" >3.015921</td>\n",
+       "      <td id=\"T_059fc_row89_col4\" class=\"data row89 col4\" >73</td>\n",
+       "      <td id=\"T_059fc_row89_col5\" class=\"data row89 col5\" >84</td>\n",
+       "      <td id=\"T_059fc_row89_col6\" class=\"data row89 col6\" >-11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row90\" class=\"row_heading level0 row90\" >openbuddy-llama2-13b-v11.1</th>\n",
+       "      <td id=\"T_059fc_row90_col0\" class=\"data row90 col0\" >1057</td>\n",
+       "      <td id=\"T_059fc_row90_col1\" class=\"data row90 col1\" >6.174716</td>\n",
+       "      <td id=\"T_059fc_row90_col2\" class=\"data row90 col2\" >10.856472</td>\n",
+       "      <td id=\"T_059fc_row90_col3\" class=\"data row90 col3\" >4.681755</td>\n",
+       "      <td id=\"T_059fc_row90_col4\" class=\"data row90 col4\" >95</td>\n",
+       "      <td id=\"T_059fc_row90_col5\" class=\"data row90 col5\" >88</td>\n",
+       "      <td id=\"T_059fc_row90_col6\" class=\"data row90 col6\" >7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row91\" class=\"row_heading level0 row91\" >ultralm-13b-v2.0</th>\n",
+       "      <td id=\"T_059fc_row91_col0\" class=\"data row91 col0\" >1399</td>\n",
+       "      <td id=\"T_059fc_row91_col1\" class=\"data row91 col1\" >7.504623</td>\n",
+       "      <td id=\"T_059fc_row91_col2\" class=\"data row91 col2\" >11.794791</td>\n",
+       "      <td id=\"T_059fc_row91_col3\" class=\"data row91 col3\" >4.290168</td>\n",
+       "      <td id=\"T_059fc_row91_col4\" class=\"data row91 col4\" >80</td>\n",
+       "      <td id=\"T_059fc_row91_col5\" class=\"data row91 col5\" >81</td>\n",
+       "      <td id=\"T_059fc_row91_col6\" class=\"data row91 col6\" >-1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row92\" class=\"row_heading level0 row92\" >text_davinci_001</th>\n",
+       "      <td id=\"T_059fc_row92_col0\" class=\"data row92 col0\" >296</td>\n",
+       "      <td id=\"T_059fc_row92_col1\" class=\"data row92 col1\" >2.764005</td>\n",
+       "      <td id=\"T_059fc_row92_col2\" class=\"data row92 col2\" >5.366913</td>\n",
+       "      <td id=\"T_059fc_row92_col3\" class=\"data row92 col3\" >2.602908</td>\n",
+       "      <td id=\"T_059fc_row92_col4\" class=\"data row92 col4\" >122</td>\n",
+       "      <td id=\"T_059fc_row92_col5\" class=\"data row92 col5\" >120</td>\n",
+       "      <td id=\"T_059fc_row92_col6\" class=\"data row92 col6\" >2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row93\" class=\"row_heading level0 row93\" >openbuddy-falcon-40b-v9</th>\n",
+       "      <td id=\"T_059fc_row93_col0\" class=\"data row93 col0\" >1089</td>\n",
+       "      <td id=\"T_059fc_row93_col1\" class=\"data row93 col1\" >5.955743</td>\n",
+       "      <td id=\"T_059fc_row93_col2\" class=\"data row93 col2\" >10.388464</td>\n",
+       "      <td id=\"T_059fc_row93_col3\" class=\"data row93 col3\" >4.432722</td>\n",
+       "      <td id=\"T_059fc_row93_col4\" class=\"data row93 col4\" >97</td>\n",
+       "      <td id=\"T_059fc_row93_col5\" class=\"data row93 col5\" >94</td>\n",
+       "      <td id=\"T_059fc_row93_col6\" class=\"data row93 col6\" >3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row94\" class=\"row_heading level0 row94\" >openchat-13b</th>\n",
+       "      <td id=\"T_059fc_row94_col0\" class=\"data row94 col0\" >1632</td>\n",
+       "      <td id=\"T_059fc_row94_col1\" class=\"data row94 col1\" >8.022386</td>\n",
+       "      <td id=\"T_059fc_row94_col2\" class=\"data row94 col2\" >11.186416</td>\n",
+       "      <td id=\"T_059fc_row94_col3\" class=\"data row94 col3\" >3.164030</td>\n",
+       "      <td id=\"T_059fc_row94_col4\" class=\"data row94 col4\" >75</td>\n",
+       "      <td id=\"T_059fc_row94_col5\" class=\"data row94 col5\" >85</td>\n",
+       "      <td id=\"T_059fc_row94_col6\" class=\"data row94 col6\" >-10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row95\" class=\"row_heading level0 row95\" >llama-2-13b-chat-hf</th>\n",
+       "      <td id=\"T_059fc_row95_col0\" class=\"data row95 col0\" >1513</td>\n",
+       "      <td id=\"T_059fc_row95_col1\" class=\"data row95 col1\" >7.702310</td>\n",
+       "      <td id=\"T_059fc_row95_col2\" class=\"data row95 col2\" >11.476089</td>\n",
+       "      <td id=\"T_059fc_row95_col3\" class=\"data row95 col3\" >3.773779</td>\n",
+       "      <td id=\"T_059fc_row95_col4\" class=\"data row95 col4\" >78</td>\n",
+       "      <td id=\"T_059fc_row95_col5\" class=\"data row95 col5\" >82</td>\n",
+       "      <td id=\"T_059fc_row95_col6\" class=\"data row95 col6\" >-4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row96\" class=\"row_heading level0 row96\" >guanaco-65b</th>\n",
+       "      <td id=\"T_059fc_row96_col0\" class=\"data row96 col0\" >1249</td>\n",
+       "      <td id=\"T_059fc_row96_col1\" class=\"data row96 col1\" >6.858495</td>\n",
+       "      <td id=\"T_059fc_row96_col2\" class=\"data row96 col2\" >11.412787</td>\n",
+       "      <td id=\"T_059fc_row96_col3\" class=\"data row96 col3\" >4.554293</td>\n",
+       "      <td id=\"T_059fc_row96_col4\" class=\"data row96 col4\" >89</td>\n",
+       "      <td id=\"T_059fc_row96_col5\" class=\"data row96 col5\" >83</td>\n",
+       "      <td id=\"T_059fc_row96_col6\" class=\"data row96 col6\" >6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row97\" class=\"row_heading level0 row97\" >opencoderplus-15b</th>\n",
+       "      <td id=\"T_059fc_row97_col0\" class=\"data row97 col0\" >1628</td>\n",
+       "      <td id=\"T_059fc_row97_col1\" class=\"data row97 col1\" >7.406222</td>\n",
+       "      <td id=\"T_059fc_row97_col2\" class=\"data row97 col2\" >10.352214</td>\n",
+       "      <td id=\"T_059fc_row97_col3\" class=\"data row97 col3\" >2.945992</td>\n",
+       "      <td id=\"T_059fc_row97_col4\" class=\"data row97 col4\" >85</td>\n",
+       "      <td id=\"T_059fc_row97_col5\" class=\"data row97 col5\" >95</td>\n",
+       "      <td id=\"T_059fc_row97_col6\" class=\"data row97 col6\" >-10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row98\" class=\"row_heading level0 row98\" >oasst-rlhf-llama-33b</th>\n",
+       "      <td id=\"T_059fc_row98_col0\" class=\"data row98 col0\" >1079</td>\n",
+       "      <td id=\"T_059fc_row98_col1\" class=\"data row98 col1\" >6.296435</td>\n",
+       "      <td id=\"T_059fc_row98_col2\" class=\"data row98 col2\" >11.010603</td>\n",
+       "      <td id=\"T_059fc_row98_col3\" class=\"data row98 col3\" >4.714168</td>\n",
+       "      <td id=\"T_059fc_row98_col4\" class=\"data row98 col4\" >94</td>\n",
+       "      <td id=\"T_059fc_row98_col5\" class=\"data row98 col5\" >86</td>\n",
+       "      <td id=\"T_059fc_row98_col6\" class=\"data row98 col6\" >8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row99\" class=\"row_heading level0 row99\" >openchat8192-13b</th>\n",
+       "      <td id=\"T_059fc_row99_col0\" class=\"data row99 col0\" >1664</td>\n",
+       "      <td id=\"T_059fc_row99_col1\" class=\"data row99 col1\" >7.472767</td>\n",
+       "      <td id=\"T_059fc_row99_col2\" class=\"data row99 col2\" >10.215584</td>\n",
+       "      <td id=\"T_059fc_row99_col3\" class=\"data row99 col3\" >2.742818</td>\n",
+       "      <td id=\"T_059fc_row99_col4\" class=\"data row99 col4\" >82</td>\n",
+       "      <td id=\"T_059fc_row99_col5\" class=\"data row99 col5\" >97</td>\n",
+       "      <td id=\"T_059fc_row99_col6\" class=\"data row99 col6\" >-15</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row100\" class=\"row_heading level0 row100\" >phi-2-dpo</th>\n",
+       "      <td id=\"T_059fc_row100_col0\" class=\"data row100 col0\" >1687</td>\n",
+       "      <td id=\"T_059fc_row100_col1\" class=\"data row100 col1\" >7.757096</td>\n",
+       "      <td id=\"T_059fc_row100_col2\" class=\"data row100 col2\" >10.448610</td>\n",
+       "      <td id=\"T_059fc_row100_col3\" class=\"data row100 col3\" >2.691514</td>\n",
+       "      <td id=\"T_059fc_row100_col4\" class=\"data row100 col4\" >77</td>\n",
+       "      <td id=\"T_059fc_row100_col5\" class=\"data row100 col5\" >93</td>\n",
+       "      <td id=\"T_059fc_row100_col6\" class=\"data row100 col6\" >-16</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row101\" class=\"row_heading level0 row101\" >minichat-1.5-3b</th>\n",
+       "      <td id=\"T_059fc_row101_col0\" class=\"data row101 col0\" >1545</td>\n",
+       "      <td id=\"T_059fc_row101_col1\" class=\"data row101 col1\" >6.553443</td>\n",
+       "      <td id=\"T_059fc_row101_col2\" class=\"data row101 col2\" >9.602479</td>\n",
+       "      <td id=\"T_059fc_row101_col3\" class=\"data row101 col3\" >3.049036</td>\n",
+       "      <td id=\"T_059fc_row101_col4\" class=\"data row101 col4\" >92</td>\n",
+       "      <td id=\"T_059fc_row101_col5\" class=\"data row101 col5\" >101</td>\n",
+       "      <td id=\"T_059fc_row101_col6\" class=\"data row101 col6\" >-9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row102\" class=\"row_heading level0 row102\" >vicuna-7b-v1.5</th>\n",
+       "      <td id=\"T_059fc_row102_col0\" class=\"data row102 col0\" >1083</td>\n",
+       "      <td id=\"T_059fc_row102_col1\" class=\"data row102 col1\" >4.797494</td>\n",
+       "      <td id=\"T_059fc_row102_col2\" class=\"data row102 col2\" >8.380940</td>\n",
+       "      <td id=\"T_059fc_row102_col3\" class=\"data row102 col3\" >3.583446</td>\n",
+       "      <td id=\"T_059fc_row102_col4\" class=\"data row102 col4\" >105</td>\n",
+       "      <td id=\"T_059fc_row102_col5\" class=\"data row102 col5\" >104</td>\n",
+       "      <td id=\"T_059fc_row102_col6\" class=\"data row102 col6\" >1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row103\" class=\"row_heading level0 row103\" >llama-2-chat-7b-evol70k-neft</th>\n",
+       "      <td id=\"T_059fc_row103_col0\" class=\"data row103 col0\" >1612</td>\n",
+       "      <td id=\"T_059fc_row103_col1\" class=\"data row103 col1\" >7.602384</td>\n",
+       "      <td id=\"T_059fc_row103_col2\" class=\"data row103 col2\" >10.728139</td>\n",
+       "      <td id=\"T_059fc_row103_col3\" class=\"data row103 col3\" >3.125755</td>\n",
+       "      <td id=\"T_059fc_row103_col4\" class=\"data row103 col4\" >79</td>\n",
+       "      <td id=\"T_059fc_row103_col5\" class=\"data row103 col5\" >89</td>\n",
+       "      <td id=\"T_059fc_row103_col6\" class=\"data row103 col6\" >-10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row104\" class=\"row_heading level0 row104\" >recycled-wizardlm-7b-v2.0</th>\n",
+       "      <td id=\"T_059fc_row104_col0\" class=\"data row104 col0\" >1583</td>\n",
+       "      <td id=\"T_059fc_row104_col1\" class=\"data row104 col1\" >7.337129</td>\n",
+       "      <td id=\"T_059fc_row104_col2\" class=\"data row104 col2\" >10.528500</td>\n",
+       "      <td id=\"T_059fc_row104_col3\" class=\"data row104 col3\" >3.191370</td>\n",
+       "      <td id=\"T_059fc_row104_col4\" class=\"data row104 col4\" >86</td>\n",
+       "      <td id=\"T_059fc_row104_col5\" class=\"data row104 col5\" >90</td>\n",
+       "      <td id=\"T_059fc_row104_col6\" class=\"data row104 col6\" >-4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row105\" class=\"row_heading level0 row105\" >vicuna-7b-v1.3</th>\n",
+       "      <td id=\"T_059fc_row105_col0\" class=\"data row105 col0\" >1110</td>\n",
+       "      <td id=\"T_059fc_row105_col1\" class=\"data row105 col1\" >4.642512</td>\n",
+       "      <td id=\"T_059fc_row105_col2\" class=\"data row105 col2\" >8.053655</td>\n",
+       "      <td id=\"T_059fc_row105_col3\" class=\"data row105 col3\" >3.411143</td>\n",
+       "      <td id=\"T_059fc_row105_col4\" class=\"data row105 col4\" >107</td>\n",
+       "      <td id=\"T_059fc_row105_col5\" class=\"data row105 col5\" >107</td>\n",
+       "      <td id=\"T_059fc_row105_col6\" class=\"data row105 col6\" >0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row106\" class=\"row_heading level0 row106\" >alpaca-farm-ppo-sim-gpt4-20k</th>\n",
+       "      <td id=\"T_059fc_row106_col0\" class=\"data row106 col0\" >511</td>\n",
+       "      <td id=\"T_059fc_row106_col1\" class=\"data row106 col1\" >3.450342</td>\n",
+       "      <td id=\"T_059fc_row106_col2\" class=\"data row106 col2\" >6.596308</td>\n",
+       "      <td id=\"T_059fc_row106_col3\" class=\"data row106 col3\" >3.145966</td>\n",
+       "      <td id=\"T_059fc_row106_col4\" class=\"data row106 col4\" >115</td>\n",
+       "      <td id=\"T_059fc_row106_col5\" class=\"data row106 col5\" >113</td>\n",
+       "      <td id=\"T_059fc_row106_col6\" class=\"data row106 col6\" >2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row107\" class=\"row_heading level0 row107\" >ultralm-13b</th>\n",
+       "      <td id=\"T_059fc_row107_col0\" class=\"data row107 col0\" >1087</td>\n",
+       "      <td id=\"T_059fc_row107_col1\" class=\"data row107 col1\" >5.074590</td>\n",
+       "      <td id=\"T_059fc_row107_col2\" class=\"data row107 col2\" >8.856011</td>\n",
+       "      <td id=\"T_059fc_row107_col3\" class=\"data row107 col3\" >3.781421</td>\n",
+       "      <td id=\"T_059fc_row107_col4\" class=\"data row107 col4\" >102</td>\n",
+       "      <td id=\"T_059fc_row107_col5\" class=\"data row107 col5\" >103</td>\n",
+       "      <td id=\"T_059fc_row107_col6\" class=\"data row107 col6\" >-1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row108\" class=\"row_heading level0 row108\" >baize-v2-13b</th>\n",
+       "      <td id=\"T_059fc_row108_col0\" class=\"data row108 col0\" >930</td>\n",
+       "      <td id=\"T_059fc_row108_col1\" class=\"data row108 col1\" >4.590545</td>\n",
+       "      <td id=\"T_059fc_row108_col2\" class=\"data row108 col2\" >8.296129</td>\n",
+       "      <td id=\"T_059fc_row108_col3\" class=\"data row108 col3\" >3.705584</td>\n",
+       "      <td id=\"T_059fc_row108_col4\" class=\"data row108 col4\" >108</td>\n",
+       "      <td id=\"T_059fc_row108_col5\" class=\"data row108 col5\" >105</td>\n",
+       "      <td id=\"T_059fc_row108_col6\" class=\"data row108 col6\" >3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row109\" class=\"row_heading level0 row109\" >recycled-wizardlm-7b-v1.0</th>\n",
+       "      <td id=\"T_059fc_row109_col0\" class=\"data row109 col0\" >1494</td>\n",
+       "      <td id=\"T_059fc_row109_col1\" class=\"data row109 col1\" >6.632750</td>\n",
+       "      <td id=\"T_059fc_row109_col2\" class=\"data row109 col2\" >9.977369</td>\n",
+       "      <td id=\"T_059fc_row109_col3\" class=\"data row109 col3\" >3.344619</td>\n",
+       "      <td id=\"T_059fc_row109_col4\" class=\"data row109 col4\" >91</td>\n",
+       "      <td id=\"T_059fc_row109_col5\" class=\"data row109 col5\" >99</td>\n",
+       "      <td id=\"T_059fc_row109_col6\" class=\"data row109 col6\" >-8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row110\" class=\"row_heading level0 row110\" >alpaca-7b_verbose</th>\n",
+       "      <td id=\"T_059fc_row110_col0\" class=\"data row110 col0\" >537</td>\n",
+       "      <td id=\"T_059fc_row110_col1\" class=\"data row110 col1\" >2.933102</td>\n",
+       "      <td id=\"T_059fc_row110_col2\" class=\"data row110 col2\" >5.594285</td>\n",
+       "      <td id=\"T_059fc_row110_col3\" class=\"data row110 col3\" >2.661184</td>\n",
+       "      <td id=\"T_059fc_row110_col4\" class=\"data row110 col4\" >120</td>\n",
+       "      <td id=\"T_059fc_row110_col5\" class=\"data row110 col5\" >118</td>\n",
+       "      <td id=\"T_059fc_row110_col6\" class=\"data row110 col6\" >2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row111\" class=\"row_heading level0 row111\" >alpaca-farm-ppo-human</th>\n",
+       "      <td id=\"T_059fc_row111_col0\" class=\"data row111 col0\" >803</td>\n",
+       "      <td id=\"T_059fc_row111_col1\" class=\"data row111 col1\" >4.100427</td>\n",
+       "      <td id=\"T_059fc_row111_col2\" class=\"data row111 col2\" >7.574137</td>\n",
+       "      <td id=\"T_059fc_row111_col3\" class=\"data row111 col3\" >3.473710</td>\n",
+       "      <td id=\"T_059fc_row111_col4\" class=\"data row111 col4\" >110</td>\n",
+       "      <td id=\"T_059fc_row111_col5\" class=\"data row111 col5\" >108</td>\n",
+       "      <td id=\"T_059fc_row111_col6\" class=\"data row111 col6\" >2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row112\" class=\"row_heading level0 row112\" >vicuna-7b</th>\n",
+       "      <td id=\"T_059fc_row112_col0\" class=\"data row112 col0\" >1044</td>\n",
+       "      <td id=\"T_059fc_row112_col1\" class=\"data row112 col1\" >4.162611</td>\n",
+       "      <td id=\"T_059fc_row112_col2\" class=\"data row112 col2\" >7.341539</td>\n",
+       "      <td id=\"T_059fc_row112_col3\" class=\"data row112 col3\" >3.178928</td>\n",
+       "      <td id=\"T_059fc_row112_col4\" class=\"data row112 col4\" >109</td>\n",
+       "      <td id=\"T_059fc_row112_col5\" class=\"data row112 col5\" >110</td>\n",
+       "      <td id=\"T_059fc_row112_col6\" class=\"data row112 col6\" >-1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row113\" class=\"row_heading level0 row113\" >alpaca-7b</th>\n",
+       "      <td id=\"T_059fc_row113_col0\" class=\"data row113 col0\" >396</td>\n",
+       "      <td id=\"T_059fc_row113_col1\" class=\"data row113 col1\" >2.591451</td>\n",
+       "      <td id=\"T_059fc_row113_col2\" class=\"data row113 col2\" >4.999603</td>\n",
+       "      <td id=\"T_059fc_row113_col3\" class=\"data row113 col3\" >2.408152</td>\n",
+       "      <td id=\"T_059fc_row113_col4\" class=\"data row113 col4\" >124</td>\n",
+       "      <td id=\"T_059fc_row113_col5\" class=\"data row113 col5\" >121</td>\n",
+       "      <td id=\"T_059fc_row113_col6\" class=\"data row113 col6\" >3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row114\" class=\"row_heading level0 row114\" >phi-2-sft</th>\n",
+       "      <td id=\"T_059fc_row114_col0\" class=\"data row114 col0\" >1068</td>\n",
+       "      <td id=\"T_059fc_row114_col1\" class=\"data row114 col1\" >3.977568</td>\n",
+       "      <td id=\"T_059fc_row114_col2\" class=\"data row114 col2\" >6.974659</td>\n",
+       "      <td id=\"T_059fc_row114_col3\" class=\"data row114 col3\" >2.997091</td>\n",
+       "      <td id=\"T_059fc_row114_col4\" class=\"data row114 col4\" >111</td>\n",
+       "      <td id=\"T_059fc_row114_col5\" class=\"data row114 col5\" >112</td>\n",
+       "      <td id=\"T_059fc_row114_col6\" class=\"data row114 col6\" >-1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row115\" class=\"row_heading level0 row115\" >minichat-3b</th>\n",
+       "      <td id=\"T_059fc_row115_col0\" class=\"data row115 col0\" >868</td>\n",
+       "      <td id=\"T_059fc_row115_col1\" class=\"data row115 col1\" >3.007151</td>\n",
+       "      <td id=\"T_059fc_row115_col2\" class=\"data row115 col2\" >5.496370</td>\n",
+       "      <td id=\"T_059fc_row115_col3\" class=\"data row115 col3\" >2.489219</td>\n",
+       "      <td id=\"T_059fc_row115_col4\" class=\"data row115 col4\" >119</td>\n",
+       "      <td id=\"T_059fc_row115_col5\" class=\"data row115 col5\" >119</td>\n",
+       "      <td id=\"T_059fc_row115_col6\" class=\"data row115 col6\" >0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row116\" class=\"row_heading level0 row116\" >guanaco-33b</th>\n",
+       "      <td id=\"T_059fc_row116_col0\" class=\"data row116 col0\" >1311</td>\n",
+       "      <td id=\"T_059fc_row116_col1\" class=\"data row116 col1\" >5.002494</td>\n",
+       "      <td id=\"T_059fc_row116_col2\" class=\"data row116 col2\" >8.143736</td>\n",
+       "      <td id=\"T_059fc_row116_col3\" class=\"data row116 col3\" >3.141242</td>\n",
+       "      <td id=\"T_059fc_row116_col4\" class=\"data row116 col4\" >103</td>\n",
+       "      <td id=\"T_059fc_row116_col5\" class=\"data row116 col5\" >106</td>\n",
+       "      <td id=\"T_059fc_row116_col6\" class=\"data row116 col6\" >-3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row117\" class=\"row_heading level0 row117\" >falcon-40b-instruct</th>\n",
+       "      <td id=\"T_059fc_row117_col0\" class=\"data row117 col0\" >662</td>\n",
+       "      <td id=\"T_059fc_row117_col1\" class=\"data row117 col1\" >3.342919</td>\n",
+       "      <td id=\"T_059fc_row117_col2\" class=\"data row117 col2\" >6.293075</td>\n",
+       "      <td id=\"T_059fc_row117_col3\" class=\"data row117 col3\" >2.950156</td>\n",
+       "      <td id=\"T_059fc_row117_col4\" class=\"data row117 col4\" >118</td>\n",
+       "      <td id=\"T_059fc_row117_col5\" class=\"data row117 col5\" >114</td>\n",
+       "      <td id=\"T_059fc_row117_col6\" class=\"data row117 col6\" >4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row118\" class=\"row_heading level0 row118\" >gemma-2b-it</th>\n",
+       "      <td id=\"T_059fc_row118_col0\" class=\"data row118 col0\" >1041</td>\n",
+       "      <td id=\"T_059fc_row118_col1\" class=\"data row118 col1\" >3.401971</td>\n",
+       "      <td id=\"T_059fc_row118_col2\" class=\"data row118 col2\" >6.004253</td>\n",
+       "      <td id=\"T_059fc_row118_col3\" class=\"data row118 col3\" >2.602282</td>\n",
+       "      <td id=\"T_059fc_row118_col4\" class=\"data row118 col4\" >117</td>\n",
+       "      <td id=\"T_059fc_row118_col5\" class=\"data row118 col5\" >116</td>\n",
+       "      <td id=\"T_059fc_row118_col6\" class=\"data row118 col6\" >1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row119\" class=\"row_heading level0 row119\" >llama-2-7b-chat-hf</th>\n",
+       "      <td id=\"T_059fc_row119_col0\" class=\"data row119 col0\" >1479</td>\n",
+       "      <td id=\"T_059fc_row119_col1\" class=\"data row119 col1\" >4.961340</td>\n",
+       "      <td id=\"T_059fc_row119_col2\" class=\"data row119 col2\" >7.518212</td>\n",
+       "      <td id=\"T_059fc_row119_col3\" class=\"data row119 col3\" >2.556872</td>\n",
+       "      <td id=\"T_059fc_row119_col4\" class=\"data row119 col4\" >104</td>\n",
+       "      <td id=\"T_059fc_row119_col5\" class=\"data row119 col5\" >109</td>\n",
+       "      <td id=\"T_059fc_row119_col6\" class=\"data row119 col6\" >-5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row120\" class=\"row_heading level0 row120\" >openbuddy-falcon-7b-v6</th>\n",
+       "      <td id=\"T_059fc_row120_col0\" class=\"data row120 col0\" >1152</td>\n",
+       "      <td id=\"T_059fc_row120_col1\" class=\"data row120 col1\" >3.521174</td>\n",
+       "      <td id=\"T_059fc_row120_col2\" class=\"data row120 col2\" >6.038229</td>\n",
+       "      <td id=\"T_059fc_row120_col3\" class=\"data row120 col3\" >2.517055</td>\n",
+       "      <td id=\"T_059fc_row120_col4\" class=\"data row120 col4\" >113</td>\n",
+       "      <td id=\"T_059fc_row120_col5\" class=\"data row120 col5\" >115</td>\n",
+       "      <td id=\"T_059fc_row120_col6\" class=\"data row120 col6\" >-2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row121\" class=\"row_heading level0 row121\" >alpaca-7b_concise</th>\n",
+       "      <td id=\"T_059fc_row121_col0\" class=\"data row121 col0\" >351</td>\n",
+       "      <td id=\"T_059fc_row121_col1\" class=\"data row121 col1\" >1.991176</td>\n",
+       "      <td id=\"T_059fc_row121_col2\" class=\"data row121 col2\" >3.853242</td>\n",
+       "      <td id=\"T_059fc_row121_col3\" class=\"data row121 col3\" >1.862066</td>\n",
+       "      <td id=\"T_059fc_row121_col4\" class=\"data row121 col4\" >129</td>\n",
+       "      <td id=\"T_059fc_row121_col5\" class=\"data row121 col5\" >128</td>\n",
+       "      <td id=\"T_059fc_row121_col6\" class=\"data row121 col6\" >1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row122\" class=\"row_heading level0 row122\" >phi-2</th>\n",
+       "      <td id=\"T_059fc_row122_col0\" class=\"data row122 col0\" >626</td>\n",
+       "      <td id=\"T_059fc_row122_col1\" class=\"data row122 col1\" >2.350210</td>\n",
+       "      <td id=\"T_059fc_row122_col2\" class=\"data row122 col2\" >4.442420</td>\n",
+       "      <td id=\"T_059fc_row122_col3\" class=\"data row122 col3\" >2.092211</td>\n",
+       "      <td id=\"T_059fc_row122_col4\" class=\"data row122 col4\" >126</td>\n",
+       "      <td id=\"T_059fc_row122_col5\" class=\"data row122 col5\" >125</td>\n",
+       "      <td id=\"T_059fc_row122_col6\" class=\"data row122 col6\" >1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row123\" class=\"row_heading level0 row123\" >baize-v2-7b</th>\n",
+       "      <td id=\"T_059fc_row123_col0\" class=\"data row123 col0\" >1127</td>\n",
+       "      <td id=\"T_059fc_row123_col1\" class=\"data row123 col1\" >3.404815</td>\n",
+       "      <td id=\"T_059fc_row123_col2\" class=\"data row123 col2\" >5.879578</td>\n",
+       "      <td id=\"T_059fc_row123_col3\" class=\"data row123 col3\" >2.474763</td>\n",
+       "      <td id=\"T_059fc_row123_col4\" class=\"data row123 col4\" >116</td>\n",
+       "      <td id=\"T_059fc_row123_col5\" class=\"data row123 col5\" >117</td>\n",
+       "      <td id=\"T_059fc_row123_col6\" class=\"data row123 col6\" >-1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row124\" class=\"row_heading level0 row124\" >chatglm2-6b</th>\n",
+       "      <td id=\"T_059fc_row124_col0\" class=\"data row124 col0\" >1027</td>\n",
+       "      <td id=\"T_059fc_row124_col1\" class=\"data row124 col1\" >2.762185</td>\n",
+       "      <td id=\"T_059fc_row124_col2\" class=\"data row124 col2\" >4.890945</td>\n",
+       "      <td id=\"T_059fc_row124_col3\" class=\"data row124 col3\" >2.128760</td>\n",
+       "      <td id=\"T_059fc_row124_col4\" class=\"data row124 col4\" >123</td>\n",
+       "      <td id=\"T_059fc_row124_col5\" class=\"data row124 col5\" >122</td>\n",
+       "      <td id=\"T_059fc_row124_col6\" class=\"data row124 col6\" >1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row125\" class=\"row_heading level0 row125\" >pythia-12b-mix-sft</th>\n",
+       "      <td id=\"T_059fc_row125_col0\" class=\"data row125 col0\" >913</td>\n",
+       "      <td id=\"T_059fc_row125_col1\" class=\"data row125 col1\" >2.578090</td>\n",
+       "      <td id=\"T_059fc_row125_col2\" class=\"data row125 col2\" >4.674240</td>\n",
+       "      <td id=\"T_059fc_row125_col3\" class=\"data row125 col3\" >2.096149</td>\n",
+       "      <td id=\"T_059fc_row125_col4\" class=\"data row125 col4\" >125</td>\n",
+       "      <td id=\"T_059fc_row125_col5\" class=\"data row125 col5\" >123</td>\n",
+       "      <td id=\"T_059fc_row125_col6\" class=\"data row125 col6\" >2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row126\" class=\"row_heading level0 row126\" >falcon-7b-instruct</th>\n",
+       "      <td id=\"T_059fc_row126_col0\" class=\"data row126 col0\" >478</td>\n",
+       "      <td id=\"T_059fc_row126_col1\" class=\"data row126 col1\" >2.146618</td>\n",
+       "      <td id=\"T_059fc_row126_col2\" class=\"data row126 col2\" >4.115462</td>\n",
+       "      <td id=\"T_059fc_row126_col3\" class=\"data row126 col3\" >1.968845</td>\n",
+       "      <td id=\"T_059fc_row126_col4\" class=\"data row126 col4\" >127</td>\n",
+       "      <td id=\"T_059fc_row126_col5\" class=\"data row126 col5\" >127</td>\n",
+       "      <td id=\"T_059fc_row126_col6\" class=\"data row126 col6\" >0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row127\" class=\"row_heading level0 row127\" >oasst-sft-pythia-12b</th>\n",
+       "      <td id=\"T_059fc_row127_col0\" class=\"data row127 col0\" >726</td>\n",
+       "      <td id=\"T_059fc_row127_col1\" class=\"data row127 col1\" >1.790114</td>\n",
+       "      <td id=\"T_059fc_row127_col2\" class=\"data row127 col2\" >3.343088</td>\n",
+       "      <td id=\"T_059fc_row127_col3\" class=\"data row127 col3\" >1.552974</td>\n",
+       "      <td id=\"T_059fc_row127_col4\" class=\"data row127 col4\" >130</td>\n",
+       "      <td id=\"T_059fc_row127_col5\" class=\"data row127 col5\" >129</td>\n",
+       "      <td id=\"T_059fc_row127_col6\" class=\"data row127 col6\" >1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row128\" class=\"row_heading level0 row128\" >guanaco-13b</th>\n",
+       "      <td id=\"T_059fc_row128_col0\" class=\"data row128 col0\" >1774</td>\n",
+       "      <td id=\"T_059fc_row128_col1\" class=\"data row128 col1\" >3.469597</td>\n",
+       "      <td id=\"T_059fc_row128_col2\" class=\"data row128 col2\" >4.400390</td>\n",
+       "      <td id=\"T_059fc_row128_col3\" class=\"data row128 col3\" >0.930793</td>\n",
+       "      <td id=\"T_059fc_row128_col4\" class=\"data row128 col4\" >114</td>\n",
+       "      <td id=\"T_059fc_row128_col5\" class=\"data row128 col5\" >126</td>\n",
+       "      <td id=\"T_059fc_row128_col6\" class=\"data row128 col6\" >-12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row129\" class=\"row_heading level0 row129\" >guanaco-7b</th>\n",
+       "      <td id=\"T_059fc_row129_col0\" class=\"data row129 col0\" >1364</td>\n",
+       "      <td id=\"T_059fc_row129_col1\" class=\"data row129 col1\" >2.880002</td>\n",
+       "      <td id=\"T_059fc_row129_col2\" class=\"data row129 col2\" >4.592913</td>\n",
+       "      <td id=\"T_059fc_row129_col3\" class=\"data row129 col3\" >1.712911</td>\n",
+       "      <td id=\"T_059fc_row129_col4\" class=\"data row129 col4\" >121</td>\n",
+       "      <td id=\"T_059fc_row129_col5\" class=\"data row129 col5\" >124</td>\n",
+       "      <td id=\"T_059fc_row129_col6\" class=\"data row129 col6\" >-3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_059fc_level0_row130\" class=\"row_heading level0 row130\" >baichuan-13b-chat</th>\n",
+       "      <td id=\"T_059fc_row130_col0\" class=\"data row130 col0\" >1727</td>\n",
+       "      <td id=\"T_059fc_row130_col1\" class=\"data row130 col1\" >1.992146</td>\n",
+       "      <td id=\"T_059fc_row130_col2\" class=\"data row130 col2\" >2.612329</td>\n",
+       "      <td id=\"T_059fc_row130_col3\" class=\"data row130 col3\" >0.620183</td>\n",
+       "      <td id=\"T_059fc_row130_col4\" class=\"data row130 col4\" >128</td>\n",
+       "      <td id=\"T_059fc_row130_col5\" class=\"data row130 col5\" >130</td>\n",
+       "      <td id=\"T_059fc_row130_col6\" class=\"data row130 col6\" >-2</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x15f6b84d0>"
+       "<pandas.io.formats.style.Styler at 0x1619e9a50>"
       ]
      },
      "execution_count": 20,
@@ -4110,7 +4158,7 @@
        "</svg>\n"
       ],
       "text/plain": [
-       "<graphviz.graphs.Digraph at 0x15f742710>"
+       "<graphviz.graphs.Digraph at 0x161bcca50>"
       ]
      },
      "metadata": {},
@@ -4299,8 +4347,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 16.3 s, sys: 183 ms, total: 16.4 s\n",
-      "Wall time: 16.4 s\n"
+      "CPU times: user 16.3 s, sys: 199 ms, total: 16.5 s\n",
+      "Wall time: 16.5 s\n"
      ]
     }
    ],
@@ -4330,17 +4378,17 @@
       "\n",
       "## Gameability (lower is better)\n",
       "Verbosity gameability (relative std metric): 6.3%\n",
-      "Conciseness gameability (relative std metric): 13.4%\n",
+      "Conciseness gameability (relative std metric): 13.6%\n",
       "Adversarial winrate gain: 8.5\n",
       "Adversarial rank gain: 45.0\n",
       "\n",
       "## Correlation with Arena (higher is better)\n",
-      "Spearman Corr: 0.971\n",
-      "Kendall Corr: 0.872\n",
+      "Spearman Corr: 0.978\n",
+      "Kendall Corr: 0.893\n",
       "\n",
-      "## Correlation with length (closer to spearman=0.28, kendall=0.19 is better)\n",
-      "Spearman Corr: 0.195\n",
-      "Kendall Corr: 0.127\n",
+      "## Correlation with length (closer to spearman=0.28, kendall=0.20 is better)\n",
+      "Spearman Corr: 0.208\n",
+      "Kendall Corr: 0.141\n",
       "\n",
       "## Top 10 models\n"
      ]
@@ -4350,14 +4398,14 @@
       "text/plain": [
        "gpt4_1106_preview_verbose    51.575008\n",
        "gpt4_1106_preview            50.000000\n",
-       "gpt4_1106_preview_concise    41.896601\n",
+       "gpt4_1106_preview_concise    41.896602\n",
        "claude-3-opus-20240229       40.391776\n",
        "gpt4                         38.128090\n",
        "Qwen1.5-72B-Chat             36.571754\n",
        "gpt4_0314                    35.307061\n",
        "claude-3-sonnet-20240229     34.872474\n",
        "gpt4_0613_verbose            33.821267\n",
-       "claude-2.1_verbose           30.291179\n",
+       "mistral-large-2402           32.652080\n",
        "Name: np.tanh(rand_delta_len_std_only) + instruction_difficulty + not_gamed_baseline.astype(float) - 1, dtype: float64"
       ]
      },
@@ -4430,1608 +4478,1628 @@
      "data": {
       "text/html": [
        "<style type=\"text/css\">\n",
-       "#T_230b2_row0_col3 {\n",
+       "#T_0026f_row0_col3 {\n",
        "  background-color: #a7d0e4;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row0_col6, #T_230b2_row1_col3, #T_230b2_row1_col6, #T_230b2_row21_col6, #T_230b2_row51_col6, #T_230b2_row98_col3, #T_230b2_row102_col3, #T_230b2_row106_col6, #T_230b2_row107_col3, #T_230b2_row123_col6, #T_230b2_row128_col3 {\n",
+       "#T_0026f_row0_col6, #T_0026f_row1_col3, #T_0026f_row1_col6, #T_0026f_row23_col6, #T_0026f_row53_col6, #T_0026f_row100_col3, #T_0026f_row104_col3, #T_0026f_row108_col6, #T_0026f_row109_col3, #T_0026f_row125_col6, #T_0026f_row130_col3 {\n",
        "  background-color: #f7f6f6;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row2_col3, #T_230b2_row65_col6 {\n",
+       "#T_0026f_row2_col3, #T_0026f_row67_col6 {\n",
        "  background-color: #e48066;\n",
        "  color: #f1f1f1;\n",
        "}\n",
-       "#T_230b2_row2_col6, #T_230b2_row32_col3, #T_230b2_row51_col3, #T_230b2_row62_col3, #T_230b2_row77_col6, #T_230b2_row86_col6, #T_230b2_row111_col6 {\n",
-       "  background-color: #fbe6da;\n",
+       "#T_0026f_row2_col6, #T_0026f_row33_col3, #T_0026f_row71_col6, #T_0026f_row75_col6, #T_0026f_row85_col3, #T_0026f_row86_col6 {\n",
+       "  background-color: #fbe4d6;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row3_col3, #T_230b2_row36_col6 {\n",
+       "#T_0026f_row3_col3, #T_0026f_row38_col6 {\n",
        "  background-color: #f8bfa4;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row3_col6, #T_230b2_row66_col3, #T_230b2_row68_col3, #T_230b2_row94_col3, #T_230b2_row100_col6, #T_230b2_row118_col3, #T_230b2_row125_col3, #T_230b2_row125_col6 {\n",
-       "  background-color: #f8f2ef;\n",
+       "#T_0026f_row3_col6, #T_0026f_row65_col6, #T_0026f_row73_col3, #T_0026f_row77_col3, #T_0026f_row91_col3, #T_0026f_row93_col6, #T_0026f_row98_col3, #T_0026f_row115_col6, #T_0026f_row122_col6, #T_0026f_row124_col3, #T_0026f_row125_col3 {\n",
+       "  background-color: #f8f1ed;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row4_col3 {\n",
+       "#T_0026f_row4_col3 {\n",
        "  background-color: #f5a886;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row4_col6, #T_230b2_row18_col6, #T_230b2_row20_col3, #T_230b2_row30_col3, #T_230b2_row39_col6, #T_230b2_row52_col3, #T_230b2_row58_col3, #T_230b2_row100_col3, #T_230b2_row113_col3 {\n",
-       "  background-color: #f9ede5;\n",
+       "#T_0026f_row4_col6, #T_0026f_row28_col6, #T_0026f_row29_col6, #T_0026f_row49_col6, #T_0026f_row50_col3, #T_0026f_row57_col3, #T_0026f_row63_col3, #T_0026f_row80_col3, #T_0026f_row80_col6, #T_0026f_row88_col3, #T_0026f_row113_col3, #T_0026f_row121_col6 {\n",
+       "  background-color: #faeae1;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row5_col3 {\n",
+       "#T_0026f_row5_col3 {\n",
        "  background-color: #facab1;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row5_col6, #T_230b2_row13_col6, #T_230b2_row42_col6, #T_230b2_row54_col3, #T_230b2_row92_col3, #T_230b2_row93_col3, #T_230b2_row95_col3, #T_230b2_row103_col6, #T_230b2_row114_col3 {\n",
-       "  background-color: #f8f4f2;\n",
+       "#T_0026f_row5_col6, #T_0026f_row68_col3, #T_0026f_row70_col3, #T_0026f_row96_col3, #T_0026f_row102_col6, #T_0026f_row120_col3, #T_0026f_row127_col3, #T_0026f_row127_col6 {\n",
+       "  background-color: #f8f2ef;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row6_col3, #T_230b2_row33_col6 {\n",
+       "#T_0026f_row6_col3, #T_0026f_row35_col6 {\n",
        "  background-color: #f6b394;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row6_col6, #T_230b2_row26_col6, #T_230b2_row27_col6, #T_230b2_row47_col6, #T_230b2_row48_col3, #T_230b2_row55_col3, #T_230b2_row61_col3, #T_230b2_row78_col3, #T_230b2_row78_col6, #T_230b2_row86_col3, #T_230b2_row111_col3, #T_230b2_row119_col6 {\n",
-       "  background-color: #faeae1;\n",
+       "#T_0026f_row6_col6, #T_0026f_row16_col6, #T_0026f_row17_col6, #T_0026f_row45_col3, #T_0026f_row65_col3, #T_0026f_row75_col3, #T_0026f_row79_col3, #T_0026f_row106_col3, #T_0026f_row106_col6 {\n",
+       "  background-color: #fae9df;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row7_col3, #T_230b2_row18_col3, #T_230b2_row25_col3, #T_230b2_row28_col3, #T_230b2_row40_col3 {\n",
+       "#T_0026f_row7_col3, #T_0026f_row20_col3, #T_0026f_row27_col3, #T_0026f_row30_col3, #T_0026f_row42_col3 {\n",
        "  background-color: #fbceb7;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row7_col6, #T_230b2_row9_col6, #T_230b2_row38_col3, #T_230b2_row53_col3, #T_230b2_row57_col3, #T_230b2_row97_col3, #T_230b2_row115_col6, #T_230b2_row117_col3, #T_230b2_row124_col6 {\n",
-       "  background-color: #f7f5f4;\n",
+       "#T_0026f_row7_col6, #T_0026f_row44_col6, #T_0026f_row56_col3, #T_0026f_row94_col3, #T_0026f_row95_col3, #T_0026f_row97_col3, #T_0026f_row105_col6, #T_0026f_row116_col3 {\n",
+       "  background-color: #f8f4f2;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row8_col3, #T_230b2_row49_col6 {\n",
+       "#T_0026f_row8_col3, #T_0026f_row51_col6 {\n",
        "  background-color: #f9c6ac;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row8_col6, #T_230b2_row63_col6, #T_230b2_row71_col3, #T_230b2_row75_col3, #T_230b2_row89_col3, #T_230b2_row91_col6, #T_230b2_row96_col3, #T_230b2_row113_col6, #T_230b2_row120_col6, #T_230b2_row122_col3, #T_230b2_row123_col3 {\n",
-       "  background-color: #f8f1ed;\n",
+       "#T_0026f_row8_col6, #T_0026f_row61_col3, #T_0026f_row90_col6, #T_0026f_row111_col3, #T_0026f_row112_col3, #T_0026f_row117_col3, #T_0026f_row118_col3 {\n",
+       "  background-color: #f9efe9;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row9_col3, #T_230b2_row46_col3 {\n",
+       "#T_0026f_row9_col3 {\n",
+       "  background-color: #f9c2a7;\n",
+       "  color: #000000;\n",
+       "}\n",
+       "#T_0026f_row9_col6, #T_0026f_row21_col6, #T_0026f_row48_col6, #T_0026f_row64_col6, #T_0026f_row78_col3, #T_0026f_row87_col3, #T_0026f_row110_col6 {\n",
+       "  background-color: #fae7dc;\n",
+       "  color: #000000;\n",
+       "}\n",
+       "#T_0026f_row10_col3, #T_0026f_row48_col3 {\n",
        "  background-color: #fce0d0;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row10_col3 {\n",
+       "#T_0026f_row10_col6, #T_0026f_row15_col6, #T_0026f_row40_col3, #T_0026f_row55_col3, #T_0026f_row59_col3, #T_0026f_row99_col3, #T_0026f_row117_col6, #T_0026f_row119_col3, #T_0026f_row126_col6 {\n",
+       "  background-color: #f7f5f4;\n",
+       "  color: #000000;\n",
+       "}\n",
+       "#T_0026f_row11_col3 {\n",
        "  background-color: #f5aa89;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row10_col6 {\n",
-       "  background-color: #fddbc7;\n",
+       "#T_0026f_row11_col6, #T_0026f_row29_col3, #T_0026f_row51_col3 {\n",
+       "  background-color: #fcd7c2;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row11_col3 {\n",
+       "#T_0026f_row12_col3 {\n",
        "  background-color: #deebf2;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row11_col6, #T_230b2_row12_col6, #T_230b2_row17_col3, #T_230b2_row41_col6, #T_230b2_row56_col6, #T_230b2_row71_col6, #T_230b2_row99_col6 {\n",
-       "  background-color: #e4eef4;\n",
+       "#T_0026f_row12_col6, #T_0026f_row13_col6, #T_0026f_row14_col6, #T_0026f_row54_col6, #T_0026f_row77_col6, #T_0026f_row81_col6, #T_0026f_row82_col6 {\n",
+       "  background-color: #e1edf3;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row12_col3, #T_230b2_row16_col3, #T_230b2_row32_col6, #T_230b2_row59_col6 {\n",
+       "#T_0026f_row13_col3, #T_0026f_row60_col6, #T_0026f_row69_col6, #T_0026f_row129_col6 {\n",
+       "  background-color: #e6eff4;\n",
+       "  color: #000000;\n",
+       "}\n",
+       "#T_0026f_row14_col3, #T_0026f_row18_col3, #T_0026f_row34_col6, #T_0026f_row61_col6 {\n",
        "  background-color: #eaf1f5;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row13_col3 {\n",
+       "#T_0026f_row15_col3 {\n",
        "  background-color: #fcdecd;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row14_col3 {\n",
+       "#T_0026f_row16_col3 {\n",
        "  background-color: #f9c4a9;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row14_col6, #T_230b2_row15_col6, #T_230b2_row43_col3, #T_230b2_row63_col3, #T_230b2_row73_col3, #T_230b2_row77_col3, #T_230b2_row104_col3, #T_230b2_row104_col6 {\n",
-       "  background-color: #fae9df;\n",
+       "#T_0026f_row17_col3, #T_0026f_row35_col3 {\n",
+       "  background-color: #fac8af;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row15_col3, #T_230b2_row33_col3 {\n",
-       "  background-color: #fac8af;\n",
+       "#T_0026f_row18_col6, #T_0026f_row68_col6, #T_0026f_row97_col6 {\n",
+       "  background-color: #ddebf2;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row16_col6, #T_230b2_row30_col6, #T_230b2_row68_col6, #T_230b2_row89_col6 {\n",
-       "  background-color: #e0ecf3;\n",
+       "#T_0026f_row19_col3, #T_0026f_row43_col6, #T_0026f_row58_col6, #T_0026f_row73_col6, #T_0026f_row101_col6 {\n",
+       "  background-color: #e4eef4;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row17_col6, #T_230b2_row44_col6, #T_230b2_row114_col6 {\n",
-       "  background-color: #dbeaf2;\n",
+       "#T_0026f_row19_col6, #T_0026f_row128_col6 {\n",
+       "  background-color: #dae9f2;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row19_col3 {\n",
-       "  background-color: #fbccb4;\n",
+       "#T_0026f_row20_col6, #T_0026f_row22_col3, #T_0026f_row32_col3, #T_0026f_row41_col6, #T_0026f_row54_col3, #T_0026f_row60_col3, #T_0026f_row102_col3, #T_0026f_row115_col3 {\n",
+       "  background-color: #f9ede5;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row19_col6, #T_230b2_row46_col6, #T_230b2_row62_col6, #T_230b2_row76_col3, #T_230b2_row85_col3, #T_230b2_row108_col6 {\n",
-       "  background-color: #fae7dc;\n",
+       "#T_0026f_row21_col3 {\n",
+       "  background-color: #fbccb4;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row20_col6, #T_230b2_row31_col6, #T_230b2_row96_col6 {\n",
-       "  background-color: #eff3f5;\n",
+       "#T_0026f_row22_col6, #T_0026f_row25_col6, #T_0026f_row45_col6, #T_0026f_row107_col6 {\n",
+       "  background-color: #ecf2f5;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row21_col3, #T_230b2_row28_col6, #T_230b2_row64_col6, #T_230b2_row76_col6, #T_230b2_row90_col3 {\n",
+       "#T_0026f_row23_col3, #T_0026f_row30_col6, #T_0026f_row66_col6, #T_0026f_row78_col6, #T_0026f_row92_col3 {\n",
        "  background-color: #fcdfcf;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row22_col3, #T_230b2_row81_col6 {\n",
+       "#T_0026f_row24_col3, #T_0026f_row83_col6 {\n",
        "  background-color: #fbe3d4;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row22_col6, #T_230b2_row128_col6 {\n",
+       "#T_0026f_row24_col6, #T_0026f_row130_col6 {\n",
        "  background-color: #f3f5f6;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row23_col3, #T_230b2_row34_col6, #T_230b2_row44_col3, #T_230b2_row56_col3, #T_230b2_row60_col6, #T_230b2_row67_col3, #T_230b2_row103_col3, #T_230b2_row106_col3, #T_230b2_row119_col3 {\n",
+       "#T_0026f_row25_col3, #T_0026f_row36_col6, #T_0026f_row46_col3, #T_0026f_row58_col3, #T_0026f_row62_col6, #T_0026f_row69_col3, #T_0026f_row105_col3, #T_0026f_row108_col3, #T_0026f_row121_col3 {\n",
        "  background-color: #f9eee7;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row23_col6, #T_230b2_row43_col6, #T_230b2_row105_col6 {\n",
-       "  background-color: #ecf2f5;\n",
-       "  color: #000000;\n",
-       "}\n",
-       "#T_230b2_row24_col3, #T_230b2_row48_col6, #T_230b2_row55_col6, #T_230b2_row82_col3, #T_230b2_row110_col6, #T_230b2_row112_col6 {\n",
+       "#T_0026f_row26_col3, #T_0026f_row50_col6, #T_0026f_row57_col6, #T_0026f_row84_col3, #T_0026f_row112_col6, #T_0026f_row114_col6 {\n",
        "  background-color: #f0f4f6;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row24_col6, #T_230b2_row45_col6, #T_230b2_row117_col6 {\n",
-       "  background-color: #d7e8f1;\n",
+       "#T_0026f_row26_col6, #T_0026f_row40_col6, #T_0026f_row89_col6 {\n",
+       "  background-color: #d5e7f1;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row25_col6, #T_230b2_row34_col3, #T_230b2_row39_col3, #T_230b2_row47_col3, #T_230b2_row70_col3, #T_230b2_row85_col6 {\n",
+       "#T_0026f_row27_col6, #T_0026f_row36_col3, #T_0026f_row41_col3, #T_0026f_row49_col3, #T_0026f_row72_col3, #T_0026f_row87_col6 {\n",
        "  background-color: #fce2d2;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row26_col3, #T_230b2_row37_col3, #T_230b2_row50_col3, #T_230b2_row65_col3 {\n",
+       "#T_0026f_row28_col3, #T_0026f_row39_col3, #T_0026f_row52_col3, #T_0026f_row67_col3 {\n",
        "  background-color: #fcd5bf;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row27_col3, #T_230b2_row49_col3 {\n",
-       "  background-color: #fcd7c2;\n",
-       "  color: #000000;\n",
-       "}\n",
-       "#T_230b2_row29_col3 {\n",
+       "#T_0026f_row31_col3 {\n",
        "  background-color: #f7b99c;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row29_col6, #T_230b2_row50_col6 {\n",
+       "#T_0026f_row31_col6, #T_0026f_row52_col6 {\n",
        "  background-color: #f6b191;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row31_col3, #T_230b2_row69_col6, #T_230b2_row73_col6, #T_230b2_row83_col3, #T_230b2_row84_col6 {\n",
-       "  background-color: #fbe4d6;\n",
+       "#T_0026f_row32_col6, #T_0026f_row70_col6, #T_0026f_row91_col6 {\n",
+       "  background-color: #e0ecf3;\n",
+       "  color: #000000;\n",
+       "}\n",
+       "#T_0026f_row33_col6, #T_0026f_row98_col6 {\n",
+       "  background-color: #eff3f5;\n",
+       "  color: #000000;\n",
+       "}\n",
+       "#T_0026f_row34_col3, #T_0026f_row53_col3, #T_0026f_row64_col3, #T_0026f_row79_col6, #T_0026f_row88_col6, #T_0026f_row113_col6 {\n",
+       "  background-color: #fbe6da;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row35_col3 {\n",
+       "#T_0026f_row37_col3 {\n",
        "  background-color: #e7f0f4;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row35_col6, #T_230b2_row54_col6, #T_230b2_row102_col6, #T_230b2_row107_col6 {\n",
-       "  background-color: #d1e5f0;\n",
+       "#T_0026f_row37_col6, #T_0026f_row94_col6 {\n",
+       "  background-color: #cce2ef;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row36_col3 {\n",
+       "#T_0026f_row38_col3 {\n",
        "  background-color: #fbd0b9;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row37_col6, #T_230b2_row83_col6 {\n",
+       "#T_0026f_row39_col6, #T_0026f_row85_col6 {\n",
        "  background-color: #fcd3bc;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row38_col6, #T_230b2_row87_col6 {\n",
-       "  background-color: #d5e7f1;\n",
-       "  color: #000000;\n",
-       "}\n",
-       "#T_230b2_row40_col6, #T_230b2_row70_col6 {\n",
+       "#T_0026f_row42_col6, #T_0026f_row72_col6 {\n",
        "  background-color: #f8bda1;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row41_col3, #T_230b2_row88_col3, #T_230b2_row91_col3 {\n",
+       "#T_0026f_row43_col3, #T_0026f_row90_col3, #T_0026f_row93_col3 {\n",
        "  background-color: #f9ebe3;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row42_col3, #T_230b2_row64_col3 {\n",
+       "#T_0026f_row44_col3, #T_0026f_row66_col3 {\n",
        "  background-color: #fbe5d8;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row45_col3, #T_230b2_row87_col3, #T_230b2_row99_col3, #T_230b2_row121_col3 {\n",
-       "  background-color: #f8f3f0;\n",
+       "#T_0026f_row46_col6, #T_0026f_row116_col6 {\n",
+       "  background-color: #dbeaf2;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row52_col6, #T_230b2_row75_col6, #T_230b2_row79_col6, #T_230b2_row80_col6 {\n",
-       "  background-color: #e1edf3;\n",
+       "#T_0026f_row47_col3, #T_0026f_row89_col3, #T_0026f_row101_col3, #T_0026f_row123_col3 {\n",
+       "  background-color: #f8f3f0;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row53_col6, #T_230b2_row57_col6 {\n",
-       "  background-color: #cae1ee;\n",
+       "#T_0026f_row47_col6, #T_0026f_row119_col6 {\n",
+       "  background-color: #d7e8f1;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row58_col6, #T_230b2_row67_col6, #T_230b2_row127_col6 {\n",
-       "  background-color: #e6eff4;\n",
+       "#T_0026f_row55_col6, #T_0026f_row59_col6 {\n",
+       "  background-color: #cae1ee;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row59_col3, #T_230b2_row88_col6, #T_230b2_row109_col3, #T_230b2_row110_col3, #T_230b2_row115_col3, #T_230b2_row116_col3 {\n",
-       "  background-color: #f9efe9;\n",
+       "#T_0026f_row56_col6, #T_0026f_row104_col6, #T_0026f_row109_col6 {\n",
+       "  background-color: #d1e5f0;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row60_col3, #T_230b2_row69_col3, #T_230b2_row81_col3, #T_230b2_row84_col3, #T_230b2_row108_col3 {\n",
+       "#T_0026f_row62_col3, #T_0026f_row71_col3, #T_0026f_row83_col3, #T_0026f_row86_col3, #T_0026f_row110_col3 {\n",
        "  background-color: #fae8de;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row61_col6, #T_230b2_row74_col3, #T_230b2_row109_col6, #T_230b2_row116_col6, #T_230b2_row122_col6, #T_230b2_row126_col3 {\n",
+       "#T_0026f_row63_col6, #T_0026f_row76_col3, #T_0026f_row111_col6, #T_0026f_row118_col6, #T_0026f_row124_col6, #T_0026f_row128_col3 {\n",
        "  background-color: #f5f6f7;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row66_col6, #T_230b2_row95_col6 {\n",
-       "  background-color: #ddebf2;\n",
-       "  color: #000000;\n",
-       "}\n",
-       "#T_230b2_row72_col3 {\n",
+       "#T_0026f_row74_col3 {\n",
        "  background-color: #edf2f5;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row72_col6 {\n",
+       "#T_0026f_row74_col6 {\n",
        "  background-color: #a2cde3;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row74_col6 {\n",
+       "#T_0026f_row76_col6 {\n",
        "  background-color: #b8d8e9;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row79_col3, #T_230b2_row80_col3, #T_230b2_row105_col3, #T_230b2_row112_col3, #T_230b2_row120_col3, #T_230b2_row124_col3 {\n",
+       "#T_0026f_row81_col3, #T_0026f_row82_col3, #T_0026f_row107_col3, #T_0026f_row114_col3, #T_0026f_row122_col3, #T_0026f_row126_col3 {\n",
        "  background-color: #f9f0eb;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row82_col6 {\n",
+       "#T_0026f_row84_col6 {\n",
        "  background-color: #98c8e0;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row90_col6 {\n",
+       "#T_0026f_row92_col6 {\n",
        "  background-color: #f7b799;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row92_col6 {\n",
-       "  background-color: #cce2ef;\n",
-       "  color: #000000;\n",
-       "}\n",
-       "#T_230b2_row93_col6, #T_230b2_row97_col6 {\n",
+       "#T_0026f_row95_col6, #T_0026f_row99_col6 {\n",
        "  background-color: #d2e6f0;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row94_col6, #T_230b2_row118_col6, #T_230b2_row121_col6 {\n",
+       "#T_0026f_row96_col6, #T_0026f_row120_col6, #T_0026f_row123_col6 {\n",
        "  background-color: #e9f0f4;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row98_col6 {\n",
+       "#T_0026f_row100_col6 {\n",
        "  background-color: #c0dceb;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row101_col3, #T_230b2_row127_col3 {\n",
+       "#T_0026f_row103_col3, #T_0026f_row129_col3 {\n",
        "  background-color: #f6f7f7;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row101_col6 {\n",
+       "#T_0026f_row103_col6 {\n",
        "  background-color: #bbdaea;\n",
        "  color: #000000;\n",
        "}\n",
-       "#T_230b2_row126_col6 {\n",
-       "  background-color: #dae9f2;\n",
-       "  color: #000000;\n",
-       "}\n",
        "</style>\n",
-       "<table id=\"T_230b2\">\n",
+       "<table id=\"T_0026f\">\n",
        "  <thead>\n",
        "    <tr>\n",
        "      <th class=\"blank level0\" >&nbsp;</th>\n",
-       "      <th id=\"T_230b2_level0_col0\" class=\"col_heading level0 col0\" >avg_length</th>\n",
-       "      <th id=\"T_230b2_level0_col1\" class=\"col_heading level0 col1\" >win_rate</th>\n",
-       "      <th id=\"T_230b2_level0_col2\" class=\"col_heading level0 col2\" >new_win_rate</th>\n",
-       "      <th id=\"T_230b2_level0_col3\" class=\"col_heading level0 col3\" >delta_win_rate</th>\n",
-       "      <th id=\"T_230b2_level0_col4\" class=\"col_heading level0 col4\" >rank_win_rate</th>\n",
-       "      <th id=\"T_230b2_level0_col5\" class=\"col_heading level0 col5\" >rank_new_win_rate</th>\n",
-       "      <th id=\"T_230b2_level0_col6\" class=\"col_heading level0 col6\" >delta_rank</th>\n",
+       "      <th id=\"T_0026f_level0_col0\" class=\"col_heading level0 col0\" >avg_length</th>\n",
+       "      <th id=\"T_0026f_level0_col1\" class=\"col_heading level0 col1\" >win_rate</th>\n",
+       "      <th id=\"T_0026f_level0_col2\" class=\"col_heading level0 col2\" >new_win_rate</th>\n",
+       "      <th id=\"T_0026f_level0_col3\" class=\"col_heading level0 col3\" >delta_win_rate</th>\n",
+       "      <th id=\"T_0026f_level0_col4\" class=\"col_heading level0 col4\" >rank_win_rate</th>\n",
+       "      <th id=\"T_0026f_level0_col5\" class=\"col_heading level0 col5\" >rank_new_win_rate</th>\n",
+       "      <th id=\"T_0026f_level0_col6\" class=\"col_heading level0 col6\" >delta_rank</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row0\" class=\"row_heading level0 row0\" >gpt4_1106_preview_verbose</th>\n",
-       "      <td id=\"T_230b2_row0_col0\" class=\"data row0 col0\" >2402</td>\n",
-       "      <td id=\"T_230b2_row0_col1\" class=\"data row0 col1\" >64.303601</td>\n",
-       "      <td id=\"T_230b2_row0_col2\" class=\"data row0 col2\" >51.575008</td>\n",
-       "      <td id=\"T_230b2_row0_col3\" class=\"data row0 col3\" >-12.728593</td>\n",
-       "      <td id=\"T_230b2_row0_col4\" class=\"data row0 col4\" >0</td>\n",
-       "      <td id=\"T_230b2_row0_col5\" class=\"data row0 col5\" >0</td>\n",
-       "      <td id=\"T_230b2_row0_col6\" class=\"data row0 col6\" >0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row1\" class=\"row_heading level0 row1\" >gpt4_1106_preview</th>\n",
-       "      <td id=\"T_230b2_row1_col0\" class=\"data row1 col0\" >2049</td>\n",
-       "      <td id=\"T_230b2_row1_col1\" class=\"data row1 col1\" >50.000000</td>\n",
-       "      <td id=\"T_230b2_row1_col2\" class=\"data row1 col2\" >50.000000</td>\n",
-       "      <td id=\"T_230b2_row1_col3\" class=\"data row1 col3\" >0.000000</td>\n",
-       "      <td id=\"T_230b2_row1_col4\" class=\"data row1 col4\" >1</td>\n",
-       "      <td id=\"T_230b2_row1_col5\" class=\"data row1 col5\" >1</td>\n",
-       "      <td id=\"T_230b2_row1_col6\" class=\"data row1 col6\" >0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row2\" class=\"row_heading level0 row2\" >gpt4_1106_preview_concise</th>\n",
-       "      <td id=\"T_230b2_row2_col0\" class=\"data row2 col0\" >1136</td>\n",
-       "      <td id=\"T_230b2_row2_col1\" class=\"data row2 col1\" >22.920194</td>\n",
-       "      <td id=\"T_230b2_row2_col2\" class=\"data row2 col2\" >41.896601</td>\n",
-       "      <td id=\"T_230b2_row2_col3\" class=\"data row2 col3\" >18.976407</td>\n",
-       "      <td id=\"T_230b2_row2_col4\" class=\"data row2 col4\" >13</td>\n",
-       "      <td id=\"T_230b2_row2_col5\" class=\"data row2 col5\" >2</td>\n",
-       "      <td id=\"T_230b2_row2_col6\" class=\"data row2 col6\" >11</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row3\" class=\"row_heading level0 row3\" >claude-3-opus-20240229</th>\n",
-       "      <td id=\"T_230b2_row3_col0\" class=\"data row3 col0\" >1388</td>\n",
-       "      <td id=\"T_230b2_row3_col1\" class=\"data row3 col1\" >29.041764</td>\n",
-       "      <td id=\"T_230b2_row3_col2\" class=\"data row3 col2\" >40.391776</td>\n",
-       "      <td id=\"T_230b2_row3_col3\" class=\"data row3 col3\" >11.350012</td>\n",
-       "      <td id=\"T_230b2_row3_col4\" class=\"data row3 col4\" >6</td>\n",
-       "      <td id=\"T_230b2_row3_col5\" class=\"data row3 col5\" >3</td>\n",
-       "      <td id=\"T_230b2_row3_col6\" class=\"data row3 col6\" >3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row4\" class=\"row_heading level0 row4\" >gpt4</th>\n",
-       "      <td id=\"T_230b2_row4_col0\" class=\"data row4 col0\" >1365</td>\n",
-       "      <td id=\"T_230b2_row4_col1\" class=\"data row4 col1\" >23.576789</td>\n",
-       "      <td id=\"T_230b2_row4_col2\" class=\"data row4 col2\" >38.128090</td>\n",
-       "      <td id=\"T_230b2_row4_col3\" class=\"data row4 col3\" >14.551300</td>\n",
-       "      <td id=\"T_230b2_row4_col4\" class=\"data row4 col4\" >11</td>\n",
-       "      <td id=\"T_230b2_row4_col5\" class=\"data row4 col5\" >4</td>\n",
-       "      <td id=\"T_230b2_row4_col6\" class=\"data row4 col6\" >7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row5\" class=\"row_heading level0 row5\" >Qwen1.5-72B-Chat</th>\n",
-       "      <td id=\"T_230b2_row5_col0\" class=\"data row5 col0\" >1549</td>\n",
-       "      <td id=\"T_230b2_row5_col1\" class=\"data row5 col1\" >26.498283</td>\n",
-       "      <td id=\"T_230b2_row5_col2\" class=\"data row5 col2\" >36.571754</td>\n",
-       "      <td id=\"T_230b2_row5_col3\" class=\"data row5 col3\" >10.073471</td>\n",
-       "      <td id=\"T_230b2_row5_col4\" class=\"data row5 col4\" >7</td>\n",
-       "      <td id=\"T_230b2_row5_col5\" class=\"data row5 col5\" >5</td>\n",
-       "      <td id=\"T_230b2_row5_col6\" class=\"data row5 col6\" >2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row6\" class=\"row_heading level0 row6\" >gpt4_0314</th>\n",
-       "      <td id=\"T_230b2_row6_col0\" class=\"data row6 col0\" >1371</td>\n",
-       "      <td id=\"T_230b2_row6_col1\" class=\"data row6 col1\" >22.073259</td>\n",
-       "      <td id=\"T_230b2_row6_col2\" class=\"data row6 col2\" >35.307061</td>\n",
-       "      <td id=\"T_230b2_row6_col3\" class=\"data row6 col3\" >13.233802</td>\n",
-       "      <td id=\"T_230b2_row6_col4\" class=\"data row6 col4\" >14</td>\n",
-       "      <td id=\"T_230b2_row6_col5\" class=\"data row6 col5\" >6</td>\n",
-       "      <td id=\"T_230b2_row6_col6\" class=\"data row6 col6\" >8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row7\" class=\"row_heading level0 row7\" >claude-3-sonnet-20240229</th>\n",
-       "      <td id=\"T_230b2_row7_col0\" class=\"data row7 col0\" >1420</td>\n",
-       "      <td id=\"T_230b2_row7_col1\" class=\"data row7 col1\" >25.556325</td>\n",
-       "      <td id=\"T_230b2_row7_col2\" class=\"data row7 col2\" >34.872474</td>\n",
-       "      <td id=\"T_230b2_row7_col3\" class=\"data row7 col3\" >9.316149</td>\n",
-       "      <td id=\"T_230b2_row7_col4\" class=\"data row7 col4\" >8</td>\n",
-       "      <td id=\"T_230b2_row7_col5\" class=\"data row7 col5\" >7</td>\n",
-       "      <td id=\"T_230b2_row7_col6\" class=\"data row7 col6\" >1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row8\" class=\"row_heading level0 row8\" >gpt4_0613_verbose</th>\n",
-       "      <td id=\"T_230b2_row8_col0\" class=\"data row8 col0\" >1473</td>\n",
-       "      <td id=\"T_230b2_row8_col1\" class=\"data row8 col1\" >23.237360</td>\n",
-       "      <td id=\"T_230b2_row8_col2\" class=\"data row8 col2\" >33.821267</td>\n",
-       "      <td id=\"T_230b2_row8_col3\" class=\"data row8 col3\" >10.583907</td>\n",
-       "      <td id=\"T_230b2_row8_col4\" class=\"data row8 col4\" >12</td>\n",
-       "      <td id=\"T_230b2_row8_col5\" class=\"data row8 col5\" >8</td>\n",
-       "      <td id=\"T_230b2_row8_col6\" class=\"data row8 col6\" >4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row9\" class=\"row_heading level0 row9\" >claude-2.1_verbose</th>\n",
-       "      <td id=\"T_230b2_row9_col0\" class=\"data row9 col0\" >1414</td>\n",
-       "      <td id=\"T_230b2_row9_col1\" class=\"data row9 col1\" >24.354071</td>\n",
-       "      <td id=\"T_230b2_row9_col2\" class=\"data row9 col2\" >30.291179</td>\n",
-       "      <td id=\"T_230b2_row9_col3\" class=\"data row9 col3\" >5.937108</td>\n",
-       "      <td id=\"T_230b2_row9_col4\" class=\"data row9 col4\" >10</td>\n",
-       "      <td id=\"T_230b2_row9_col5\" class=\"data row9 col5\" >9</td>\n",
-       "      <td id=\"T_230b2_row9_col6\" class=\"data row9 col6\" >1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row10\" class=\"row_heading level0 row10\" >gpt4_0613</th>\n",
-       "      <td id=\"T_230b2_row10_col0\" class=\"data row10 col0\" >1140</td>\n",
-       "      <td id=\"T_230b2_row10_col1\" class=\"data row10 col1\" >15.755038</td>\n",
-       "      <td id=\"T_230b2_row10_col2\" class=\"data row10 col2\" >30.183322</td>\n",
-       "      <td id=\"T_230b2_row10_col3\" class=\"data row10 col3\" >14.428284</td>\n",
-       "      <td id=\"T_230b2_row10_col4\" class=\"data row10 col4\" >28</td>\n",
-       "      <td id=\"T_230b2_row10_col5\" class=\"data row10 col5\" >10</td>\n",
-       "      <td id=\"T_230b2_row10_col6\" class=\"data row10 col6\" >18</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row11\" class=\"row_heading level0 row11\" >Snorkel-Mistral-PairRM-DPO-best-of-16</th>\n",
-       "      <td id=\"T_230b2_row11_col0\" class=\"data row11 col0\" >2616</td>\n",
-       "      <td id=\"T_230b2_row11_col1\" class=\"data row11 col1\" >34.860133</td>\n",
-       "      <td id=\"T_230b2_row11_col2\" class=\"data row11 col2\" >29.974322</td>\n",
-       "      <td id=\"T_230b2_row11_col3\" class=\"data row11 col3\" >-4.885811</td>\n",
-       "      <td id=\"T_230b2_row11_col4\" class=\"data row11 col4\" >2</td>\n",
-       "      <td id=\"T_230b2_row11_col5\" class=\"data row11 col5\" >11</td>\n",
-       "      <td id=\"T_230b2_row11_col6\" class=\"data row11 col6\" >-9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row12\" class=\"row_heading level0 row12\" >pairrm-Yi-34B-Chat</th>\n",
-       "      <td id=\"T_230b2_row12_col0\" class=\"data row12 col0\" >2195</td>\n",
-       "      <td id=\"T_230b2_row12_col1\" class=\"data row12 col1\" >31.241283</td>\n",
-       "      <td id=\"T_230b2_row12_col2\" class=\"data row12 col2\" >28.814841</td>\n",
-       "      <td id=\"T_230b2_row12_col3\" class=\"data row12 col3\" >-2.426442</td>\n",
-       "      <td id=\"T_230b2_row12_col4\" class=\"data row12 col4\" >3</td>\n",
-       "      <td id=\"T_230b2_row12_col5\" class=\"data row12 col5\" >12</td>\n",
-       "      <td id=\"T_230b2_row12_col6\" class=\"data row12 col6\" >-9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row13\" class=\"row_heading level0 row13\" >mistral-medium</th>\n",
-       "      <td id=\"T_230b2_row13_col0\" class=\"data row13 col0\" >1500</td>\n",
-       "      <td id=\"T_230b2_row13_col1\" class=\"data row13 col1\" >21.855773</td>\n",
-       "      <td id=\"T_230b2_row13_col2\" class=\"data row13 col2\" >28.614337</td>\n",
-       "      <td id=\"T_230b2_row13_col3\" class=\"data row13 col3\" >6.758565</td>\n",
-       "      <td id=\"T_230b2_row13_col4\" class=\"data row13 col4\" >15</td>\n",
-       "      <td id=\"T_230b2_row13_col5\" class=\"data row13 col5\" >13</td>\n",
-       "      <td id=\"T_230b2_row13_col6\" class=\"data row13 col6\" >2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row14\" class=\"row_heading level0 row14\" >claude-2</th>\n",
-       "      <td id=\"T_230b2_row14_col0\" class=\"data row14 col0\" >1069</td>\n",
-       "      <td id=\"T_230b2_row14_col1\" class=\"data row14 col1\" >17.188240</td>\n",
-       "      <td id=\"T_230b2_row14_col2\" class=\"data row14 col2\" >28.155196</td>\n",
-       "      <td id=\"T_230b2_row14_col3\" class=\"data row14 col3\" >10.966956</td>\n",
-       "      <td id=\"T_230b2_row14_col4\" class=\"data row14 col4\" >23</td>\n",
-       "      <td id=\"T_230b2_row14_col5\" class=\"data row14 col5\" >14</td>\n",
-       "      <td id=\"T_230b2_row14_col6\" class=\"data row14 col6\" >9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row15\" class=\"row_heading level0 row15\" >claude</th>\n",
-       "      <td id=\"T_230b2_row15_col0\" class=\"data row15 col0\" >1082</td>\n",
-       "      <td id=\"T_230b2_row15_col1\" class=\"data row15 col1\" >16.985344</td>\n",
-       "      <td id=\"T_230b2_row15_col2\" class=\"data row15 col2\" >27.289504</td>\n",
-       "      <td id=\"T_230b2_row15_col3\" class=\"data row15 col3\" >10.304161</td>\n",
-       "      <td id=\"T_230b2_row15_col4\" class=\"data row15 col4\" >24</td>\n",
-       "      <td id=\"T_230b2_row15_col5\" class=\"data row15 col5\" >15</td>\n",
-       "      <td id=\"T_230b2_row15_col6\" class=\"data row15 col6\" >9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row16\" class=\"row_heading level0 row16\" >Yi-34B-Chat</th>\n",
-       "      <td id=\"T_230b2_row16_col0\" class=\"data row16 col0\" >2123</td>\n",
-       "      <td id=\"T_230b2_row16_col1\" class=\"data row16 col1\" >29.659947</td>\n",
-       "      <td id=\"T_230b2_row16_col2\" class=\"data row16 col2\" >27.190548</td>\n",
-       "      <td id=\"T_230b2_row16_col3\" class=\"data row16 col3\" >-2.469399</td>\n",
-       "      <td id=\"T_230b2_row16_col4\" class=\"data row16 col4\" >5</td>\n",
-       "      <td id=\"T_230b2_row16_col5\" class=\"data row16 col5\" >16</td>\n",
-       "      <td id=\"T_230b2_row16_col6\" class=\"data row16 col6\" >-11</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row17\" class=\"row_heading level0 row17\" >Snorkel-Mistral-PairRM-DPO</th>\n",
-       "      <td id=\"T_230b2_row17_col0\" class=\"data row17 col0\" >2736</td>\n",
-       "      <td id=\"T_230b2_row17_col1\" class=\"data row17 col1\" >30.220053</td>\n",
-       "      <td id=\"T_230b2_row17_col2\" class=\"data row17 col2\" >26.386425</td>\n",
-       "      <td id=\"T_230b2_row17_col3\" class=\"data row17 col3\" >-3.833628</td>\n",
-       "      <td id=\"T_230b2_row17_col4\" class=\"data row17 col4\" >4</td>\n",
-       "      <td id=\"T_230b2_row17_col5\" class=\"data row17 col5\" >17</td>\n",
-       "      <td id=\"T_230b2_row17_col6\" class=\"data row17 col6\" >-13</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row18\" class=\"row_heading level0 row18\" >claude-instant-1.2</th>\n",
-       "      <td id=\"T_230b2_row18_col0\" class=\"data row18 col0\" >1112</td>\n",
-       "      <td id=\"T_230b2_row18_col1\" class=\"data row18 col1\" >16.127400</td>\n",
-       "      <td id=\"T_230b2_row18_col2\" class=\"data row18 col2\" >25.612259</td>\n",
-       "      <td id=\"T_230b2_row18_col3\" class=\"data row18 col3\" >9.484859</td>\n",
-       "      <td id=\"T_230b2_row18_col4\" class=\"data row18 col4\" >25</td>\n",
-       "      <td id=\"T_230b2_row18_col5\" class=\"data row18 col5\" >18</td>\n",
-       "      <td id=\"T_230b2_row18_col6\" class=\"data row18 col6\" >7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row19\" class=\"row_heading level0 row19\" >claude-2.1</th>\n",
-       "      <td id=\"T_230b2_row19_col0\" class=\"data row19 col0\" >1096</td>\n",
-       "      <td id=\"T_230b2_row19_col1\" class=\"data row19 col1\" >15.733507</td>\n",
-       "      <td id=\"T_230b2_row19_col2\" class=\"data row19 col2\" >25.251944</td>\n",
-       "      <td id=\"T_230b2_row19_col3\" class=\"data row19 col3\" >9.518437</td>\n",
-       "      <td id=\"T_230b2_row19_col4\" class=\"data row19 col4\" >29</td>\n",
-       "      <td id=\"T_230b2_row19_col5\" class=\"data row19 col5\" >19</td>\n",
-       "      <td id=\"T_230b2_row19_col6\" class=\"data row19 col6\" >10</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row20\" class=\"row_heading level0 row20\" >xwinlm-70b-v0.1</th>\n",
-       "      <td id=\"T_230b2_row20_col0\" class=\"data row20 col0\" >1775</td>\n",
-       "      <td id=\"T_230b2_row20_col1\" class=\"data row20 col1\" >21.812957</td>\n",
-       "      <td id=\"T_230b2_row20_col2\" class=\"data row20 col2\" >24.649686</td>\n",
-       "      <td id=\"T_230b2_row20_col3\" class=\"data row20 col3\" >2.836729</td>\n",
-       "      <td id=\"T_230b2_row20_col4\" class=\"data row20 col4\" >16</td>\n",
-       "      <td id=\"T_230b2_row20_col5\" class=\"data row20 col5\" >20</td>\n",
-       "      <td id=\"T_230b2_row20_col6\" class=\"data row20 col6\" >-4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row21\" class=\"row_heading level0 row21\" >gemini-pro</th>\n",
-       "      <td id=\"T_230b2_row21_col0\" class=\"data row21 col0\" >1456</td>\n",
-       "      <td id=\"T_230b2_row21_col1\" class=\"data row21 col1\" >18.177645</td>\n",
-       "      <td id=\"T_230b2_row21_col2\" class=\"data row21 col2\" >24.427105</td>\n",
-       "      <td id=\"T_230b2_row21_col3\" class=\"data row21 col3\" >6.249460</td>\n",
-       "      <td id=\"T_230b2_row21_col4\" class=\"data row21 col4\" >21</td>\n",
-       "      <td id=\"T_230b2_row21_col5\" class=\"data row21 col5\" >21</td>\n",
-       "      <td id=\"T_230b2_row21_col6\" class=\"data row21 col6\" >0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row22\" class=\"row_heading level0 row22\" >Mixtral-8x7B-Instruct-v0.1</th>\n",
-       "      <td id=\"T_230b2_row22_col0\" class=\"data row22 col0\" >1465</td>\n",
-       "      <td id=\"T_230b2_row22_col1\" class=\"data row22 col1\" >18.255318</td>\n",
-       "      <td id=\"T_230b2_row22_col2\" class=\"data row22 col2\" >23.688483</td>\n",
-       "      <td id=\"T_230b2_row22_col3\" class=\"data row22 col3\" >5.433165</td>\n",
-       "      <td id=\"T_230b2_row22_col4\" class=\"data row22 col4\" >20</td>\n",
-       "      <td id=\"T_230b2_row22_col5\" class=\"data row22 col5\" >22</td>\n",
-       "      <td id=\"T_230b2_row22_col6\" class=\"data row22 col6\" >-2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row23\" class=\"row_heading level0 row23\" >evo-v2-7b</th>\n",
-       "      <td id=\"T_230b2_row23_col0\" class=\"data row23 col0\" >1754</td>\n",
-       "      <td id=\"T_230b2_row23_col1\" class=\"data row23 col1\" >20.834113</td>\n",
-       "      <td id=\"T_230b2_row23_col2\" class=\"data row23 col2\" >23.357706</td>\n",
-       "      <td id=\"T_230b2_row23_col3\" class=\"data row23 col3\" >2.523593</td>\n",
-       "      <td id=\"T_230b2_row23_col4\" class=\"data row23 col4\" >18</td>\n",
-       "      <td id=\"T_230b2_row23_col5\" class=\"data row23 col5\" >23</td>\n",
-       "      <td id=\"T_230b2_row23_col6\" class=\"data row23 col6\" >-5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row24\" class=\"row_heading level0 row24\" >Mixtral-8x7B-Instruct-v0.1_verbose</th>\n",
-       "      <td id=\"T_230b2_row24_col0\" class=\"data row24 col0\" >2083</td>\n",
-       "      <td id=\"T_230b2_row24_col1\" class=\"data row24 col1\" >24.614063</td>\n",
-       "      <td id=\"T_230b2_row24_col2\" class=\"data row24 col2\" >23.223121</td>\n",
-       "      <td id=\"T_230b2_row24_col3\" class=\"data row24 col3\" >-1.390942</td>\n",
-       "      <td id=\"T_230b2_row24_col4\" class=\"data row24 col4\" >9</td>\n",
-       "      <td id=\"T_230b2_row24_col5\" class=\"data row24 col5\" >24</td>\n",
-       "      <td id=\"T_230b2_row24_col6\" class=\"data row24 col6\" >-15</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row25\" class=\"row_heading level0 row25\" >Mixtral-8x7B-Instruct-v0.1_concise</th>\n",
-       "      <td id=\"T_230b2_row25_col0\" class=\"data row25 col0\" >910</td>\n",
-       "      <td id=\"T_230b2_row25_col1\" class=\"data row25 col1\" >13.744040</td>\n",
-       "      <td id=\"T_230b2_row25_col2\" class=\"data row25 col2\" >22.962609</td>\n",
-       "      <td id=\"T_230b2_row25_col3\" class=\"data row25 col3\" >9.218569</td>\n",
-       "      <td id=\"T_230b2_row25_col4\" class=\"data row25 col4\" >39</td>\n",
-       "      <td id=\"T_230b2_row25_col5\" class=\"data row25 col5\" >25</td>\n",
-       "      <td id=\"T_230b2_row25_col6\" class=\"data row25 col6\" >14</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row26\" class=\"row_heading level0 row26\" >gpt-3.5-turbo-16k-0613</th>\n",
-       "      <td id=\"T_230b2_row26_col0\" class=\"data row26 col0\" >1328</td>\n",
-       "      <td id=\"T_230b2_row26_col1\" class=\"data row26 col1\" >14.132391</td>\n",
-       "      <td id=\"T_230b2_row26_col2\" class=\"data row26 col2\" >22.720189</td>\n",
-       "      <td id=\"T_230b2_row26_col3\" class=\"data row26 col3\" >8.587798</td>\n",
-       "      <td id=\"T_230b2_row26_col4\" class=\"data row26 col4\" >34</td>\n",
-       "      <td id=\"T_230b2_row26_col5\" class=\"data row26 col5\" >26</td>\n",
-       "      <td id=\"T_230b2_row26_col6\" class=\"data row26 col6\" >8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row27\" class=\"row_heading level0 row27\" >gpt-3.5-turbo-0613</th>\n",
-       "      <td id=\"T_230b2_row27_col0\" class=\"data row27 col0\" >1331</td>\n",
-       "      <td id=\"T_230b2_row27_col1\" class=\"data row27 col1\" >14.095799</td>\n",
-       "      <td id=\"T_230b2_row27_col2\" class=\"data row27 col2\" >22.352513</td>\n",
-       "      <td id=\"T_230b2_row27_col3\" class=\"data row27 col3\" >8.256714</td>\n",
-       "      <td id=\"T_230b2_row27_col4\" class=\"data row27 col4\" >35</td>\n",
-       "      <td id=\"T_230b2_row27_col5\" class=\"data row27 col5\" >27</td>\n",
-       "      <td id=\"T_230b2_row27_col6\" class=\"data row27 col6\" >8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row28\" class=\"row_heading level0 row28\" >gpt-3.5-turbo-1106_verbose</th>\n",
-       "      <td id=\"T_230b2_row28_col0\" class=\"data row28 col0\" >1058</td>\n",
-       "      <td id=\"T_230b2_row28_col1\" class=\"data row28 col1\" >12.763170</td>\n",
-       "      <td id=\"T_230b2_row28_col2\" class=\"data row28 col2\" >22.000937</td>\n",
-       "      <td id=\"T_230b2_row28_col3\" class=\"data row28 col3\" >9.237767</td>\n",
-       "      <td id=\"T_230b2_row28_col4\" class=\"data row28 col4\" >43</td>\n",
-       "      <td id=\"T_230b2_row28_col5\" class=\"data row28 col5\" >28</td>\n",
-       "      <td id=\"T_230b2_row28_col6\" class=\"data row28 col6\" >15</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row29\" class=\"row_heading level0 row29\" >gpt4_0613_concise</th>\n",
-       "      <td id=\"T_230b2_row29_col0\" class=\"data row29 col0\" >627</td>\n",
-       "      <td id=\"T_230b2_row29_col1\" class=\"data row29 col1\" >9.400321</td>\n",
-       "      <td id=\"T_230b2_row29_col2\" class=\"data row29 col2\" >21.577991</td>\n",
-       "      <td id=\"T_230b2_row29_col3\" class=\"data row29 col3\" >12.177670</td>\n",
-       "      <td id=\"T_230b2_row29_col4\" class=\"data row29 col4\" >61</td>\n",
-       "      <td id=\"T_230b2_row29_col5\" class=\"data row29 col5\" >29</td>\n",
-       "      <td id=\"T_230b2_row29_col6\" class=\"data row29 col6\" >32</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row30\" class=\"row_heading level0 row30\" >pairrm-tulu-2-70b</th>\n",
-       "      <td id=\"T_230b2_row30_col0\" class=\"data row30 col0\" >1607</td>\n",
-       "      <td id=\"T_230b2_row30_col1\" class=\"data row30 col1\" >18.638963</td>\n",
-       "      <td id=\"T_230b2_row30_col2\" class=\"data row30 col2\" >21.428404</td>\n",
-       "      <td id=\"T_230b2_row30_col3\" class=\"data row30 col3\" >2.789441</td>\n",
-       "      <td id=\"T_230b2_row30_col4\" class=\"data row30 col4\" >19</td>\n",
-       "      <td id=\"T_230b2_row30_col5\" class=\"data row30 col5\" >30</td>\n",
-       "      <td id=\"T_230b2_row30_col6\" class=\"data row30 col6\" >-11</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row31\" class=\"row_heading level0 row31\" >tulu-2-dpo-70b</th>\n",
-       "      <td id=\"T_230b2_row31_col0\" class=\"data row31 col0\" >1418</td>\n",
-       "      <td id=\"T_230b2_row31_col1\" class=\"data row31 col1\" >15.982854</td>\n",
-       "      <td id=\"T_230b2_row31_col2\" class=\"data row31 col2\" >21.238610</td>\n",
-       "      <td id=\"T_230b2_row31_col3\" class=\"data row31 col3\" >5.255756</td>\n",
-       "      <td id=\"T_230b2_row31_col4\" class=\"data row31 col4\" >27</td>\n",
-       "      <td id=\"T_230b2_row31_col5\" class=\"data row31 col5\" >31</td>\n",
-       "      <td id=\"T_230b2_row31_col6\" class=\"data row31 col6\" >-4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row32\" class=\"row_heading level0 row32\" >Mistral-7B-ReMax-v0.1</th>\n",
-       "      <td id=\"T_230b2_row32_col0\" class=\"data row32 col0\" >1478</td>\n",
-       "      <td id=\"T_230b2_row32_col1\" class=\"data row32 col1\" >15.999331</td>\n",
-       "      <td id=\"T_230b2_row32_col2\" class=\"data row32 col2\" >20.551368</td>\n",
-       "      <td id=\"T_230b2_row32_col3\" class=\"data row32 col3\" >4.552036</td>\n",
-       "      <td id=\"T_230b2_row32_col4\" class=\"data row32 col4\" >26</td>\n",
-       "      <td id=\"T_230b2_row32_col5\" class=\"data row32 col5\" >32</td>\n",
-       "      <td id=\"T_230b2_row32_col6\" class=\"data row32 col6\" >-6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row33\" class=\"row_heading level0 row33\" >gpt-3.5-turbo-1106</th>\n",
-       "      <td id=\"T_230b2_row33_col0\" class=\"data row33 col0\" >796</td>\n",
-       "      <td id=\"T_230b2_row33_col1\" class=\"data row33 col1\" >9.177965</td>\n",
-       "      <td id=\"T_230b2_row33_col2\" class=\"data row33 col2\" >19.300589</td>\n",
-       "      <td id=\"T_230b2_row33_col3\" class=\"data row33 col3\" >10.122624</td>\n",
-       "      <td id=\"T_230b2_row33_col4\" class=\"data row33 col4\" >64</td>\n",
-       "      <td id=\"T_230b2_row33_col5\" class=\"data row33 col5\" >33</td>\n",
-       "      <td id=\"T_230b2_row33_col6\" class=\"data row33 col6\" >31</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row34\" class=\"row_heading level0 row34\" >LMCocktail-10.7B-v1</th>\n",
-       "      <td id=\"T_230b2_row34_col0\" class=\"data row34 col0\" >1203</td>\n",
-       "      <td id=\"T_230b2_row34_col1\" class=\"data row34 col1\" >13.153431</td>\n",
-       "      <td id=\"T_230b2_row34_col2\" class=\"data row34 col2\" >18.950710</td>\n",
-       "      <td id=\"T_230b2_row34_col3\" class=\"data row34 col3\" >5.797279</td>\n",
-       "      <td id=\"T_230b2_row34_col4\" class=\"data row34 col4\" >40</td>\n",
-       "      <td id=\"T_230b2_row34_col5\" class=\"data row34 col5\" >34</td>\n",
-       "      <td id=\"T_230b2_row34_col6\" class=\"data row34 col6\" >6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row35\" class=\"row_heading level0 row35\" >internlm2-chat-20b-ppo</th>\n",
-       "      <td id=\"T_230b2_row35_col0\" class=\"data row35 col0\" >2373</td>\n",
-       "      <td id=\"T_230b2_row35_col1\" class=\"data row35 col1\" >21.749155</td>\n",
-       "      <td id=\"T_230b2_row35_col2\" class=\"data row35 col2\" >18.748739</td>\n",
-       "      <td id=\"T_230b2_row35_col3\" class=\"data row35 col3\" >-3.000415</td>\n",
-       "      <td id=\"T_230b2_row35_col4\" class=\"data row35 col4\" >17</td>\n",
-       "      <td id=\"T_230b2_row35_col5\" class=\"data row35 col5\" >35</td>\n",
-       "      <td id=\"T_230b2_row35_col6\" class=\"data row35 col6\" >-18</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row36\" class=\"row_heading level0 row36\" >claude-2.1_concise</th>\n",
-       "      <td id=\"T_230b2_row36_col0\" class=\"data row36 col0\" >573</td>\n",
-       "      <td id=\"T_230b2_row36_col1\" class=\"data row36 col1\" >9.227125</td>\n",
-       "      <td id=\"T_230b2_row36_col2\" class=\"data row36 col2\" >18.208458</td>\n",
-       "      <td id=\"T_230b2_row36_col3\" class=\"data row36 col3\" >8.981333</td>\n",
-       "      <td id=\"T_230b2_row36_col4\" class=\"data row36 col4\" >63</td>\n",
-       "      <td id=\"T_230b2_row36_col5\" class=\"data row36 col5\" >36</td>\n",
-       "      <td id=\"T_230b2_row36_col6\" class=\"data row36 col6\" >27</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row37\" class=\"row_heading level0 row37\" >gpt-3.5-turbo-0301</th>\n",
-       "      <td id=\"T_230b2_row37_col0\" class=\"data row37 col0\" >827</td>\n",
-       "      <td id=\"T_230b2_row37_col1\" class=\"data row37 col1\" >9.622453</td>\n",
-       "      <td id=\"T_230b2_row37_col2\" class=\"data row37 col2\" >18.093242</td>\n",
-       "      <td id=\"T_230b2_row37_col3\" class=\"data row37 col3\" >8.470788</td>\n",
-       "      <td id=\"T_230b2_row37_col4\" class=\"data row37 col4\" >58</td>\n",
-       "      <td id=\"T_230b2_row37_col5\" class=\"data row37 col5\" >37</td>\n",
-       "      <td id=\"T_230b2_row37_col6\" class=\"data row37 col6\" >21</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row38\" class=\"row_heading level0 row38\" >xwinlm-13b-v0.1</th>\n",
-       "      <td id=\"T_230b2_row38_col0\" class=\"data row38 col0\" >1894</td>\n",
-       "      <td id=\"T_230b2_row38_col1\" class=\"data row38 col1\" >17.427935</td>\n",
-       "      <td id=\"T_230b2_row38_col2\" class=\"data row38 col2\" >17.918938</td>\n",
-       "      <td id=\"T_230b2_row38_col3\" class=\"data row38 col3\" >0.491003</td>\n",
-       "      <td id=\"T_230b2_row38_col4\" class=\"data row38 col4\" >22</td>\n",
-       "      <td id=\"T_230b2_row38_col5\" class=\"data row38 col5\" >38</td>\n",
-       "      <td id=\"T_230b2_row38_col6\" class=\"data row38 col6\" >-16</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row39\" class=\"row_heading level0 row39\" >deepseek-llm-67b-chat</th>\n",
-       "      <td id=\"T_230b2_row39_col0\" class=\"data row39 col0\" >1151</td>\n",
-       "      <td id=\"T_230b2_row39_col1\" class=\"data row39 col1\" >12.093422</td>\n",
-       "      <td id=\"T_230b2_row39_col2\" class=\"data row39 col2\" >17.843384</td>\n",
-       "      <td id=\"T_230b2_row39_col3\" class=\"data row39 col3\" >5.749962</td>\n",
-       "      <td id=\"T_230b2_row39_col4\" class=\"data row39 col4\" >46</td>\n",
-       "      <td id=\"T_230b2_row39_col5\" class=\"data row39 col5\" >39</td>\n",
-       "      <td id=\"T_230b2_row39_col6\" class=\"data row39 col6\" >7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row40\" class=\"row_heading level0 row40\" >gpt35_turbo_instruct</th>\n",
-       "      <td id=\"T_230b2_row40_col0\" class=\"data row40 col0\" >1018</td>\n",
-       "      <td id=\"T_230b2_row40_col1\" class=\"data row40 col1\" >8.462447</td>\n",
-       "      <td id=\"T_230b2_row40_col2\" class=\"data row40 col2\" >17.721303</td>\n",
-       "      <td id=\"T_230b2_row40_col3\" class=\"data row40 col3\" >9.258856</td>\n",
-       "      <td id=\"T_230b2_row40_col4\" class=\"data row40 col4\" >68</td>\n",
-       "      <td id=\"T_230b2_row40_col5\" class=\"data row40 col5\" >40</td>\n",
-       "      <td id=\"T_230b2_row40_col6\" class=\"data row40 col6\" >28</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row41\" class=\"row_heading level0 row41\" >wizardlm-70b</th>\n",
-       "      <td id=\"T_230b2_row41_col0\" class=\"data row41 col0\" >1545</td>\n",
-       "      <td id=\"T_230b2_row41_col1\" class=\"data row41 col1\" >14.383896</td>\n",
-       "      <td id=\"T_230b2_row41_col2\" class=\"data row41 col2\" >17.575061</td>\n",
-       "      <td id=\"T_230b2_row41_col3\" class=\"data row41 col3\" >3.191165</td>\n",
-       "      <td id=\"T_230b2_row41_col4\" class=\"data row41 col4\" >32</td>\n",
-       "      <td id=\"T_230b2_row41_col5\" class=\"data row41 col5\" >41</td>\n",
-       "      <td id=\"T_230b2_row41_col6\" class=\"data row41 col6\" >-9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row42\" class=\"row_heading level0 row42\" >vicuna-33b-v1.3</th>\n",
-       "      <td id=\"T_230b2_row42_col0\" class=\"data row42 col0\" >1479</td>\n",
-       "      <td id=\"T_230b2_row42_col1\" class=\"data row42 col1\" >12.705948</td>\n",
-       "      <td id=\"T_230b2_row42_col2\" class=\"data row42 col2\" >17.574575</td>\n",
-       "      <td id=\"T_230b2_row42_col3\" class=\"data row42 col3\" >4.868627</td>\n",
-       "      <td id=\"T_230b2_row42_col4\" class=\"data row42 col4\" >44</td>\n",
-       "      <td id=\"T_230b2_row42_col5\" class=\"data row42 col5\" >42</td>\n",
-       "      <td id=\"T_230b2_row42_col6\" class=\"data row42 col6\" >2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row43\" class=\"row_heading level0 row43\" >pairrm-tulu-2-13b</th>\n",
-       "      <td id=\"T_230b2_row43_col0\" class=\"data row43 col0\" >1454</td>\n",
-       "      <td id=\"T_230b2_row43_col1\" class=\"data row43 col1\" >13.831901</td>\n",
-       "      <td id=\"T_230b2_row43_col2\" class=\"data row43 col2\" >17.405204</td>\n",
-       "      <td id=\"T_230b2_row43_col3\" class=\"data row43 col3\" >3.573303</td>\n",
-       "      <td id=\"T_230b2_row43_col4\" class=\"data row43 col4\" >38</td>\n",
-       "      <td id=\"T_230b2_row43_col5\" class=\"data row43 col5\" >43</td>\n",
-       "      <td id=\"T_230b2_row43_col6\" class=\"data row43 col6\" >-5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row44\" class=\"row_heading level0 row44\" >Mistral-7B-Instruct-v0.2</th>\n",
-       "      <td id=\"T_230b2_row44_col0\" class=\"data row44 col0\" >1676</td>\n",
-       "      <td id=\"T_230b2_row44_col1\" class=\"data row44 col1\" >14.722773</td>\n",
-       "      <td id=\"T_230b2_row44_col2\" class=\"data row44 col2\" >17.111252</td>\n",
-       "      <td id=\"T_230b2_row44_col3\" class=\"data row44 col3\" >2.388479</td>\n",
-       "      <td id=\"T_230b2_row44_col4\" class=\"data row44 col4\" >31</td>\n",
-       "      <td id=\"T_230b2_row44_col5\" class=\"data row44 col5\" >44</td>\n",
-       "      <td id=\"T_230b2_row44_col6\" class=\"data row44 col6\" >-13</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row45\" class=\"row_heading level0 row45\" >evo-7b</th>\n",
-       "      <td id=\"T_230b2_row45_col0\" class=\"data row45 col0\" >1774</td>\n",
-       "      <td id=\"T_230b2_row45_col1\" class=\"data row45 col1\" >15.577437</td>\n",
-       "      <td id=\"T_230b2_row45_col2\" class=\"data row45 col2\" >16.489386</td>\n",
-       "      <td id=\"T_230b2_row45_col3\" class=\"data row45 col3\" >0.911949</td>\n",
-       "      <td id=\"T_230b2_row45_col4\" class=\"data row45 col4\" >30</td>\n",
-       "      <td id=\"T_230b2_row45_col5\" class=\"data row45 col5\" >45</td>\n",
-       "      <td id=\"T_230b2_row45_col6\" class=\"data row45 col6\" >-15</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row46\" class=\"row_heading level0 row46\" >humpback-llama2-70b</th>\n",
-       "      <td id=\"T_230b2_row46_col0\" class=\"data row46 col0\" >1107</td>\n",
-       "      <td id=\"T_230b2_row46_col1\" class=\"data row46 col1\" >10.121772</td>\n",
-       "      <td id=\"T_230b2_row46_col2\" class=\"data row46 col2\" >16.249164</td>\n",
-       "      <td id=\"T_230b2_row46_col3\" class=\"data row46 col3\" >6.127393</td>\n",
-       "      <td id=\"T_230b2_row46_col4\" class=\"data row46 col4\" >56</td>\n",
-       "      <td id=\"T_230b2_row46_col5\" class=\"data row46 col5\" >46</td>\n",
-       "      <td id=\"T_230b2_row46_col6\" class=\"data row46 col6\" >10</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row47\" class=\"row_heading level0 row47\" >OpenHermes-2.5-Mistral-7B</th>\n",
-       "      <td id=\"T_230b2_row47_col0\" class=\"data row47 col0\" >1107</td>\n",
-       "      <td id=\"T_230b2_row47_col1\" class=\"data row47 col1\" >10.340416</td>\n",
-       "      <td id=\"T_230b2_row47_col2\" class=\"data row47 col2\" >16.248578</td>\n",
-       "      <td id=\"T_230b2_row47_col3\" class=\"data row47 col3\" >5.908162</td>\n",
-       "      <td id=\"T_230b2_row47_col4\" class=\"data row47 col4\" >55</td>\n",
-       "      <td id=\"T_230b2_row47_col5\" class=\"data row47 col5\" >47</td>\n",
-       "      <td id=\"T_230b2_row47_col6\" class=\"data row47 col6\" >8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row48\" class=\"row_heading level0 row48\" >deita-7b-v1.0</th>\n",
-       "      <td id=\"T_230b2_row48_col0\" class=\"data row48 col0\" >1417</td>\n",
-       "      <td id=\"T_230b2_row48_col1\" class=\"data row48 col1\" >12.646639</td>\n",
-       "      <td id=\"T_230b2_row48_col2\" class=\"data row48 col2\" >16.059014</td>\n",
-       "      <td id=\"T_230b2_row48_col3\" class=\"data row48 col3\" >3.412374</td>\n",
-       "      <td id=\"T_230b2_row48_col4\" class=\"data row48 col4\" >45</td>\n",
-       "      <td id=\"T_230b2_row48_col5\" class=\"data row48 col5\" >48</td>\n",
-       "      <td id=\"T_230b2_row48_col6\" class=\"data row48 col6\" >-3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row49\" class=\"row_heading level0 row49\" >jina-chat</th>\n",
-       "      <td id=\"T_230b2_row49_col0\" class=\"data row49 col0\" >676</td>\n",
-       "      <td id=\"T_230b2_row49_col1\" class=\"data row49 col1\" >7.786130</td>\n",
-       "      <td id=\"T_230b2_row49_col2\" class=\"data row49 col2\" >15.866004</td>\n",
-       "      <td id=\"T_230b2_row49_col3\" class=\"data row49 col3\" >8.079874</td>\n",
-       "      <td id=\"T_230b2_row49_col4\" class=\"data row49 col4\" >74</td>\n",
-       "      <td id=\"T_230b2_row49_col5\" class=\"data row49 col5\" >49</td>\n",
-       "      <td id=\"T_230b2_row49_col6\" class=\"data row49 col6\" >25</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row50\" class=\"row_heading level0 row50\" >gpt-3.5-turbo-1106_concise</th>\n",
-       "      <td id=\"T_230b2_row50_col0\" class=\"data row50 col0\" >431</td>\n",
-       "      <td id=\"T_230b2_row50_col1\" class=\"data row50 col1\" >7.415865</td>\n",
-       "      <td id=\"T_230b2_row50_col2\" class=\"data row50 col2\" >15.769521</td>\n",
-       "      <td id=\"T_230b2_row50_col3\" class=\"data row50 col3\" >8.353656</td>\n",
-       "      <td id=\"T_230b2_row50_col4\" class=\"data row50 col4\" >82</td>\n",
-       "      <td id=\"T_230b2_row50_col5\" class=\"data row50 col5\" >50</td>\n",
-       "      <td id=\"T_230b2_row50_col6\" class=\"data row50 col6\" >32</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row51\" class=\"row_heading level0 row51\" >causallm-14b</th>\n",
-       "      <td id=\"T_230b2_row51_col0\" class=\"data row51 col0\" >1391</td>\n",
-       "      <td id=\"T_230b2_row51_col1\" class=\"data row51 col1\" >11.146161</td>\n",
-       "      <td id=\"T_230b2_row51_col2\" class=\"data row51 col2\" >15.720325</td>\n",
-       "      <td id=\"T_230b2_row51_col3\" class=\"data row51 col3\" >4.574164</td>\n",
-       "      <td id=\"T_230b2_row51_col4\" class=\"data row51 col4\" >51</td>\n",
-       "      <td id=\"T_230b2_row51_col5\" class=\"data row51 col5\" >51</td>\n",
-       "      <td id=\"T_230b2_row51_col6\" class=\"data row51 col6\" >0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row52\" class=\"row_heading level0 row52\" >pairrm-zephyr-7b-beta</th>\n",
-       "      <td id=\"T_230b2_row52_col0\" class=\"data row52 col0\" >1487</td>\n",
-       "      <td id=\"T_230b2_row52_col1\" class=\"data row52 col1\" >12.841278</td>\n",
-       "      <td id=\"T_230b2_row52_col2\" class=\"data row52 col2\" >15.529867</td>\n",
-       "      <td id=\"T_230b2_row52_col3\" class=\"data row52 col3\" >2.688589</td>\n",
-       "      <td id=\"T_230b2_row52_col4\" class=\"data row52 col4\" >42</td>\n",
-       "      <td id=\"T_230b2_row52_col5\" class=\"data row52 col5\" >52</td>\n",
-       "      <td id=\"T_230b2_row52_col6\" class=\"data row52 col6\" >-10</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row53\" class=\"row_heading level0 row53\" >Starling-LM-7B-alpha</th>\n",
-       "      <td id=\"T_230b2_row53_col0\" class=\"data row53 col0\" >1895</td>\n",
-       "      <td id=\"T_230b2_row53_col1\" class=\"data row53 col1\" >14.245924</td>\n",
-       "      <td id=\"T_230b2_row53_col2\" class=\"data row53 col2\" >14.690471</td>\n",
-       "      <td id=\"T_230b2_row53_col3\" class=\"data row53 col3\" >0.444548</td>\n",
-       "      <td id=\"T_230b2_row53_col4\" class=\"data row53 col4\" >33</td>\n",
-       "      <td id=\"T_230b2_row53_col5\" class=\"data row53 col5\" >53</td>\n",
-       "      <td id=\"T_230b2_row53_col6\" class=\"data row53 col6\" >-20</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row54\" class=\"row_heading level0 row54\" >llama-2-70b-chat-hf</th>\n",
-       "      <td id=\"T_230b2_row54_col0\" class=\"data row54 col0\" >1790</td>\n",
-       "      <td id=\"T_230b2_row54_col1\" class=\"data row54 col1\" >13.888258</td>\n",
-       "      <td id=\"T_230b2_row54_col2\" class=\"data row54 col2\" >14.677319</td>\n",
-       "      <td id=\"T_230b2_row54_col3\" class=\"data row54 col3\" >0.789061</td>\n",
-       "      <td id=\"T_230b2_row54_col4\" class=\"data row54 col4\" >36</td>\n",
-       "      <td id=\"T_230b2_row54_col5\" class=\"data row54 col5\" >54</td>\n",
-       "      <td id=\"T_230b2_row54_col6\" class=\"data row54 col6\" >-18</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row55\" class=\"row_heading level0 row55\" >openchat-v3.1-13b</th>\n",
-       "      <td id=\"T_230b2_row55_col0\" class=\"data row55 col0\" >1484</td>\n",
-       "      <td id=\"T_230b2_row55_col1\" class=\"data row55 col1\" >11.082230</td>\n",
-       "      <td id=\"T_230b2_row55_col2\" class=\"data row55 col2\" >14.503388</td>\n",
-       "      <td id=\"T_230b2_row55_col3\" class=\"data row55 col3\" >3.421157</td>\n",
-       "      <td id=\"T_230b2_row55_col4\" class=\"data row55 col4\" >52</td>\n",
-       "      <td id=\"T_230b2_row55_col5\" class=\"data row55 col5\" >55</td>\n",
-       "      <td id=\"T_230b2_row55_col6\" class=\"data row55 col6\" >-3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row56\" class=\"row_heading level0 row56\" >wizardlm-13b-v1.2</th>\n",
-       "      <td id=\"T_230b2_row56_col0\" class=\"data row56 col0\" >1635</td>\n",
-       "      <td id=\"T_230b2_row56_col1\" class=\"data row56 col1\" >12.027480</td>\n",
-       "      <td id=\"T_230b2_row56_col2\" class=\"data row56 col2\" >14.462591</td>\n",
-       "      <td id=\"T_230b2_row56_col3\" class=\"data row56 col3\" >2.435110</td>\n",
-       "      <td id=\"T_230b2_row56_col4\" class=\"data row56 col4\" >47</td>\n",
-       "      <td id=\"T_230b2_row56_col5\" class=\"data row56 col5\" >56</td>\n",
-       "      <td id=\"T_230b2_row56_col6\" class=\"data row56 col6\" >-9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row57\" class=\"row_heading level0 row57\" >ultralm-13b-v2.0-best-of-16</th>\n",
-       "      <td id=\"T_230b2_row57_col0\" class=\"data row57 col0\" >1720</td>\n",
-       "      <td id=\"T_230b2_row57_col1\" class=\"data row57 col1\" >13.853373</td>\n",
-       "      <td id=\"T_230b2_row57_col2\" class=\"data row57 col2\" >14.198988</td>\n",
-       "      <td id=\"T_230b2_row57_col3\" class=\"data row57 col3\" >0.345614</td>\n",
-       "      <td id=\"T_230b2_row57_col4\" class=\"data row57 col4\" >37</td>\n",
-       "      <td id=\"T_230b2_row57_col5\" class=\"data row57 col5\" >57</td>\n",
-       "      <td id=\"T_230b2_row57_col6\" class=\"data row57 col6\" >-20</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row58\" class=\"row_heading level0 row58\" >wizardlm-13b-v1.1</th>\n",
-       "      <td id=\"T_230b2_row58_col0\" class=\"data row58 col0\" >1525</td>\n",
-       "      <td id=\"T_230b2_row58_col1\" class=\"data row58 col1\" >11.233910</td>\n",
-       "      <td id=\"T_230b2_row58_col2\" class=\"data row58 col2\" >13.915721</td>\n",
-       "      <td id=\"T_230b2_row58_col3\" class=\"data row58 col3\" >2.681811</td>\n",
-       "      <td id=\"T_230b2_row58_col4\" class=\"data row58 col4\" >50</td>\n",
-       "      <td id=\"T_230b2_row58_col5\" class=\"data row58 col5\" >58</td>\n",
-       "      <td id=\"T_230b2_row58_col6\" class=\"data row58 col6\" >-8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row59\" class=\"row_heading level0 row59\" >zephyr-7b-beta</th>\n",
-       "      <td id=\"T_230b2_row59_col0\" class=\"data row59 col0\" >1444</td>\n",
-       "      <td id=\"T_230b2_row59_col1\" class=\"data row59 col1\" >10.992886</td>\n",
-       "      <td id=\"T_230b2_row59_col2\" class=\"data row59 col2\" >13.203198</td>\n",
-       "      <td id=\"T_230b2_row59_col3\" class=\"data row59 col3\" >2.210313</td>\n",
-       "      <td id=\"T_230b2_row59_col4\" class=\"data row59 col4\" >53</td>\n",
-       "      <td id=\"T_230b2_row59_col5\" class=\"data row59 col5\" >59</td>\n",
-       "      <td id=\"T_230b2_row59_col6\" class=\"data row59 col6\" >-6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row60\" class=\"row_heading level0 row60\" >dolphin-2.2.1-mistral-7b</th>\n",
-       "      <td id=\"T_230b2_row60_col0\" class=\"data row60 col0\" >1130</td>\n",
-       "      <td id=\"T_230b2_row60_col1\" class=\"data row60 col1\" >9.039800</td>\n",
-       "      <td id=\"T_230b2_row60_col2\" class=\"data row60 col2\" >13.121478</td>\n",
-       "      <td id=\"T_230b2_row60_col3\" class=\"data row60 col3\" >4.081678</td>\n",
-       "      <td id=\"T_230b2_row60_col4\" class=\"data row60 col4\" >66</td>\n",
-       "      <td id=\"T_230b2_row60_col5\" class=\"data row60 col5\" >60</td>\n",
-       "      <td id=\"T_230b2_row60_col6\" class=\"data row60 col6\" >6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row61\" class=\"row_heading level0 row61\" >humpback-llama-65b</th>\n",
-       "      <td id=\"T_230b2_row61_col0\" class=\"data row61 col0\" >1232</td>\n",
-       "      <td id=\"T_230b2_row61_col1\" class=\"data row61 col1\" >9.425139</td>\n",
-       "      <td id=\"T_230b2_row61_col2\" class=\"data row61 col2\" >12.799860</td>\n",
-       "      <td id=\"T_230b2_row61_col3\" class=\"data row61 col3\" >3.374721</td>\n",
-       "      <td id=\"T_230b2_row61_col4\" class=\"data row61 col4\" >60</td>\n",
-       "      <td id=\"T_230b2_row61_col5\" class=\"data row61 col5\" >61</td>\n",
-       "      <td id=\"T_230b2_row61_col6\" class=\"data row61 col6\" >-1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row62\" class=\"row_heading level0 row62\" >openbuddy-llama2-70b-v10.1</th>\n",
-       "      <td id=\"T_230b2_row62_col0\" class=\"data row62 col0\" >1077</td>\n",
-       "      <td id=\"T_230b2_row62_col1\" class=\"data row62 col1\" >8.096422</td>\n",
-       "      <td id=\"T_230b2_row62_col2\" class=\"data row62 col2\" >12.572173</td>\n",
-       "      <td id=\"T_230b2_row62_col3\" class=\"data row62 col3\" >4.475751</td>\n",
-       "      <td id=\"T_230b2_row62_col4\" class=\"data row62 col4\" >72</td>\n",
-       "      <td id=\"T_230b2_row62_col5\" class=\"data row62 col5\" >62</td>\n",
-       "      <td id=\"T_230b2_row62_col6\" class=\"data row62 col6\" >10</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row63\" class=\"row_heading level0 row63\" >openbuddy-llama-65b-v8</th>\n",
-       "      <td id=\"T_230b2_row63_col0\" class=\"data row63 col0\" >1162</td>\n",
-       "      <td id=\"T_230b2_row63_col1\" class=\"data row63 col1\" >8.770650</td>\n",
-       "      <td id=\"T_230b2_row63_col2\" class=\"data row63 col2\" >12.469356</td>\n",
-       "      <td id=\"T_230b2_row63_col3\" class=\"data row63 col3\" >3.698706</td>\n",
-       "      <td id=\"T_230b2_row63_col4\" class=\"data row63 col4\" >67</td>\n",
-       "      <td id=\"T_230b2_row63_col5\" class=\"data row63 col5\" >63</td>\n",
-       "      <td id=\"T_230b2_row63_col6\" class=\"data row63 col6\" >4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row64\" class=\"row_heading level0 row64\" >Qwen-14B-Chat</th>\n",
-       "      <td id=\"T_230b2_row64_col0\" class=\"data row64 col0\" >1013</td>\n",
-       "      <td id=\"T_230b2_row64_col1\" class=\"data row64 col1\" >7.502333</td>\n",
-       "      <td id=\"T_230b2_row64_col2\" class=\"data row64 col2\" >12.378742</td>\n",
-       "      <td id=\"T_230b2_row64_col3\" class=\"data row64 col3\" >4.876408</td>\n",
-       "      <td id=\"T_230b2_row64_col4\" class=\"data row64 col4\" >79</td>\n",
-       "      <td id=\"T_230b2_row64_col5\" class=\"data row64 col5\" >64</td>\n",
-       "      <td id=\"T_230b2_row64_col6\" class=\"data row64 col6\" >15</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row65\" class=\"row_heading level0 row65\" >gpt4_gamed</th>\n",
-       "      <td id=\"T_230b2_row65_col0\" class=\"data row65 col0\" >68</td>\n",
-       "      <td id=\"T_230b2_row65_col1\" class=\"data row65 col1\" >3.738337</td>\n",
-       "      <td id=\"T_230b2_row65_col2\" class=\"data row65 col2\" >12.188764</td>\n",
-       "      <td id=\"T_230b2_row65_col3\" class=\"data row65 col3\" >8.450427</td>\n",
-       "      <td id=\"T_230b2_row65_col4\" class=\"data row65 col4\" >110</td>\n",
-       "      <td id=\"T_230b2_row65_col5\" class=\"data row65 col5\" >65</td>\n",
-       "      <td id=\"T_230b2_row65_col6\" class=\"data row65 col6\" >45</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row66\" class=\"row_heading level0 row66\" >cut-13b</th>\n",
-       "      <td id=\"T_230b2_row66_col0\" class=\"data row66 col0\" >1637</td>\n",
-       "      <td id=\"T_230b2_row66_col1\" class=\"data row66 col1\" >10.779089</td>\n",
-       "      <td id=\"T_230b2_row66_col2\" class=\"data row66 col2\" >12.154782</td>\n",
-       "      <td id=\"T_230b2_row66_col3\" class=\"data row66 col3\" >1.375693</td>\n",
-       "      <td id=\"T_230b2_row66_col4\" class=\"data row66 col4\" >54</td>\n",
-       "      <td id=\"T_230b2_row66_col5\" class=\"data row66 col5\" >66</td>\n",
-       "      <td id=\"T_230b2_row66_col6\" class=\"data row66 col6\" >-12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row67\" class=\"row_heading level0 row67\" >openchat-v2-w-13b</th>\n",
-       "      <td id=\"T_230b2_row67_col0\" class=\"data row67 col0\" >1566</td>\n",
-       "      <td id=\"T_230b2_row67_col1\" class=\"data row67 col1\" >9.615344</td>\n",
-       "      <td id=\"T_230b2_row67_col2\" class=\"data row67 col2\" >12.030428</td>\n",
-       "      <td id=\"T_230b2_row67_col3\" class=\"data row67 col3\" >2.415084</td>\n",
-       "      <td id=\"T_230b2_row67_col4\" class=\"data row67 col4\" >59</td>\n",
-       "      <td id=\"T_230b2_row67_col5\" class=\"data row67 col5\" >67</td>\n",
-       "      <td id=\"T_230b2_row67_col6\" class=\"data row67 col6\" >-8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row68\" class=\"row_heading level0 row68\" >tulu-2-dpo-13b</th>\n",
-       "      <td id=\"T_230b2_row68_col0\" class=\"data row68 col0\" >1614</td>\n",
-       "      <td id=\"T_230b2_row68_col1\" class=\"data row68 col1\" >10.119788</td>\n",
-       "      <td id=\"T_230b2_row68_col2\" class=\"data row68 col2\" >11.554479</td>\n",
-       "      <td id=\"T_230b2_row68_col3\" class=\"data row68 col3\" >1.434691</td>\n",
-       "      <td id=\"T_230b2_row68_col4\" class=\"data row68 col4\" >57</td>\n",
-       "      <td id=\"T_230b2_row68_col5\" class=\"data row68 col5\" >68</td>\n",
-       "      <td id=\"T_230b2_row68_col6\" class=\"data row68 col6\" >-11</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row69\" class=\"row_heading level0 row69\" >claude2-alpaca-13b</th>\n",
-       "      <td id=\"T_230b2_row69_col0\" class=\"data row69 col0\" >1127</td>\n",
-       "      <td id=\"T_230b2_row69_col1\" class=\"data row69 col1\" >7.437351</td>\n",
-       "      <td id=\"T_230b2_row69_col2\" class=\"data row69 col2\" >11.498898</td>\n",
-       "      <td id=\"T_230b2_row69_col3\" class=\"data row69 col3\" >4.061547</td>\n",
-       "      <td id=\"T_230b2_row69_col4\" class=\"data row69 col4\" >81</td>\n",
-       "      <td id=\"T_230b2_row69_col5\" class=\"data row69 col5\" >69</td>\n",
-       "      <td id=\"T_230b2_row69_col6\" class=\"data row69 col6\" >12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row70\" class=\"row_heading level0 row70\" >minotaur-13b</th>\n",
-       "      <td id=\"T_230b2_row70_col0\" class=\"data row70 col0\" >881</td>\n",
-       "      <td id=\"T_230b2_row70_col1\" class=\"data row70 col1\" >5.738964</td>\n",
-       "      <td id=\"T_230b2_row70_col2\" class=\"data row70 col2\" >11.458819</td>\n",
-       "      <td id=\"T_230b2_row70_col3\" class=\"data row70 col3\" >5.719855</td>\n",
-       "      <td id=\"T_230b2_row70_col4\" class=\"data row70 col4\" >98</td>\n",
-       "      <td id=\"T_230b2_row70_col5\" class=\"data row70 col5\" >70</td>\n",
-       "      <td id=\"T_230b2_row70_col6\" class=\"data row70 col6\" >28</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row71\" class=\"row_heading level0 row71\" >airoboros-65b</th>\n",
-       "      <td id=\"T_230b2_row71_col0\" class=\"data row71 col0\" >1512</td>\n",
-       "      <td id=\"T_230b2_row71_col1\" class=\"data row71 col1\" >9.388950</td>\n",
-       "      <td id=\"T_230b2_row71_col2\" class=\"data row71 col2\" >11.007642</td>\n",
-       "      <td id=\"T_230b2_row71_col3\" class=\"data row71 col3\" >1.618692</td>\n",
-       "      <td id=\"T_230b2_row71_col4\" class=\"data row71 col4\" >62</td>\n",
-       "      <td id=\"T_230b2_row71_col5\" class=\"data row71 col5\" >71</td>\n",
-       "      <td id=\"T_230b2_row71_col6\" class=\"data row71 col6\" >-9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row72\" class=\"row_heading level0 row72\" >cohere</th>\n",
-       "      <td id=\"T_230b2_row72_col0\" class=\"data row72 col0\" >1983</td>\n",
-       "      <td id=\"T_230b2_row72_col1\" class=\"data row72 col1\" >12.901455</td>\n",
-       "      <td id=\"T_230b2_row72_col2\" class=\"data row72 col2\" >10.893021</td>\n",
-       "      <td id=\"T_230b2_row72_col3\" class=\"data row72 col3\" >-2.008434</td>\n",
-       "      <td id=\"T_230b2_row72_col4\" class=\"data row72 col4\" >41</td>\n",
-       "      <td id=\"T_230b2_row72_col5\" class=\"data row72 col5\" >72</td>\n",
-       "      <td id=\"T_230b2_row72_col6\" class=\"data row72 col6\" >-31</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row73\" class=\"row_heading level0 row73\" >vicuna-13b-v1.3</th>\n",
-       "      <td id=\"T_230b2_row73_col0\" class=\"data row73 col0\" >1132</td>\n",
-       "      <td id=\"T_230b2_row73_col1\" class=\"data row73 col1\" >7.137240</td>\n",
-       "      <td id=\"T_230b2_row73_col2\" class=\"data row73 col2\" >10.843165</td>\n",
-       "      <td id=\"T_230b2_row73_col3\" class=\"data row73 col3\" >3.705925</td>\n",
-       "      <td id=\"T_230b2_row73_col4\" class=\"data row73 col4\" >85</td>\n",
-       "      <td id=\"T_230b2_row73_col5\" class=\"data row73 col5\" >73</td>\n",
-       "      <td id=\"T_230b2_row73_col6\" class=\"data row73 col6\" >12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row74\" class=\"row_heading level0 row74\" >xwinlm-7b-v0.1</th>\n",
-       "      <td id=\"T_230b2_row74_col0\" class=\"data row74 col0\" >1894</td>\n",
-       "      <td id=\"T_230b2_row74_col1\" class=\"data row74 col1\" >11.245652</td>\n",
-       "      <td id=\"T_230b2_row74_col2\" class=\"data row74 col2\" >10.812206</td>\n",
-       "      <td id=\"T_230b2_row74_col3\" class=\"data row74 col3\" >-0.433446</td>\n",
-       "      <td id=\"T_230b2_row74_col4\" class=\"data row74 col4\" >49</td>\n",
-       "      <td id=\"T_230b2_row74_col5\" class=\"data row74 col5\" >74</td>\n",
-       "      <td id=\"T_230b2_row74_col6\" class=\"data row74 col6\" >-25</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row75\" class=\"row_heading level0 row75\" >airoboros-33b</th>\n",
-       "      <td id=\"T_230b2_row75_col0\" class=\"data row75 col0\" >1514</td>\n",
-       "      <td id=\"T_230b2_row75_col1\" class=\"data row75 col1\" >9.053160</td>\n",
-       "      <td id=\"T_230b2_row75_col2\" class=\"data row75 col2\" >10.719003</td>\n",
-       "      <td id=\"T_230b2_row75_col3\" class=\"data row75 col3\" >1.665842</td>\n",
-       "      <td id=\"T_230b2_row75_col4\" class=\"data row75 col4\" >65</td>\n",
-       "      <td id=\"T_230b2_row75_col5\" class=\"data row75 col5\" >75</td>\n",
-       "      <td id=\"T_230b2_row75_col6\" class=\"data row75 col6\" >-10</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row76\" class=\"row_heading level0 row76\" >platolm-7b</th>\n",
-       "      <td id=\"T_230b2_row76_col0\" class=\"data row76 col0\" >1344</td>\n",
-       "      <td id=\"T_230b2_row76_col1\" class=\"data row76 col1\" >6.320828</td>\n",
-       "      <td id=\"T_230b2_row76_col2\" class=\"data row76 col2\" >10.532885</td>\n",
-       "      <td id=\"T_230b2_row76_col3\" class=\"data row76 col3\" >4.212057</td>\n",
-       "      <td id=\"T_230b2_row76_col4\" class=\"data row76 col4\" >91</td>\n",
-       "      <td id=\"T_230b2_row76_col5\" class=\"data row76 col5\" >76</td>\n",
-       "      <td id=\"T_230b2_row76_col6\" class=\"data row76 col6\" >15</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row77\" class=\"row_heading level0 row77\" >vicuna-13b-v1.5</th>\n",
-       "      <td id=\"T_230b2_row77_col0\" class=\"data row77 col0\" >1061</td>\n",
-       "      <td id=\"T_230b2_row77_col1\" class=\"data row77 col1\" >6.722122</td>\n",
-       "      <td id=\"T_230b2_row77_col2\" class=\"data row77 col2\" >10.484438</td>\n",
-       "      <td id=\"T_230b2_row77_col3\" class=\"data row77 col3\" >3.762316</td>\n",
-       "      <td id=\"T_230b2_row77_col4\" class=\"data row77 col4\" >88</td>\n",
-       "      <td id=\"T_230b2_row77_col5\" class=\"data row77 col5\" >77</td>\n",
-       "      <td id=\"T_230b2_row77_col6\" class=\"data row77 col6\" >11</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row78\" class=\"row_heading level0 row78\" >gemma-7b-it</th>\n",
-       "      <td id=\"T_230b2_row78_col0\" class=\"data row78 col0\" >1115</td>\n",
-       "      <td id=\"T_230b2_row78_col1\" class=\"data row78 col1\" >6.937294</td>\n",
-       "      <td id=\"T_230b2_row78_col2\" class=\"data row78 col2\" >10.425760</td>\n",
-       "      <td id=\"T_230b2_row78_col3\" class=\"data row78 col3\" >3.488466</td>\n",
-       "      <td id=\"T_230b2_row78_col4\" class=\"data row78 col4\" >86</td>\n",
-       "      <td id=\"T_230b2_row78_col5\" class=\"data row78 col5\" >78</td>\n",
-       "      <td id=\"T_230b2_row78_col6\" class=\"data row78 col6\" >8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row79\" class=\"row_heading level0 row79\" >openchat-v2-13b</th>\n",
-       "      <td id=\"T_230b2_row79_col0\" class=\"data row79 col0\" >1564</td>\n",
-       "      <td id=\"T_230b2_row79_col1\" class=\"data row79 col1\" >8.435076</td>\n",
-       "      <td id=\"T_230b2_row79_col2\" class=\"data row79 col2\" >10.399607</td>\n",
-       "      <td id=\"T_230b2_row79_col3\" class=\"data row79 col3\" >1.964532</td>\n",
-       "      <td id=\"T_230b2_row79_col4\" class=\"data row79 col4\" >69</td>\n",
-       "      <td id=\"T_230b2_row79_col5\" class=\"data row79 col5\" >79</td>\n",
-       "      <td id=\"T_230b2_row79_col6\" class=\"data row79 col6\" >-10</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row80\" class=\"row_heading level0 row80\" >zephyr-7b-alpha</th>\n",
-       "      <td id=\"T_230b2_row80_col0\" class=\"data row80 col0\" >1302</td>\n",
-       "      <td id=\"T_230b2_row80_col1\" class=\"data row80 col1\" >8.352664</td>\n",
-       "      <td id=\"T_230b2_row80_col2\" class=\"data row80 col2\" >10.289761</td>\n",
-       "      <td id=\"T_230b2_row80_col3\" class=\"data row80 col3\" >1.937097</td>\n",
-       "      <td id=\"T_230b2_row80_col4\" class=\"data row80 col4\" >70</td>\n",
-       "      <td id=\"T_230b2_row80_col5\" class=\"data row80 col5\" >80</td>\n",
-       "      <td id=\"T_230b2_row80_col6\" class=\"data row80 col6\" >-10</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row81\" class=\"row_heading level0 row81\" >openbuddy-llama-30b-v7.1</th>\n",
-       "      <td id=\"T_230b2_row81_col0\" class=\"data row81 col0\" >968</td>\n",
-       "      <td id=\"T_230b2_row81_col1\" class=\"data row81 col1\" >6.130015</td>\n",
-       "      <td id=\"T_230b2_row81_col2\" class=\"data row81 col2\" >10.214495</td>\n",
-       "      <td id=\"T_230b2_row81_col3\" class=\"data row81 col3\" >4.084480</td>\n",
-       "      <td id=\"T_230b2_row81_col4\" class=\"data row81 col4\" >94</td>\n",
-       "      <td id=\"T_230b2_row81_col5\" class=\"data row81 col5\" >81</td>\n",
-       "      <td id=\"T_230b2_row81_col6\" class=\"data row81 col6\" >13</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row82\" class=\"row_heading level0 row82\" >ultralm-13b-best-of-16</th>\n",
-       "      <td id=\"T_230b2_row82_col0\" class=\"data row82 col0\" >1980</td>\n",
-       "      <td id=\"T_230b2_row82_col1\" class=\"data row82 col1\" >11.307315</td>\n",
-       "      <td id=\"T_230b2_row82_col2\" class=\"data row82 col2\" >9.876089</td>\n",
-       "      <td id=\"T_230b2_row82_col3\" class=\"data row82 col3\" >-1.431226</td>\n",
-       "      <td id=\"T_230b2_row82_col4\" class=\"data row82 col4\" >48</td>\n",
-       "      <td id=\"T_230b2_row82_col5\" class=\"data row82 col5\" >82</td>\n",
-       "      <td id=\"T_230b2_row82_col6\" class=\"data row82 col6\" >-34</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row83\" class=\"row_heading level0 row83\" >oasst-sft-llama-33b</th>\n",
-       "      <td id=\"T_230b2_row83_col0\" class=\"data row83 col0\" >748</td>\n",
-       "      <td id=\"T_230b2_row83_col1\" class=\"data row83 col1\" >4.770391</td>\n",
-       "      <td id=\"T_230b2_row83_col2\" class=\"data row83 col2\" >9.866412</td>\n",
-       "      <td id=\"T_230b2_row83_col3\" class=\"data row83 col3\" >5.096021</td>\n",
-       "      <td id=\"T_230b2_row83_col4\" class=\"data row83 col4\" >104</td>\n",
-       "      <td id=\"T_230b2_row83_col5\" class=\"data row83 col5\" >83</td>\n",
-       "      <td id=\"T_230b2_row83_col6\" class=\"data row83 col6\" >21</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row84\" class=\"row_heading level0 row84\" >wizardlm-13b</th>\n",
-       "      <td id=\"T_230b2_row84_col0\" class=\"data row84 col0\" >985</td>\n",
-       "      <td id=\"T_230b2_row84_col1\" class=\"data row84 col1\" >5.878153</td>\n",
-       "      <td id=\"T_230b2_row84_col2\" class=\"data row84 col2\" >9.828151</td>\n",
-       "      <td id=\"T_230b2_row84_col3\" class=\"data row84 col3\" >3.949998</td>\n",
-       "      <td id=\"T_230b2_row84_col4\" class=\"data row84 col4\" >96</td>\n",
-       "      <td id=\"T_230b2_row84_col5\" class=\"data row84 col5\" >84</td>\n",
-       "      <td id=\"T_230b2_row84_col6\" class=\"data row84 col6\" >12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row85\" class=\"row_heading level0 row85\" >nous-hermes-13b</th>\n",
-       "      <td id=\"T_230b2_row85_col0\" class=\"data row85 col0\" >844</td>\n",
-       "      <td id=\"T_230b2_row85_col1\" class=\"data row85 col1\" >5.411879</td>\n",
-       "      <td id=\"T_230b2_row85_col2\" class=\"data row85 col2\" >9.717863</td>\n",
-       "      <td id=\"T_230b2_row85_col3\" class=\"data row85 col3\" >4.305984</td>\n",
-       "      <td id=\"T_230b2_row85_col4\" class=\"data row85 col4\" >99</td>\n",
-       "      <td id=\"T_230b2_row85_col5\" class=\"data row85 col5\" >85</td>\n",
-       "      <td id=\"T_230b2_row85_col6\" class=\"data row85 col6\" >14</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row86\" class=\"row_heading level0 row86\" >vicuna-13b</th>\n",
-       "      <td id=\"T_230b2_row86_col0\" class=\"data row86 col0\" >1037</td>\n",
-       "      <td id=\"T_230b2_row86_col1\" class=\"data row86 col1\" >5.831103</td>\n",
-       "      <td id=\"T_230b2_row86_col2\" class=\"data row86 col2\" >9.222060</td>\n",
-       "      <td id=\"T_230b2_row86_col3\" class=\"data row86 col3\" >3.390957</td>\n",
-       "      <td id=\"T_230b2_row86_col4\" class=\"data row86 col4\" >97</td>\n",
-       "      <td id=\"T_230b2_row86_col5\" class=\"data row86 col5\" >86</td>\n",
-       "      <td id=\"T_230b2_row86_col6\" class=\"data row86 col6\" >11</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row87\" class=\"row_heading level0 row87\" >tulu-2-dpo-7b</th>\n",
-       "      <td id=\"T_230b2_row87_col0\" class=\"data row87 col0\" >1663</td>\n",
-       "      <td id=\"T_230b2_row87_col1\" class=\"data row87 col1\" >8.197515</td>\n",
-       "      <td id=\"T_230b2_row87_col2\" class=\"data row87 col2\" >9.200266</td>\n",
-       "      <td id=\"T_230b2_row87_col3\" class=\"data row87 col3\" >1.002750</td>\n",
-       "      <td id=\"T_230b2_row87_col4\" class=\"data row87 col4\" >71</td>\n",
-       "      <td id=\"T_230b2_row87_col5\" class=\"data row87 col5\" >87</td>\n",
-       "      <td id=\"T_230b2_row87_col6\" class=\"data row87 col6\" >-16</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row88\" class=\"row_heading level0 row88\" >openbuddy-llama2-13b-v11.1</th>\n",
-       "      <td id=\"T_230b2_row88_col0\" class=\"data row88 col0\" >1057</td>\n",
-       "      <td id=\"T_230b2_row88_col1\" class=\"data row88 col1\" >6.174716</td>\n",
-       "      <td id=\"T_230b2_row88_col2\" class=\"data row88 col2\" >9.159090</td>\n",
-       "      <td id=\"T_230b2_row88_col3\" class=\"data row88 col3\" >2.984373</td>\n",
-       "      <td id=\"T_230b2_row88_col4\" class=\"data row88 col4\" >93</td>\n",
-       "      <td id=\"T_230b2_row88_col5\" class=\"data row88 col5\" >88</td>\n",
-       "      <td id=\"T_230b2_row88_col6\" class=\"data row88 col6\" >5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row89\" class=\"row_heading level0 row89\" >ultralm-13b-v2.0</th>\n",
-       "      <td id=\"T_230b2_row89_col0\" class=\"data row89 col0\" >1399</td>\n",
-       "      <td id=\"T_230b2_row89_col1\" class=\"data row89 col1\" >7.504623</td>\n",
-       "      <td id=\"T_230b2_row89_col2\" class=\"data row89 col2\" >9.129018</td>\n",
-       "      <td id=\"T_230b2_row89_col3\" class=\"data row89 col3\" >1.624396</td>\n",
-       "      <td id=\"T_230b2_row89_col4\" class=\"data row89 col4\" >78</td>\n",
-       "      <td id=\"T_230b2_row89_col5\" class=\"data row89 col5\" >89</td>\n",
-       "      <td id=\"T_230b2_row89_col6\" class=\"data row89 col6\" >-11</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row90\" class=\"row_heading level0 row90\" >text_davinci_001</th>\n",
-       "      <td id=\"T_230b2_row90_col0\" class=\"data row90 col0\" >296</td>\n",
-       "      <td id=\"T_230b2_row90_col1\" class=\"data row90 col1\" >2.764005</td>\n",
-       "      <td id=\"T_230b2_row90_col2\" class=\"data row90 col2\" >9.020601</td>\n",
-       "      <td id=\"T_230b2_row90_col3\" class=\"data row90 col3\" >6.256596</td>\n",
-       "      <td id=\"T_230b2_row90_col4\" class=\"data row90 col4\" >120</td>\n",
-       "      <td id=\"T_230b2_row90_col5\" class=\"data row90 col5\" >90</td>\n",
-       "      <td id=\"T_230b2_row90_col6\" class=\"data row90 col6\" >30</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row91\" class=\"row_heading level0 row91\" >openbuddy-falcon-40b-v9</th>\n",
-       "      <td id=\"T_230b2_row91_col0\" class=\"data row91 col0\" >1089</td>\n",
-       "      <td id=\"T_230b2_row91_col1\" class=\"data row91 col1\" >5.955743</td>\n",
-       "      <td id=\"T_230b2_row91_col2\" class=\"data row91 col2\" >8.988936</td>\n",
-       "      <td id=\"T_230b2_row91_col3\" class=\"data row91 col3\" >3.033194</td>\n",
-       "      <td id=\"T_230b2_row91_col4\" class=\"data row91 col4\" >95</td>\n",
-       "      <td id=\"T_230b2_row91_col5\" class=\"data row91 col5\" >91</td>\n",
-       "      <td id=\"T_230b2_row91_col6\" class=\"data row91 col6\" >4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row92\" class=\"row_heading level0 row92\" >openchat-13b</th>\n",
-       "      <td id=\"T_230b2_row92_col0\" class=\"data row92 col0\" >1632</td>\n",
-       "      <td id=\"T_230b2_row92_col1\" class=\"data row92 col1\" >8.022386</td>\n",
-       "      <td id=\"T_230b2_row92_col2\" class=\"data row92 col2\" >8.806053</td>\n",
-       "      <td id=\"T_230b2_row92_col3\" class=\"data row92 col3\" >0.783667</td>\n",
-       "      <td id=\"T_230b2_row92_col4\" class=\"data row92 col4\" >73</td>\n",
-       "      <td id=\"T_230b2_row92_col5\" class=\"data row92 col5\" >92</td>\n",
-       "      <td id=\"T_230b2_row92_col6\" class=\"data row92 col6\" >-19</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row93\" class=\"row_heading level0 row93\" >llama-2-13b-chat-hf</th>\n",
-       "      <td id=\"T_230b2_row93_col0\" class=\"data row93 col0\" >1513</td>\n",
-       "      <td id=\"T_230b2_row93_col1\" class=\"data row93 col1\" >7.702310</td>\n",
-       "      <td id=\"T_230b2_row93_col2\" class=\"data row93 col2\" >8.436015</td>\n",
-       "      <td id=\"T_230b2_row93_col3\" class=\"data row93 col3\" >0.733705</td>\n",
-       "      <td id=\"T_230b2_row93_col4\" class=\"data row93 col4\" >76</td>\n",
-       "      <td id=\"T_230b2_row93_col5\" class=\"data row93 col5\" >93</td>\n",
-       "      <td id=\"T_230b2_row93_col6\" class=\"data row93 col6\" >-17</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row94\" class=\"row_heading level0 row94\" >guanaco-65b</th>\n",
-       "      <td id=\"T_230b2_row94_col0\" class=\"data row94 col0\" >1249</td>\n",
-       "      <td id=\"T_230b2_row94_col1\" class=\"data row94 col1\" >6.858495</td>\n",
-       "      <td id=\"T_230b2_row94_col2\" class=\"data row94 col2\" >8.252917</td>\n",
-       "      <td id=\"T_230b2_row94_col3\" class=\"data row94 col3\" >1.394422</td>\n",
-       "      <td id=\"T_230b2_row94_col4\" class=\"data row94 col4\" >87</td>\n",
-       "      <td id=\"T_230b2_row94_col5\" class=\"data row94 col5\" >94</td>\n",
-       "      <td id=\"T_230b2_row94_col6\" class=\"data row94 col6\" >-7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row95\" class=\"row_heading level0 row95\" >opencoderplus-15b</th>\n",
-       "      <td id=\"T_230b2_row95_col0\" class=\"data row95 col0\" >1628</td>\n",
-       "      <td id=\"T_230b2_row95_col1\" class=\"data row95 col1\" >7.406222</td>\n",
-       "      <td id=\"T_230b2_row95_col2\" class=\"data row95 col2\" >8.152410</td>\n",
-       "      <td id=\"T_230b2_row95_col3\" class=\"data row95 col3\" >0.746188</td>\n",
-       "      <td id=\"T_230b2_row95_col4\" class=\"data row95 col4\" >83</td>\n",
-       "      <td id=\"T_230b2_row95_col5\" class=\"data row95 col5\" >95</td>\n",
-       "      <td id=\"T_230b2_row95_col6\" class=\"data row95 col6\" >-12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row96\" class=\"row_heading level0 row96\" >oasst-rlhf-llama-33b</th>\n",
-       "      <td id=\"T_230b2_row96_col0\" class=\"data row96 col0\" >1079</td>\n",
-       "      <td id=\"T_230b2_row96_col1\" class=\"data row96 col1\" >6.296435</td>\n",
-       "      <td id=\"T_230b2_row96_col2\" class=\"data row96 col2\" >7.970922</td>\n",
-       "      <td id=\"T_230b2_row96_col3\" class=\"data row96 col3\" >1.674487</td>\n",
-       "      <td id=\"T_230b2_row96_col4\" class=\"data row96 col4\" >92</td>\n",
-       "      <td id=\"T_230b2_row96_col5\" class=\"data row96 col5\" >96</td>\n",
-       "      <td id=\"T_230b2_row96_col6\" class=\"data row96 col6\" >-4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row97\" class=\"row_heading level0 row97\" >openchat8192-13b</th>\n",
-       "      <td id=\"T_230b2_row97_col0\" class=\"data row97 col0\" >1664</td>\n",
-       "      <td id=\"T_230b2_row97_col1\" class=\"data row97 col1\" >7.472767</td>\n",
-       "      <td id=\"T_230b2_row97_col2\" class=\"data row97 col2\" >7.897062</td>\n",
-       "      <td id=\"T_230b2_row97_col3\" class=\"data row97 col3\" >0.424295</td>\n",
-       "      <td id=\"T_230b2_row97_col4\" class=\"data row97 col4\" >80</td>\n",
-       "      <td id=\"T_230b2_row97_col5\" class=\"data row97 col5\" >97</td>\n",
-       "      <td id=\"T_230b2_row97_col6\" class=\"data row97 col6\" >-17</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row98\" class=\"row_heading level0 row98\" >phi-2-dpo</th>\n",
-       "      <td id=\"T_230b2_row98_col0\" class=\"data row98 col0\" >1687</td>\n",
-       "      <td id=\"T_230b2_row98_col1\" class=\"data row98 col1\" >7.757096</td>\n",
-       "      <td id=\"T_230b2_row98_col2\" class=\"data row98 col2\" >7.770895</td>\n",
-       "      <td id=\"T_230b2_row98_col3\" class=\"data row98 col3\" >0.013799</td>\n",
-       "      <td id=\"T_230b2_row98_col4\" class=\"data row98 col4\" >75</td>\n",
-       "      <td id=\"T_230b2_row98_col5\" class=\"data row98 col5\" >98</td>\n",
-       "      <td id=\"T_230b2_row98_col6\" class=\"data row98 col6\" >-23</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row99\" class=\"row_heading level0 row99\" >minichat-1.5-3b</th>\n",
-       "      <td id=\"T_230b2_row99_col0\" class=\"data row99 col0\" >1545</td>\n",
-       "      <td id=\"T_230b2_row99_col1\" class=\"data row99 col1\" >6.553443</td>\n",
-       "      <td id=\"T_230b2_row99_col2\" class=\"data row99 col2\" >7.701633</td>\n",
-       "      <td id=\"T_230b2_row99_col3\" class=\"data row99 col3\" >1.148190</td>\n",
-       "      <td id=\"T_230b2_row99_col4\" class=\"data row99 col4\" >90</td>\n",
-       "      <td id=\"T_230b2_row99_col5\" class=\"data row99 col5\" >99</td>\n",
-       "      <td id=\"T_230b2_row99_col6\" class=\"data row99 col6\" >-9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row100\" class=\"row_heading level0 row100\" >vicuna-7b-v1.5</th>\n",
-       "      <td id=\"T_230b2_row100_col0\" class=\"data row100 col0\" >1083</td>\n",
-       "      <td id=\"T_230b2_row100_col1\" class=\"data row100 col1\" >4.797494</td>\n",
-       "      <td id=\"T_230b2_row100_col2\" class=\"data row100 col2\" >7.616893</td>\n",
-       "      <td id=\"T_230b2_row100_col3\" class=\"data row100 col3\" >2.819399</td>\n",
-       "      <td id=\"T_230b2_row100_col4\" class=\"data row100 col4\" >103</td>\n",
-       "      <td id=\"T_230b2_row100_col5\" class=\"data row100 col5\" >100</td>\n",
-       "      <td id=\"T_230b2_row100_col6\" class=\"data row100 col6\" >3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row101\" class=\"row_heading level0 row101\" >llama-2-chat-7b-evol70k-neft</th>\n",
-       "      <td id=\"T_230b2_row101_col0\" class=\"data row101 col0\" >1612</td>\n",
-       "      <td id=\"T_230b2_row101_col1\" class=\"data row101 col1\" >7.602384</td>\n",
-       "      <td id=\"T_230b2_row101_col2\" class=\"data row101 col2\" >7.533053</td>\n",
-       "      <td id=\"T_230b2_row101_col3\" class=\"data row101 col3\" >-0.069331</td>\n",
-       "      <td id=\"T_230b2_row101_col4\" class=\"data row101 col4\" >77</td>\n",
-       "      <td id=\"T_230b2_row101_col5\" class=\"data row101 col5\" >101</td>\n",
-       "      <td id=\"T_230b2_row101_col6\" class=\"data row101 col6\" >-24</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row102\" class=\"row_heading level0 row102\" >recycled-wizardlm-7b-v2.0</th>\n",
-       "      <td id=\"T_230b2_row102_col0\" class=\"data row102 col0\" >1583</td>\n",
-       "      <td id=\"T_230b2_row102_col1\" class=\"data row102 col1\" >7.337129</td>\n",
-       "      <td id=\"T_230b2_row102_col2\" class=\"data row102 col2\" >7.521610</td>\n",
-       "      <td id=\"T_230b2_row102_col3\" class=\"data row102 col3\" >0.184481</td>\n",
-       "      <td id=\"T_230b2_row102_col4\" class=\"data row102 col4\" >84</td>\n",
-       "      <td id=\"T_230b2_row102_col5\" class=\"data row102 col5\" >102</td>\n",
-       "      <td id=\"T_230b2_row102_col6\" class=\"data row102 col6\" >-18</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row103\" class=\"row_heading level0 row103\" >vicuna-7b-v1.3</th>\n",
-       "      <td id=\"T_230b2_row103_col0\" class=\"data row103 col0\" >1110</td>\n",
-       "      <td id=\"T_230b2_row103_col1\" class=\"data row103 col1\" >4.642512</td>\n",
-       "      <td id=\"T_230b2_row103_col2\" class=\"data row103 col2\" >7.156461</td>\n",
-       "      <td id=\"T_230b2_row103_col3\" class=\"data row103 col3\" >2.513949</td>\n",
-       "      <td id=\"T_230b2_row103_col4\" class=\"data row103 col4\" >105</td>\n",
-       "      <td id=\"T_230b2_row103_col5\" class=\"data row103 col5\" >103</td>\n",
-       "      <td id=\"T_230b2_row103_col6\" class=\"data row103 col6\" >2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row104\" class=\"row_heading level0 row104\" >alpaca-farm-ppo-sim-gpt4-20k</th>\n",
-       "      <td id=\"T_230b2_row104_col0\" class=\"data row104 col0\" >511</td>\n",
-       "      <td id=\"T_230b2_row104_col1\" class=\"data row104 col1\" >3.450342</td>\n",
-       "      <td id=\"T_230b2_row104_col2\" class=\"data row104 col2\" >7.121808</td>\n",
-       "      <td id=\"T_230b2_row104_col3\" class=\"data row104 col3\" >3.671466</td>\n",
-       "      <td id=\"T_230b2_row104_col4\" class=\"data row104 col4\" >113</td>\n",
-       "      <td id=\"T_230b2_row104_col5\" class=\"data row104 col5\" >104</td>\n",
-       "      <td id=\"T_230b2_row104_col6\" class=\"data row104 col6\" >9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row105\" class=\"row_heading level0 row105\" >ultralm-13b</th>\n",
-       "      <td id=\"T_230b2_row105_col0\" class=\"data row105 col0\" >1087</td>\n",
-       "      <td id=\"T_230b2_row105_col1\" class=\"data row105 col1\" >5.074590</td>\n",
-       "      <td id=\"T_230b2_row105_col2\" class=\"data row105 col2\" >7.108191</td>\n",
-       "      <td id=\"T_230b2_row105_col3\" class=\"data row105 col3\" >2.033601</td>\n",
-       "      <td id=\"T_230b2_row105_col4\" class=\"data row105 col4\" >100</td>\n",
-       "      <td id=\"T_230b2_row105_col5\" class=\"data row105 col5\" >105</td>\n",
-       "      <td id=\"T_230b2_row105_col6\" class=\"data row105 col6\" >-5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row106\" class=\"row_heading level0 row106\" >baize-v2-13b</th>\n",
-       "      <td id=\"T_230b2_row106_col0\" class=\"data row106 col0\" >930</td>\n",
-       "      <td id=\"T_230b2_row106_col1\" class=\"data row106 col1\" >4.590545</td>\n",
-       "      <td id=\"T_230b2_row106_col2\" class=\"data row106 col2\" >7.012247</td>\n",
-       "      <td id=\"T_230b2_row106_col3\" class=\"data row106 col3\" >2.421702</td>\n",
-       "      <td id=\"T_230b2_row106_col4\" class=\"data row106 col4\" >106</td>\n",
-       "      <td id=\"T_230b2_row106_col5\" class=\"data row106 col5\" >106</td>\n",
-       "      <td id=\"T_230b2_row106_col6\" class=\"data row106 col6\" >0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row107\" class=\"row_heading level0 row107\" >recycled-wizardlm-7b-v1.0</th>\n",
-       "      <td id=\"T_230b2_row107_col0\" class=\"data row107 col0\" >1494</td>\n",
-       "      <td id=\"T_230b2_row107_col1\" class=\"data row107 col1\" >6.632750</td>\n",
-       "      <td id=\"T_230b2_row107_col2\" class=\"data row107 col2\" >6.901477</td>\n",
-       "      <td id=\"T_230b2_row107_col3\" class=\"data row107 col3\" >0.268727</td>\n",
-       "      <td id=\"T_230b2_row107_col4\" class=\"data row107 col4\" >89</td>\n",
-       "      <td id=\"T_230b2_row107_col5\" class=\"data row107 col5\" >107</td>\n",
-       "      <td id=\"T_230b2_row107_col6\" class=\"data row107 col6\" >-18</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row108\" class=\"row_heading level0 row108\" >alpaca-7b_verbose</th>\n",
-       "      <td id=\"T_230b2_row108_col0\" class=\"data row108 col0\" >537</td>\n",
-       "      <td id=\"T_230b2_row108_col1\" class=\"data row108 col1\" >2.933102</td>\n",
-       "      <td id=\"T_230b2_row108_col2\" class=\"data row108 col2\" >6.818464</td>\n",
-       "      <td id=\"T_230b2_row108_col3\" class=\"data row108 col3\" >3.885363</td>\n",
-       "      <td id=\"T_230b2_row108_col4\" class=\"data row108 col4\" >118</td>\n",
-       "      <td id=\"T_230b2_row108_col5\" class=\"data row108 col5\" >108</td>\n",
-       "      <td id=\"T_230b2_row108_col6\" class=\"data row108 col6\" >10</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row109\" class=\"row_heading level0 row109\" >alpaca-farm-ppo-human</th>\n",
-       "      <td id=\"T_230b2_row109_col0\" class=\"data row109 col0\" >803</td>\n",
-       "      <td id=\"T_230b2_row109_col1\" class=\"data row109 col1\" >4.100427</td>\n",
-       "      <td id=\"T_230b2_row109_col2\" class=\"data row109 col2\" >6.418603</td>\n",
-       "      <td id=\"T_230b2_row109_col3\" class=\"data row109 col3\" >2.318176</td>\n",
-       "      <td id=\"T_230b2_row109_col4\" class=\"data row109 col4\" >108</td>\n",
-       "      <td id=\"T_230b2_row109_col5\" class=\"data row109 col5\" >109</td>\n",
-       "      <td id=\"T_230b2_row109_col6\" class=\"data row109 col6\" >-1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row110\" class=\"row_heading level0 row110\" >vicuna-7b</th>\n",
-       "      <td id=\"T_230b2_row110_col0\" class=\"data row110 col0\" >1044</td>\n",
-       "      <td id=\"T_230b2_row110_col1\" class=\"data row110 col1\" >4.162611</td>\n",
-       "      <td id=\"T_230b2_row110_col2\" class=\"data row110 col2\" >6.277218</td>\n",
-       "      <td id=\"T_230b2_row110_col3\" class=\"data row110 col3\" >2.114607</td>\n",
-       "      <td id=\"T_230b2_row110_col4\" class=\"data row110 col4\" >107</td>\n",
-       "      <td id=\"T_230b2_row110_col5\" class=\"data row110 col5\" >110</td>\n",
-       "      <td id=\"T_230b2_row110_col6\" class=\"data row110 col6\" >-3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row111\" class=\"row_heading level0 row111\" >alpaca-7b</th>\n",
-       "      <td id=\"T_230b2_row111_col0\" class=\"data row111 col0\" >396</td>\n",
-       "      <td id=\"T_230b2_row111_col1\" class=\"data row111 col1\" >2.591451</td>\n",
-       "      <td id=\"T_230b2_row111_col2\" class=\"data row111 col2\" >5.875487</td>\n",
-       "      <td id=\"T_230b2_row111_col3\" class=\"data row111 col3\" >3.284037</td>\n",
-       "      <td id=\"T_230b2_row111_col4\" class=\"data row111 col4\" >122</td>\n",
-       "      <td id=\"T_230b2_row111_col5\" class=\"data row111 col5\" >111</td>\n",
-       "      <td id=\"T_230b2_row111_col6\" class=\"data row111 col6\" >11</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row112\" class=\"row_heading level0 row112\" >phi-2-sft</th>\n",
-       "      <td id=\"T_230b2_row112_col0\" class=\"data row112 col0\" >1068</td>\n",
-       "      <td id=\"T_230b2_row112_col1\" class=\"data row112 col1\" >3.977568</td>\n",
-       "      <td id=\"T_230b2_row112_col2\" class=\"data row112 col2\" >5.853788</td>\n",
-       "      <td id=\"T_230b2_row112_col3\" class=\"data row112 col3\" >1.876220</td>\n",
-       "      <td id=\"T_230b2_row112_col4\" class=\"data row112 col4\" >109</td>\n",
-       "      <td id=\"T_230b2_row112_col5\" class=\"data row112 col5\" >112</td>\n",
-       "      <td id=\"T_230b2_row112_col6\" class=\"data row112 col6\" >-3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row113\" class=\"row_heading level0 row113\" >minichat-3b</th>\n",
-       "      <td id=\"T_230b2_row113_col0\" class=\"data row113 col0\" >868</td>\n",
-       "      <td id=\"T_230b2_row113_col1\" class=\"data row113 col1\" >3.007151</td>\n",
-       "      <td id=\"T_230b2_row113_col2\" class=\"data row113 col2\" >5.729333</td>\n",
-       "      <td id=\"T_230b2_row113_col3\" class=\"data row113 col3\" >2.722182</td>\n",
-       "      <td id=\"T_230b2_row113_col4\" class=\"data row113 col4\" >117</td>\n",
-       "      <td id=\"T_230b2_row113_col5\" class=\"data row113 col5\" >113</td>\n",
-       "      <td id=\"T_230b2_row113_col6\" class=\"data row113 col6\" >4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row114\" class=\"row_heading level0 row114\" >guanaco-33b</th>\n",
-       "      <td id=\"T_230b2_row114_col0\" class=\"data row114 col0\" >1311</td>\n",
-       "      <td id=\"T_230b2_row114_col1\" class=\"data row114 col1\" >5.002494</td>\n",
-       "      <td id=\"T_230b2_row114_col2\" class=\"data row114 col2\" >5.690019</td>\n",
-       "      <td id=\"T_230b2_row114_col3\" class=\"data row114 col3\" >0.687525</td>\n",
-       "      <td id=\"T_230b2_row114_col4\" class=\"data row114 col4\" >101</td>\n",
-       "      <td id=\"T_230b2_row114_col5\" class=\"data row114 col5\" >114</td>\n",
-       "      <td id=\"T_230b2_row114_col6\" class=\"data row114 col6\" >-13</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row115\" class=\"row_heading level0 row115\" >falcon-40b-instruct</th>\n",
-       "      <td id=\"T_230b2_row115_col0\" class=\"data row115 col0\" >662</td>\n",
-       "      <td id=\"T_230b2_row115_col1\" class=\"data row115 col1\" >3.342919</td>\n",
-       "      <td id=\"T_230b2_row115_col2\" class=\"data row115 col2\" >5.607533</td>\n",
-       "      <td id=\"T_230b2_row115_col3\" class=\"data row115 col3\" >2.264614</td>\n",
-       "      <td id=\"T_230b2_row115_col4\" class=\"data row115 col4\" >116</td>\n",
-       "      <td id=\"T_230b2_row115_col5\" class=\"data row115 col5\" >115</td>\n",
-       "      <td id=\"T_230b2_row115_col6\" class=\"data row115 col6\" >1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row116\" class=\"row_heading level0 row116\" >gemma-2b-it</th>\n",
-       "      <td id=\"T_230b2_row116_col0\" class=\"data row116 col0\" >1041</td>\n",
-       "      <td id=\"T_230b2_row116_col1\" class=\"data row116 col1\" >3.401971</td>\n",
-       "      <td id=\"T_230b2_row116_col2\" class=\"data row116 col2\" >5.596482</td>\n",
-       "      <td id=\"T_230b2_row116_col3\" class=\"data row116 col3\" >2.194511</td>\n",
-       "      <td id=\"T_230b2_row116_col4\" class=\"data row116 col4\" >115</td>\n",
-       "      <td id=\"T_230b2_row116_col5\" class=\"data row116 col5\" >116</td>\n",
-       "      <td id=\"T_230b2_row116_col6\" class=\"data row116 col6\" >-1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row117\" class=\"row_heading level0 row117\" >llama-2-7b-chat-hf</th>\n",
-       "      <td id=\"T_230b2_row117_col0\" class=\"data row117 col0\" >1479</td>\n",
-       "      <td id=\"T_230b2_row117_col1\" class=\"data row117 col1\" >4.961340</td>\n",
-       "      <td id=\"T_230b2_row117_col2\" class=\"data row117 col2\" >5.354821</td>\n",
-       "      <td id=\"T_230b2_row117_col3\" class=\"data row117 col3\" >0.393482</td>\n",
-       "      <td id=\"T_230b2_row117_col4\" class=\"data row117 col4\" >102</td>\n",
-       "      <td id=\"T_230b2_row117_col5\" class=\"data row117 col5\" >117</td>\n",
-       "      <td id=\"T_230b2_row117_col6\" class=\"data row117 col6\" >-15</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row118\" class=\"row_heading level0 row118\" >openbuddy-falcon-7b-v6</th>\n",
-       "      <td id=\"T_230b2_row118_col0\" class=\"data row118 col0\" >1152</td>\n",
-       "      <td id=\"T_230b2_row118_col1\" class=\"data row118 col1\" >3.521174</td>\n",
-       "      <td id=\"T_230b2_row118_col2\" class=\"data row118 col2\" >4.826124</td>\n",
-       "      <td id=\"T_230b2_row118_col3\" class=\"data row118 col3\" >1.304950</td>\n",
-       "      <td id=\"T_230b2_row118_col4\" class=\"data row118 col4\" >111</td>\n",
-       "      <td id=\"T_230b2_row118_col5\" class=\"data row118 col5\" >118</td>\n",
-       "      <td id=\"T_230b2_row118_col6\" class=\"data row118 col6\" >-7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row119\" class=\"row_heading level0 row119\" >alpaca-7b_concise</th>\n",
-       "      <td id=\"T_230b2_row119_col0\" class=\"data row119 col0\" >351</td>\n",
-       "      <td id=\"T_230b2_row119_col1\" class=\"data row119 col1\" >1.991176</td>\n",
-       "      <td id=\"T_230b2_row119_col2\" class=\"data row119 col2\" >4.463108</td>\n",
-       "      <td id=\"T_230b2_row119_col3\" class=\"data row119 col3\" >2.471931</td>\n",
-       "      <td id=\"T_230b2_row119_col4\" class=\"data row119 col4\" >127</td>\n",
-       "      <td id=\"T_230b2_row119_col5\" class=\"data row119 col5\" >119</td>\n",
-       "      <td id=\"T_230b2_row119_col6\" class=\"data row119 col6\" >8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row120\" class=\"row_heading level0 row120\" >phi-2</th>\n",
-       "      <td id=\"T_230b2_row120_col0\" class=\"data row120 col0\" >626</td>\n",
-       "      <td id=\"T_230b2_row120_col1\" class=\"data row120 col1\" >2.350210</td>\n",
-       "      <td id=\"T_230b2_row120_col2\" class=\"data row120 col2\" >4.395548</td>\n",
-       "      <td id=\"T_230b2_row120_col3\" class=\"data row120 col3\" >2.045338</td>\n",
-       "      <td id=\"T_230b2_row120_col4\" class=\"data row120 col4\" >124</td>\n",
-       "      <td id=\"T_230b2_row120_col5\" class=\"data row120 col5\" >120</td>\n",
-       "      <td id=\"T_230b2_row120_col6\" class=\"data row120 col6\" >4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row121\" class=\"row_heading level0 row121\" >baize-v2-7b</th>\n",
-       "      <td id=\"T_230b2_row121_col0\" class=\"data row121 col0\" >1127</td>\n",
-       "      <td id=\"T_230b2_row121_col1\" class=\"data row121 col1\" >3.404815</td>\n",
-       "      <td id=\"T_230b2_row121_col2\" class=\"data row121 col2\" >4.382565</td>\n",
-       "      <td id=\"T_230b2_row121_col3\" class=\"data row121 col3\" >0.977750</td>\n",
-       "      <td id=\"T_230b2_row121_col4\" class=\"data row121 col4\" >114</td>\n",
-       "      <td id=\"T_230b2_row121_col5\" class=\"data row121 col5\" >121</td>\n",
-       "      <td id=\"T_230b2_row121_col6\" class=\"data row121 col6\" >-7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row122\" class=\"row_heading level0 row122\" >chatglm2-6b</th>\n",
-       "      <td id=\"T_230b2_row122_col0\" class=\"data row122 col0\" >1027</td>\n",
-       "      <td id=\"T_230b2_row122_col1\" class=\"data row122 col1\" >2.762185</td>\n",
-       "      <td id=\"T_230b2_row122_col2\" class=\"data row122 col2\" >4.359283</td>\n",
-       "      <td id=\"T_230b2_row122_col3\" class=\"data row122 col3\" >1.597098</td>\n",
-       "      <td id=\"T_230b2_row122_col4\" class=\"data row122 col4\" >121</td>\n",
-       "      <td id=\"T_230b2_row122_col5\" class=\"data row122 col5\" >122</td>\n",
-       "      <td id=\"T_230b2_row122_col6\" class=\"data row122 col6\" >-1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row123\" class=\"row_heading level0 row123\" >pythia-12b-mix-sft</th>\n",
-       "      <td id=\"T_230b2_row123_col0\" class=\"data row123 col0\" >913</td>\n",
-       "      <td id=\"T_230b2_row123_col1\" class=\"data row123 col1\" >2.578090</td>\n",
-       "      <td id=\"T_230b2_row123_col2\" class=\"data row123 col2\" >4.221362</td>\n",
-       "      <td id=\"T_230b2_row123_col3\" class=\"data row123 col3\" >1.643272</td>\n",
-       "      <td id=\"T_230b2_row123_col4\" class=\"data row123 col4\" >123</td>\n",
-       "      <td id=\"T_230b2_row123_col5\" class=\"data row123 col5\" >123</td>\n",
-       "      <td id=\"T_230b2_row123_col6\" class=\"data row123 col6\" >0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row124\" class=\"row_heading level0 row124\" >falcon-7b-instruct</th>\n",
-       "      <td id=\"T_230b2_row124_col0\" class=\"data row124 col0\" >478</td>\n",
-       "      <td id=\"T_230b2_row124_col1\" class=\"data row124 col1\" >2.146618</td>\n",
-       "      <td id=\"T_230b2_row124_col2\" class=\"data row124 col2\" >4.036938</td>\n",
-       "      <td id=\"T_230b2_row124_col3\" class=\"data row124 col3\" >1.890320</td>\n",
-       "      <td id=\"T_230b2_row124_col4\" class=\"data row124 col4\" >125</td>\n",
-       "      <td id=\"T_230b2_row124_col5\" class=\"data row124 col5\" >124</td>\n",
-       "      <td id=\"T_230b2_row124_col6\" class=\"data row124 col6\" >1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row125\" class=\"row_heading level0 row125\" >oasst-sft-pythia-12b</th>\n",
-       "      <td id=\"T_230b2_row125_col0\" class=\"data row125 col0\" >726</td>\n",
-       "      <td id=\"T_230b2_row125_col1\" class=\"data row125 col1\" >1.790114</td>\n",
-       "      <td id=\"T_230b2_row125_col2\" class=\"data row125 col2\" >3.270102</td>\n",
-       "      <td id=\"T_230b2_row125_col3\" class=\"data row125 col3\" >1.479988</td>\n",
-       "      <td id=\"T_230b2_row125_col4\" class=\"data row125 col4\" >128</td>\n",
-       "      <td id=\"T_230b2_row125_col5\" class=\"data row125 col5\" >125</td>\n",
-       "      <td id=\"T_230b2_row125_col6\" class=\"data row125 col6\" >3</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row126\" class=\"row_heading level0 row126\" >guanaco-13b</th>\n",
-       "      <td id=\"T_230b2_row126_col0\" class=\"data row126 col0\" >1774</td>\n",
-       "      <td id=\"T_230b2_row126_col1\" class=\"data row126 col1\" >3.469597</td>\n",
-       "      <td id=\"T_230b2_row126_col2\" class=\"data row126 col2\" >3.003787</td>\n",
-       "      <td id=\"T_230b2_row126_col3\" class=\"data row126 col3\" >-0.465810</td>\n",
-       "      <td id=\"T_230b2_row126_col4\" class=\"data row126 col4\" >112</td>\n",
-       "      <td id=\"T_230b2_row126_col5\" class=\"data row126 col5\" >126</td>\n",
-       "      <td id=\"T_230b2_row126_col6\" class=\"data row126 col6\" >-14</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row127\" class=\"row_heading level0 row127\" >guanaco-7b</th>\n",
-       "      <td id=\"T_230b2_row127_col0\" class=\"data row127 col0\" >1364</td>\n",
-       "      <td id=\"T_230b2_row127_col1\" class=\"data row127 col1\" >2.880002</td>\n",
-       "      <td id=\"T_230b2_row127_col2\" class=\"data row127 col2\" >2.871117</td>\n",
-       "      <td id=\"T_230b2_row127_col3\" class=\"data row127 col3\" >-0.008885</td>\n",
-       "      <td id=\"T_230b2_row127_col4\" class=\"data row127 col4\" >119</td>\n",
-       "      <td id=\"T_230b2_row127_col5\" class=\"data row127 col5\" >127</td>\n",
-       "      <td id=\"T_230b2_row127_col6\" class=\"data row127 col6\" >-8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th id=\"T_230b2_level0_row128\" class=\"row_heading level0 row128\" >baichuan-13b-chat</th>\n",
-       "      <td id=\"T_230b2_row128_col0\" class=\"data row128 col0\" >1727</td>\n",
-       "      <td id=\"T_230b2_row128_col1\" class=\"data row128 col1\" >1.992146</td>\n",
-       "      <td id=\"T_230b2_row128_col2\" class=\"data row128 col2\" >2.062170</td>\n",
-       "      <td id=\"T_230b2_row128_col3\" class=\"data row128 col3\" >0.070025</td>\n",
-       "      <td id=\"T_230b2_row128_col4\" class=\"data row128 col4\" >126</td>\n",
-       "      <td id=\"T_230b2_row128_col5\" class=\"data row128 col5\" >128</td>\n",
-       "      <td id=\"T_230b2_row128_col6\" class=\"data row128 col6\" >-2</td>\n",
+       "      <th id=\"T_0026f_level0_row0\" class=\"row_heading level0 row0\" >gpt4_1106_preview_verbose</th>\n",
+       "      <td id=\"T_0026f_row0_col0\" class=\"data row0 col0\" >2402</td>\n",
+       "      <td id=\"T_0026f_row0_col1\" class=\"data row0 col1\" >64.303601</td>\n",
+       "      <td id=\"T_0026f_row0_col2\" class=\"data row0 col2\" >51.575008</td>\n",
+       "      <td id=\"T_0026f_row0_col3\" class=\"data row0 col3\" >-12.728593</td>\n",
+       "      <td id=\"T_0026f_row0_col4\" class=\"data row0 col4\" >0</td>\n",
+       "      <td id=\"T_0026f_row0_col5\" class=\"data row0 col5\" >0</td>\n",
+       "      <td id=\"T_0026f_row0_col6\" class=\"data row0 col6\" >0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row1\" class=\"row_heading level0 row1\" >gpt4_1106_preview</th>\n",
+       "      <td id=\"T_0026f_row1_col0\" class=\"data row1 col0\" >2049</td>\n",
+       "      <td id=\"T_0026f_row1_col1\" class=\"data row1 col1\" >50.000000</td>\n",
+       "      <td id=\"T_0026f_row1_col2\" class=\"data row1 col2\" >50.000000</td>\n",
+       "      <td id=\"T_0026f_row1_col3\" class=\"data row1 col3\" >0.000000</td>\n",
+       "      <td id=\"T_0026f_row1_col4\" class=\"data row1 col4\" >1</td>\n",
+       "      <td id=\"T_0026f_row1_col5\" class=\"data row1 col5\" >1</td>\n",
+       "      <td id=\"T_0026f_row1_col6\" class=\"data row1 col6\" >0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row2\" class=\"row_heading level0 row2\" >gpt4_1106_preview_concise</th>\n",
+       "      <td id=\"T_0026f_row2_col0\" class=\"data row2 col0\" >1136</td>\n",
+       "      <td id=\"T_0026f_row2_col1\" class=\"data row2 col1\" >22.920194</td>\n",
+       "      <td id=\"T_0026f_row2_col2\" class=\"data row2 col2\" >41.896602</td>\n",
+       "      <td id=\"T_0026f_row2_col3\" class=\"data row2 col3\" >18.976407</td>\n",
+       "      <td id=\"T_0026f_row2_col4\" class=\"data row2 col4\" >14</td>\n",
+       "      <td id=\"T_0026f_row2_col5\" class=\"data row2 col5\" >2</td>\n",
+       "      <td id=\"T_0026f_row2_col6\" class=\"data row2 col6\" >12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row3\" class=\"row_heading level0 row3\" >claude-3-opus-20240229</th>\n",
+       "      <td id=\"T_0026f_row3_col0\" class=\"data row3 col0\" >1388</td>\n",
+       "      <td id=\"T_0026f_row3_col1\" class=\"data row3 col1\" >29.041764</td>\n",
+       "      <td id=\"T_0026f_row3_col2\" class=\"data row3 col2\" >40.391776</td>\n",
+       "      <td id=\"T_0026f_row3_col3\" class=\"data row3 col3\" >11.350012</td>\n",
+       "      <td id=\"T_0026f_row3_col4\" class=\"data row3 col4\" >7</td>\n",
+       "      <td id=\"T_0026f_row3_col5\" class=\"data row3 col5\" >3</td>\n",
+       "      <td id=\"T_0026f_row3_col6\" class=\"data row3 col6\" >4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row4\" class=\"row_heading level0 row4\" >gpt4</th>\n",
+       "      <td id=\"T_0026f_row4_col0\" class=\"data row4 col0\" >1365</td>\n",
+       "      <td id=\"T_0026f_row4_col1\" class=\"data row4 col1\" >23.576789</td>\n",
+       "      <td id=\"T_0026f_row4_col2\" class=\"data row4 col2\" >38.128090</td>\n",
+       "      <td id=\"T_0026f_row4_col3\" class=\"data row4 col3\" >14.551300</td>\n",
+       "      <td id=\"T_0026f_row4_col4\" class=\"data row4 col4\" >12</td>\n",
+       "      <td id=\"T_0026f_row4_col5\" class=\"data row4 col5\" >4</td>\n",
+       "      <td id=\"T_0026f_row4_col6\" class=\"data row4 col6\" >8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row5\" class=\"row_heading level0 row5\" >Qwen1.5-72B-Chat</th>\n",
+       "      <td id=\"T_0026f_row5_col0\" class=\"data row5 col0\" >1549</td>\n",
+       "      <td id=\"T_0026f_row5_col1\" class=\"data row5 col1\" >26.498283</td>\n",
+       "      <td id=\"T_0026f_row5_col2\" class=\"data row5 col2\" >36.571754</td>\n",
+       "      <td id=\"T_0026f_row5_col3\" class=\"data row5 col3\" >10.073471</td>\n",
+       "      <td id=\"T_0026f_row5_col4\" class=\"data row5 col4\" >8</td>\n",
+       "      <td id=\"T_0026f_row5_col5\" class=\"data row5 col5\" >5</td>\n",
+       "      <td id=\"T_0026f_row5_col6\" class=\"data row5 col6\" >3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row6\" class=\"row_heading level0 row6\" >gpt4_0314</th>\n",
+       "      <td id=\"T_0026f_row6_col0\" class=\"data row6 col0\" >1371</td>\n",
+       "      <td id=\"T_0026f_row6_col1\" class=\"data row6 col1\" >22.073259</td>\n",
+       "      <td id=\"T_0026f_row6_col2\" class=\"data row6 col2\" >35.307061</td>\n",
+       "      <td id=\"T_0026f_row6_col3\" class=\"data row6 col3\" >13.233802</td>\n",
+       "      <td id=\"T_0026f_row6_col4\" class=\"data row6 col4\" >15</td>\n",
+       "      <td id=\"T_0026f_row6_col5\" class=\"data row6 col5\" >6</td>\n",
+       "      <td id=\"T_0026f_row6_col6\" class=\"data row6 col6\" >9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row7\" class=\"row_heading level0 row7\" >claude-3-sonnet-20240229</th>\n",
+       "      <td id=\"T_0026f_row7_col0\" class=\"data row7 col0\" >1420</td>\n",
+       "      <td id=\"T_0026f_row7_col1\" class=\"data row7 col1\" >25.556325</td>\n",
+       "      <td id=\"T_0026f_row7_col2\" class=\"data row7 col2\" >34.872474</td>\n",
+       "      <td id=\"T_0026f_row7_col3\" class=\"data row7 col3\" >9.316149</td>\n",
+       "      <td id=\"T_0026f_row7_col4\" class=\"data row7 col4\" >9</td>\n",
+       "      <td id=\"T_0026f_row7_col5\" class=\"data row7 col5\" >7</td>\n",
+       "      <td id=\"T_0026f_row7_col6\" class=\"data row7 col6\" >2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row8\" class=\"row_heading level0 row8\" >gpt4_0613_verbose</th>\n",
+       "      <td id=\"T_0026f_row8_col0\" class=\"data row8 col0\" >1473</td>\n",
+       "      <td id=\"T_0026f_row8_col1\" class=\"data row8 col1\" >23.237360</td>\n",
+       "      <td id=\"T_0026f_row8_col2\" class=\"data row8 col2\" >33.821267</td>\n",
+       "      <td id=\"T_0026f_row8_col3\" class=\"data row8 col3\" >10.583907</td>\n",
+       "      <td id=\"T_0026f_row8_col4\" class=\"data row8 col4\" >13</td>\n",
+       "      <td id=\"T_0026f_row8_col5\" class=\"data row8 col5\" >8</td>\n",
+       "      <td id=\"T_0026f_row8_col6\" class=\"data row8 col6\" >5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row9\" class=\"row_heading level0 row9\" >mistral-large-2402</th>\n",
+       "      <td id=\"T_0026f_row9_col0\" class=\"data row9 col0\" >1362</td>\n",
+       "      <td id=\"T_0026f_row9_col1\" class=\"data row9 col1\" >21.438776</td>\n",
+       "      <td id=\"T_0026f_row9_col2\" class=\"data row9 col2\" >32.652080</td>\n",
+       "      <td id=\"T_0026f_row9_col3\" class=\"data row9 col3\" >11.213304</td>\n",
+       "      <td id=\"T_0026f_row9_col4\" class=\"data row9 col4\" >19</td>\n",
+       "      <td id=\"T_0026f_row9_col5\" class=\"data row9 col5\" >9</td>\n",
+       "      <td id=\"T_0026f_row9_col6\" class=\"data row9 col6\" >10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row10\" class=\"row_heading level0 row10\" >claude-2.1_verbose</th>\n",
+       "      <td id=\"T_0026f_row10_col0\" class=\"data row10 col0\" >1414</td>\n",
+       "      <td id=\"T_0026f_row10_col1\" class=\"data row10 col1\" >24.354071</td>\n",
+       "      <td id=\"T_0026f_row10_col2\" class=\"data row10 col2\" >30.291179</td>\n",
+       "      <td id=\"T_0026f_row10_col3\" class=\"data row10 col3\" >5.937108</td>\n",
+       "      <td id=\"T_0026f_row10_col4\" class=\"data row10 col4\" >11</td>\n",
+       "      <td id=\"T_0026f_row10_col5\" class=\"data row10 col5\" >10</td>\n",
+       "      <td id=\"T_0026f_row10_col6\" class=\"data row10 col6\" >1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row11\" class=\"row_heading level0 row11\" >gpt4_0613</th>\n",
+       "      <td id=\"T_0026f_row11_col0\" class=\"data row11 col0\" >1140</td>\n",
+       "      <td id=\"T_0026f_row11_col1\" class=\"data row11 col1\" >15.755038</td>\n",
+       "      <td id=\"T_0026f_row11_col2\" class=\"data row11 col2\" >30.183322</td>\n",
+       "      <td id=\"T_0026f_row11_col3\" class=\"data row11 col3\" >14.428284</td>\n",
+       "      <td id=\"T_0026f_row11_col4\" class=\"data row11 col4\" >30</td>\n",
+       "      <td id=\"T_0026f_row11_col5\" class=\"data row11 col5\" >11</td>\n",
+       "      <td id=\"T_0026f_row11_col6\" class=\"data row11 col6\" >19</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row12\" class=\"row_heading level0 row12\" >Snorkel-Mistral-PairRM-DPO-best-of-16</th>\n",
+       "      <td id=\"T_0026f_row12_col0\" class=\"data row12 col0\" >2616</td>\n",
+       "      <td id=\"T_0026f_row12_col1\" class=\"data row12 col1\" >34.860133</td>\n",
+       "      <td id=\"T_0026f_row12_col2\" class=\"data row12 col2\" >29.974322</td>\n",
+       "      <td id=\"T_0026f_row12_col3\" class=\"data row12 col3\" >-4.885811</td>\n",
+       "      <td id=\"T_0026f_row12_col4\" class=\"data row12 col4\" >2</td>\n",
+       "      <td id=\"T_0026f_row12_col5\" class=\"data row12 col5\" >12</td>\n",
+       "      <td id=\"T_0026f_row12_col6\" class=\"data row12 col6\" >-10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row13\" class=\"row_heading level0 row13\" >Contextual-KTO-Mistral-PairRM</th>\n",
+       "      <td id=\"T_0026f_row13_col0\" class=\"data row13 col0\" >2521</td>\n",
+       "      <td id=\"T_0026f_row13_col1\" class=\"data row13 col1\" >33.227355</td>\n",
+       "      <td id=\"T_0026f_row13_col2\" class=\"data row13 col2\" >29.705809</td>\n",
+       "      <td id=\"T_0026f_row13_col3\" class=\"data row13 col3\" >-3.521546</td>\n",
+       "      <td id=\"T_0026f_row13_col4\" class=\"data row13 col4\" >3</td>\n",
+       "      <td id=\"T_0026f_row13_col5\" class=\"data row13 col5\" >13</td>\n",
+       "      <td id=\"T_0026f_row13_col6\" class=\"data row13 col6\" >-10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row14\" class=\"row_heading level0 row14\" >pairrm-Yi-34B-Chat</th>\n",
+       "      <td id=\"T_0026f_row14_col0\" class=\"data row14 col0\" >2195</td>\n",
+       "      <td id=\"T_0026f_row14_col1\" class=\"data row14 col1\" >31.241283</td>\n",
+       "      <td id=\"T_0026f_row14_col2\" class=\"data row14 col2\" >28.814841</td>\n",
+       "      <td id=\"T_0026f_row14_col3\" class=\"data row14 col3\" >-2.426442</td>\n",
+       "      <td id=\"T_0026f_row14_col4\" class=\"data row14 col4\" >4</td>\n",
+       "      <td id=\"T_0026f_row14_col5\" class=\"data row14 col5\" >14</td>\n",
+       "      <td id=\"T_0026f_row14_col6\" class=\"data row14 col6\" >-10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row15\" class=\"row_heading level0 row15\" >mistral-medium</th>\n",
+       "      <td id=\"T_0026f_row15_col0\" class=\"data row15 col0\" >1500</td>\n",
+       "      <td id=\"T_0026f_row15_col1\" class=\"data row15 col1\" >21.855773</td>\n",
+       "      <td id=\"T_0026f_row15_col2\" class=\"data row15 col2\" >28.614337</td>\n",
+       "      <td id=\"T_0026f_row15_col3\" class=\"data row15 col3\" >6.758565</td>\n",
+       "      <td id=\"T_0026f_row15_col4\" class=\"data row15 col4\" >16</td>\n",
+       "      <td id=\"T_0026f_row15_col5\" class=\"data row15 col5\" >15</td>\n",
+       "      <td id=\"T_0026f_row15_col6\" class=\"data row15 col6\" >1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row16\" class=\"row_heading level0 row16\" >claude-2</th>\n",
+       "      <td id=\"T_0026f_row16_col0\" class=\"data row16 col0\" >1069</td>\n",
+       "      <td id=\"T_0026f_row16_col1\" class=\"data row16 col1\" >17.188240</td>\n",
+       "      <td id=\"T_0026f_row16_col2\" class=\"data row16 col2\" >28.155196</td>\n",
+       "      <td id=\"T_0026f_row16_col3\" class=\"data row16 col3\" >10.966956</td>\n",
+       "      <td id=\"T_0026f_row16_col4\" class=\"data row16 col4\" >25</td>\n",
+       "      <td id=\"T_0026f_row16_col5\" class=\"data row16 col5\" >16</td>\n",
+       "      <td id=\"T_0026f_row16_col6\" class=\"data row16 col6\" >9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row17\" class=\"row_heading level0 row17\" >claude</th>\n",
+       "      <td id=\"T_0026f_row17_col0\" class=\"data row17 col0\" >1082</td>\n",
+       "      <td id=\"T_0026f_row17_col1\" class=\"data row17 col1\" >16.985344</td>\n",
+       "      <td id=\"T_0026f_row17_col2\" class=\"data row17 col2\" >27.289504</td>\n",
+       "      <td id=\"T_0026f_row17_col3\" class=\"data row17 col3\" >10.304161</td>\n",
+       "      <td id=\"T_0026f_row17_col4\" class=\"data row17 col4\" >26</td>\n",
+       "      <td id=\"T_0026f_row17_col5\" class=\"data row17 col5\" >17</td>\n",
+       "      <td id=\"T_0026f_row17_col6\" class=\"data row17 col6\" >9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row18\" class=\"row_heading level0 row18\" >Yi-34B-Chat</th>\n",
+       "      <td id=\"T_0026f_row18_col0\" class=\"data row18 col0\" >2123</td>\n",
+       "      <td id=\"T_0026f_row18_col1\" class=\"data row18 col1\" >29.659947</td>\n",
+       "      <td id=\"T_0026f_row18_col2\" class=\"data row18 col2\" >27.190548</td>\n",
+       "      <td id=\"T_0026f_row18_col3\" class=\"data row18 col3\" >-2.469399</td>\n",
+       "      <td id=\"T_0026f_row18_col4\" class=\"data row18 col4\" >6</td>\n",
+       "      <td id=\"T_0026f_row18_col5\" class=\"data row18 col5\" >18</td>\n",
+       "      <td id=\"T_0026f_row18_col6\" class=\"data row18 col6\" >-12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row19\" class=\"row_heading level0 row19\" >Snorkel-Mistral-PairRM-DPO</th>\n",
+       "      <td id=\"T_0026f_row19_col0\" class=\"data row19 col0\" >2736</td>\n",
+       "      <td id=\"T_0026f_row19_col1\" class=\"data row19 col1\" >30.220053</td>\n",
+       "      <td id=\"T_0026f_row19_col2\" class=\"data row19 col2\" >26.386425</td>\n",
+       "      <td id=\"T_0026f_row19_col3\" class=\"data row19 col3\" >-3.833628</td>\n",
+       "      <td id=\"T_0026f_row19_col4\" class=\"data row19 col4\" >5</td>\n",
+       "      <td id=\"T_0026f_row19_col5\" class=\"data row19 col5\" >19</td>\n",
+       "      <td id=\"T_0026f_row19_col6\" class=\"data row19 col6\" >-14</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row20\" class=\"row_heading level0 row20\" >claude-instant-1.2</th>\n",
+       "      <td id=\"T_0026f_row20_col0\" class=\"data row20 col0\" >1112</td>\n",
+       "      <td id=\"T_0026f_row20_col1\" class=\"data row20 col1\" >16.127400</td>\n",
+       "      <td id=\"T_0026f_row20_col2\" class=\"data row20 col2\" >25.612259</td>\n",
+       "      <td id=\"T_0026f_row20_col3\" class=\"data row20 col3\" >9.484859</td>\n",
+       "      <td id=\"T_0026f_row20_col4\" class=\"data row20 col4\" >27</td>\n",
+       "      <td id=\"T_0026f_row20_col5\" class=\"data row20 col5\" >20</td>\n",
+       "      <td id=\"T_0026f_row20_col6\" class=\"data row20 col6\" >7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row21\" class=\"row_heading level0 row21\" >claude-2.1</th>\n",
+       "      <td id=\"T_0026f_row21_col0\" class=\"data row21 col0\" >1096</td>\n",
+       "      <td id=\"T_0026f_row21_col1\" class=\"data row21 col1\" >15.733507</td>\n",
+       "      <td id=\"T_0026f_row21_col2\" class=\"data row21 col2\" >25.251944</td>\n",
+       "      <td id=\"T_0026f_row21_col3\" class=\"data row21 col3\" >9.518437</td>\n",
+       "      <td id=\"T_0026f_row21_col4\" class=\"data row21 col4\" >31</td>\n",
+       "      <td id=\"T_0026f_row21_col5\" class=\"data row21 col5\" >21</td>\n",
+       "      <td id=\"T_0026f_row21_col6\" class=\"data row21 col6\" >10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row22\" class=\"row_heading level0 row22\" >xwinlm-70b-v0.1</th>\n",
+       "      <td id=\"T_0026f_row22_col0\" class=\"data row22 col0\" >1775</td>\n",
+       "      <td id=\"T_0026f_row22_col1\" class=\"data row22 col1\" >21.812957</td>\n",
+       "      <td id=\"T_0026f_row22_col2\" class=\"data row22 col2\" >24.649686</td>\n",
+       "      <td id=\"T_0026f_row22_col3\" class=\"data row22 col3\" >2.836729</td>\n",
+       "      <td id=\"T_0026f_row22_col4\" class=\"data row22 col4\" >17</td>\n",
+       "      <td id=\"T_0026f_row22_col5\" class=\"data row22 col5\" >22</td>\n",
+       "      <td id=\"T_0026f_row22_col6\" class=\"data row22 col6\" >-5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row23\" class=\"row_heading level0 row23\" >gemini-pro</th>\n",
+       "      <td id=\"T_0026f_row23_col0\" class=\"data row23 col0\" >1456</td>\n",
+       "      <td id=\"T_0026f_row23_col1\" class=\"data row23 col1\" >18.177645</td>\n",
+       "      <td id=\"T_0026f_row23_col2\" class=\"data row23 col2\" >24.427105</td>\n",
+       "      <td id=\"T_0026f_row23_col3\" class=\"data row23 col3\" >6.249460</td>\n",
+       "      <td id=\"T_0026f_row23_col4\" class=\"data row23 col4\" >23</td>\n",
+       "      <td id=\"T_0026f_row23_col5\" class=\"data row23 col5\" >23</td>\n",
+       "      <td id=\"T_0026f_row23_col6\" class=\"data row23 col6\" >0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row24\" class=\"row_heading level0 row24\" >Mixtral-8x7B-Instruct-v0.1</th>\n",
+       "      <td id=\"T_0026f_row24_col0\" class=\"data row24 col0\" >1465</td>\n",
+       "      <td id=\"T_0026f_row24_col1\" class=\"data row24 col1\" >18.255318</td>\n",
+       "      <td id=\"T_0026f_row24_col2\" class=\"data row24 col2\" >23.688483</td>\n",
+       "      <td id=\"T_0026f_row24_col3\" class=\"data row24 col3\" >5.433165</td>\n",
+       "      <td id=\"T_0026f_row24_col4\" class=\"data row24 col4\" >22</td>\n",
+       "      <td id=\"T_0026f_row24_col5\" class=\"data row24 col5\" >24</td>\n",
+       "      <td id=\"T_0026f_row24_col6\" class=\"data row24 col6\" >-2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row25\" class=\"row_heading level0 row25\" >evo-v2-7b</th>\n",
+       "      <td id=\"T_0026f_row25_col0\" class=\"data row25 col0\" >1754</td>\n",
+       "      <td id=\"T_0026f_row25_col1\" class=\"data row25 col1\" >20.834113</td>\n",
+       "      <td id=\"T_0026f_row25_col2\" class=\"data row25 col2\" >23.357706</td>\n",
+       "      <td id=\"T_0026f_row25_col3\" class=\"data row25 col3\" >2.523593</td>\n",
+       "      <td id=\"T_0026f_row25_col4\" class=\"data row25 col4\" >20</td>\n",
+       "      <td id=\"T_0026f_row25_col5\" class=\"data row25 col5\" >25</td>\n",
+       "      <td id=\"T_0026f_row25_col6\" class=\"data row25 col6\" >-5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row26\" class=\"row_heading level0 row26\" >Mixtral-8x7B-Instruct-v0.1_verbose</th>\n",
+       "      <td id=\"T_0026f_row26_col0\" class=\"data row26 col0\" >2083</td>\n",
+       "      <td id=\"T_0026f_row26_col1\" class=\"data row26 col1\" >24.614063</td>\n",
+       "      <td id=\"T_0026f_row26_col2\" class=\"data row26 col2\" >23.223121</td>\n",
+       "      <td id=\"T_0026f_row26_col3\" class=\"data row26 col3\" >-1.390942</td>\n",
+       "      <td id=\"T_0026f_row26_col4\" class=\"data row26 col4\" >10</td>\n",
+       "      <td id=\"T_0026f_row26_col5\" class=\"data row26 col5\" >26</td>\n",
+       "      <td id=\"T_0026f_row26_col6\" class=\"data row26 col6\" >-16</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row27\" class=\"row_heading level0 row27\" >Mixtral-8x7B-Instruct-v0.1_concise</th>\n",
+       "      <td id=\"T_0026f_row27_col0\" class=\"data row27 col0\" >910</td>\n",
+       "      <td id=\"T_0026f_row27_col1\" class=\"data row27 col1\" >13.744040</td>\n",
+       "      <td id=\"T_0026f_row27_col2\" class=\"data row27 col2\" >22.962609</td>\n",
+       "      <td id=\"T_0026f_row27_col3\" class=\"data row27 col3\" >9.218569</td>\n",
+       "      <td id=\"T_0026f_row27_col4\" class=\"data row27 col4\" >41</td>\n",
+       "      <td id=\"T_0026f_row27_col5\" class=\"data row27 col5\" >27</td>\n",
+       "      <td id=\"T_0026f_row27_col6\" class=\"data row27 col6\" >14</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row28\" class=\"row_heading level0 row28\" >gpt-3.5-turbo-16k-0613</th>\n",
+       "      <td id=\"T_0026f_row28_col0\" class=\"data row28 col0\" >1328</td>\n",
+       "      <td id=\"T_0026f_row28_col1\" class=\"data row28 col1\" >14.132391</td>\n",
+       "      <td id=\"T_0026f_row28_col2\" class=\"data row28 col2\" >22.720189</td>\n",
+       "      <td id=\"T_0026f_row28_col3\" class=\"data row28 col3\" >8.587799</td>\n",
+       "      <td id=\"T_0026f_row28_col4\" class=\"data row28 col4\" >36</td>\n",
+       "      <td id=\"T_0026f_row28_col5\" class=\"data row28 col5\" >28</td>\n",
+       "      <td id=\"T_0026f_row28_col6\" class=\"data row28 col6\" >8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row29\" class=\"row_heading level0 row29\" >gpt-3.5-turbo-0613</th>\n",
+       "      <td id=\"T_0026f_row29_col0\" class=\"data row29 col0\" >1331</td>\n",
+       "      <td id=\"T_0026f_row29_col1\" class=\"data row29 col1\" >14.095799</td>\n",
+       "      <td id=\"T_0026f_row29_col2\" class=\"data row29 col2\" >22.352513</td>\n",
+       "      <td id=\"T_0026f_row29_col3\" class=\"data row29 col3\" >8.256714</td>\n",
+       "      <td id=\"T_0026f_row29_col4\" class=\"data row29 col4\" >37</td>\n",
+       "      <td id=\"T_0026f_row29_col5\" class=\"data row29 col5\" >29</td>\n",
+       "      <td id=\"T_0026f_row29_col6\" class=\"data row29 col6\" >8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row30\" class=\"row_heading level0 row30\" >gpt-3.5-turbo-1106_verbose</th>\n",
+       "      <td id=\"T_0026f_row30_col0\" class=\"data row30 col0\" >1058</td>\n",
+       "      <td id=\"T_0026f_row30_col1\" class=\"data row30 col1\" >12.763170</td>\n",
+       "      <td id=\"T_0026f_row30_col2\" class=\"data row30 col2\" >22.000937</td>\n",
+       "      <td id=\"T_0026f_row30_col3\" class=\"data row30 col3\" >9.237767</td>\n",
+       "      <td id=\"T_0026f_row30_col4\" class=\"data row30 col4\" >45</td>\n",
+       "      <td id=\"T_0026f_row30_col5\" class=\"data row30 col5\" >30</td>\n",
+       "      <td id=\"T_0026f_row30_col6\" class=\"data row30 col6\" >15</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row31\" class=\"row_heading level0 row31\" >gpt4_0613_concise</th>\n",
+       "      <td id=\"T_0026f_row31_col0\" class=\"data row31 col0\" >627</td>\n",
+       "      <td id=\"T_0026f_row31_col1\" class=\"data row31 col1\" >9.400321</td>\n",
+       "      <td id=\"T_0026f_row31_col2\" class=\"data row31 col2\" >21.577991</td>\n",
+       "      <td id=\"T_0026f_row31_col3\" class=\"data row31 col3\" >12.177670</td>\n",
+       "      <td id=\"T_0026f_row31_col4\" class=\"data row31 col4\" >63</td>\n",
+       "      <td id=\"T_0026f_row31_col5\" class=\"data row31 col5\" >31</td>\n",
+       "      <td id=\"T_0026f_row31_col6\" class=\"data row31 col6\" >32</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row32\" class=\"row_heading level0 row32\" >pairrm-tulu-2-70b</th>\n",
+       "      <td id=\"T_0026f_row32_col0\" class=\"data row32 col0\" >1607</td>\n",
+       "      <td id=\"T_0026f_row32_col1\" class=\"data row32 col1\" >18.638963</td>\n",
+       "      <td id=\"T_0026f_row32_col2\" class=\"data row32 col2\" >21.428404</td>\n",
+       "      <td id=\"T_0026f_row32_col3\" class=\"data row32 col3\" >2.789441</td>\n",
+       "      <td id=\"T_0026f_row32_col4\" class=\"data row32 col4\" >21</td>\n",
+       "      <td id=\"T_0026f_row32_col5\" class=\"data row32 col5\" >32</td>\n",
+       "      <td id=\"T_0026f_row32_col6\" class=\"data row32 col6\" >-11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row33\" class=\"row_heading level0 row33\" >tulu-2-dpo-70b</th>\n",
+       "      <td id=\"T_0026f_row33_col0\" class=\"data row33 col0\" >1418</td>\n",
+       "      <td id=\"T_0026f_row33_col1\" class=\"data row33 col1\" >15.982854</td>\n",
+       "      <td id=\"T_0026f_row33_col2\" class=\"data row33 col2\" >21.238610</td>\n",
+       "      <td id=\"T_0026f_row33_col3\" class=\"data row33 col3\" >5.255756</td>\n",
+       "      <td id=\"T_0026f_row33_col4\" class=\"data row33 col4\" >29</td>\n",
+       "      <td id=\"T_0026f_row33_col5\" class=\"data row33 col5\" >33</td>\n",
+       "      <td id=\"T_0026f_row33_col6\" class=\"data row33 col6\" >-4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row34\" class=\"row_heading level0 row34\" >Mistral-7B-ReMax-v0.1</th>\n",
+       "      <td id=\"T_0026f_row34_col0\" class=\"data row34 col0\" >1478</td>\n",
+       "      <td id=\"T_0026f_row34_col1\" class=\"data row34 col1\" >15.999331</td>\n",
+       "      <td id=\"T_0026f_row34_col2\" class=\"data row34 col2\" >20.551368</td>\n",
+       "      <td id=\"T_0026f_row34_col3\" class=\"data row34 col3\" >4.552036</td>\n",
+       "      <td id=\"T_0026f_row34_col4\" class=\"data row34 col4\" >28</td>\n",
+       "      <td id=\"T_0026f_row34_col5\" class=\"data row34 col5\" >34</td>\n",
+       "      <td id=\"T_0026f_row34_col6\" class=\"data row34 col6\" >-6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row35\" class=\"row_heading level0 row35\" >gpt-3.5-turbo-1106</th>\n",
+       "      <td id=\"T_0026f_row35_col0\" class=\"data row35 col0\" >796</td>\n",
+       "      <td id=\"T_0026f_row35_col1\" class=\"data row35 col1\" >9.177965</td>\n",
+       "      <td id=\"T_0026f_row35_col2\" class=\"data row35 col2\" >19.300589</td>\n",
+       "      <td id=\"T_0026f_row35_col3\" class=\"data row35 col3\" >10.122625</td>\n",
+       "      <td id=\"T_0026f_row35_col4\" class=\"data row35 col4\" >66</td>\n",
+       "      <td id=\"T_0026f_row35_col5\" class=\"data row35 col5\" >35</td>\n",
+       "      <td id=\"T_0026f_row35_col6\" class=\"data row35 col6\" >31</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row36\" class=\"row_heading level0 row36\" >LMCocktail-10.7B-v1</th>\n",
+       "      <td id=\"T_0026f_row36_col0\" class=\"data row36 col0\" >1203</td>\n",
+       "      <td id=\"T_0026f_row36_col1\" class=\"data row36 col1\" >13.153431</td>\n",
+       "      <td id=\"T_0026f_row36_col2\" class=\"data row36 col2\" >18.950710</td>\n",
+       "      <td id=\"T_0026f_row36_col3\" class=\"data row36 col3\" >5.797279</td>\n",
+       "      <td id=\"T_0026f_row36_col4\" class=\"data row36 col4\" >42</td>\n",
+       "      <td id=\"T_0026f_row36_col5\" class=\"data row36 col5\" >36</td>\n",
+       "      <td id=\"T_0026f_row36_col6\" class=\"data row36 col6\" >6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row37\" class=\"row_heading level0 row37\" >internlm2-chat-20b-ppo</th>\n",
+       "      <td id=\"T_0026f_row37_col0\" class=\"data row37 col0\" >2373</td>\n",
+       "      <td id=\"T_0026f_row37_col1\" class=\"data row37 col1\" >21.749155</td>\n",
+       "      <td id=\"T_0026f_row37_col2\" class=\"data row37 col2\" >18.748740</td>\n",
+       "      <td id=\"T_0026f_row37_col3\" class=\"data row37 col3\" >-3.000415</td>\n",
+       "      <td id=\"T_0026f_row37_col4\" class=\"data row37 col4\" >18</td>\n",
+       "      <td id=\"T_0026f_row37_col5\" class=\"data row37 col5\" >37</td>\n",
+       "      <td id=\"T_0026f_row37_col6\" class=\"data row37 col6\" >-19</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row38\" class=\"row_heading level0 row38\" >claude-2.1_concise</th>\n",
+       "      <td id=\"T_0026f_row38_col0\" class=\"data row38 col0\" >573</td>\n",
+       "      <td id=\"T_0026f_row38_col1\" class=\"data row38 col1\" >9.227125</td>\n",
+       "      <td id=\"T_0026f_row38_col2\" class=\"data row38 col2\" >18.208458</td>\n",
+       "      <td id=\"T_0026f_row38_col3\" class=\"data row38 col3\" >8.981333</td>\n",
+       "      <td id=\"T_0026f_row38_col4\" class=\"data row38 col4\" >65</td>\n",
+       "      <td id=\"T_0026f_row38_col5\" class=\"data row38 col5\" >38</td>\n",
+       "      <td id=\"T_0026f_row38_col6\" class=\"data row38 col6\" >27</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row39\" class=\"row_heading level0 row39\" >gpt-3.5-turbo-0301</th>\n",
+       "      <td id=\"T_0026f_row39_col0\" class=\"data row39 col0\" >827</td>\n",
+       "      <td id=\"T_0026f_row39_col1\" class=\"data row39 col1\" >9.622453</td>\n",
+       "      <td id=\"T_0026f_row39_col2\" class=\"data row39 col2\" >18.093242</td>\n",
+       "      <td id=\"T_0026f_row39_col3\" class=\"data row39 col3\" >8.470788</td>\n",
+       "      <td id=\"T_0026f_row39_col4\" class=\"data row39 col4\" >60</td>\n",
+       "      <td id=\"T_0026f_row39_col5\" class=\"data row39 col5\" >39</td>\n",
+       "      <td id=\"T_0026f_row39_col6\" class=\"data row39 col6\" >21</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row40\" class=\"row_heading level0 row40\" >xwinlm-13b-v0.1</th>\n",
+       "      <td id=\"T_0026f_row40_col0\" class=\"data row40 col0\" >1894</td>\n",
+       "      <td id=\"T_0026f_row40_col1\" class=\"data row40 col1\" >17.427935</td>\n",
+       "      <td id=\"T_0026f_row40_col2\" class=\"data row40 col2\" >17.918938</td>\n",
+       "      <td id=\"T_0026f_row40_col3\" class=\"data row40 col3\" >0.491003</td>\n",
+       "      <td id=\"T_0026f_row40_col4\" class=\"data row40 col4\" >24</td>\n",
+       "      <td id=\"T_0026f_row40_col5\" class=\"data row40 col5\" >40</td>\n",
+       "      <td id=\"T_0026f_row40_col6\" class=\"data row40 col6\" >-16</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row41\" class=\"row_heading level0 row41\" >deepseek-llm-67b-chat</th>\n",
+       "      <td id=\"T_0026f_row41_col0\" class=\"data row41 col0\" >1151</td>\n",
+       "      <td id=\"T_0026f_row41_col1\" class=\"data row41 col1\" >12.093422</td>\n",
+       "      <td id=\"T_0026f_row41_col2\" class=\"data row41 col2\" >17.843384</td>\n",
+       "      <td id=\"T_0026f_row41_col3\" class=\"data row41 col3\" >5.749962</td>\n",
+       "      <td id=\"T_0026f_row41_col4\" class=\"data row41 col4\" >48</td>\n",
+       "      <td id=\"T_0026f_row41_col5\" class=\"data row41 col5\" >41</td>\n",
+       "      <td id=\"T_0026f_row41_col6\" class=\"data row41 col6\" >7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row42\" class=\"row_heading level0 row42\" >gpt35_turbo_instruct</th>\n",
+       "      <td id=\"T_0026f_row42_col0\" class=\"data row42 col0\" >1018</td>\n",
+       "      <td id=\"T_0026f_row42_col1\" class=\"data row42 col1\" >8.462447</td>\n",
+       "      <td id=\"T_0026f_row42_col2\" class=\"data row42 col2\" >17.721303</td>\n",
+       "      <td id=\"T_0026f_row42_col3\" class=\"data row42 col3\" >9.258856</td>\n",
+       "      <td id=\"T_0026f_row42_col4\" class=\"data row42 col4\" >70</td>\n",
+       "      <td id=\"T_0026f_row42_col5\" class=\"data row42 col5\" >42</td>\n",
+       "      <td id=\"T_0026f_row42_col6\" class=\"data row42 col6\" >28</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row43\" class=\"row_heading level0 row43\" >wizardlm-70b</th>\n",
+       "      <td id=\"T_0026f_row43_col0\" class=\"data row43 col0\" >1545</td>\n",
+       "      <td id=\"T_0026f_row43_col1\" class=\"data row43 col1\" >14.383896</td>\n",
+       "      <td id=\"T_0026f_row43_col2\" class=\"data row43 col2\" >17.575061</td>\n",
+       "      <td id=\"T_0026f_row43_col3\" class=\"data row43 col3\" >3.191165</td>\n",
+       "      <td id=\"T_0026f_row43_col4\" class=\"data row43 col4\" >34</td>\n",
+       "      <td id=\"T_0026f_row43_col5\" class=\"data row43 col5\" >43</td>\n",
+       "      <td id=\"T_0026f_row43_col6\" class=\"data row43 col6\" >-9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row44\" class=\"row_heading level0 row44\" >vicuna-33b-v1.3</th>\n",
+       "      <td id=\"T_0026f_row44_col0\" class=\"data row44 col0\" >1479</td>\n",
+       "      <td id=\"T_0026f_row44_col1\" class=\"data row44 col1\" >12.705948</td>\n",
+       "      <td id=\"T_0026f_row44_col2\" class=\"data row44 col2\" >17.574575</td>\n",
+       "      <td id=\"T_0026f_row44_col3\" class=\"data row44 col3\" >4.868627</td>\n",
+       "      <td id=\"T_0026f_row44_col4\" class=\"data row44 col4\" >46</td>\n",
+       "      <td id=\"T_0026f_row44_col5\" class=\"data row44 col5\" >44</td>\n",
+       "      <td id=\"T_0026f_row44_col6\" class=\"data row44 col6\" >2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row45\" class=\"row_heading level0 row45\" >pairrm-tulu-2-13b</th>\n",
+       "      <td id=\"T_0026f_row45_col0\" class=\"data row45 col0\" >1454</td>\n",
+       "      <td id=\"T_0026f_row45_col1\" class=\"data row45 col1\" >13.831901</td>\n",
+       "      <td id=\"T_0026f_row45_col2\" class=\"data row45 col2\" >17.405204</td>\n",
+       "      <td id=\"T_0026f_row45_col3\" class=\"data row45 col3\" >3.573303</td>\n",
+       "      <td id=\"T_0026f_row45_col4\" class=\"data row45 col4\" >40</td>\n",
+       "      <td id=\"T_0026f_row45_col5\" class=\"data row45 col5\" >45</td>\n",
+       "      <td id=\"T_0026f_row45_col6\" class=\"data row45 col6\" >-5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row46\" class=\"row_heading level0 row46\" >Mistral-7B-Instruct-v0.2</th>\n",
+       "      <td id=\"T_0026f_row46_col0\" class=\"data row46 col0\" >1676</td>\n",
+       "      <td id=\"T_0026f_row46_col1\" class=\"data row46 col1\" >14.722773</td>\n",
+       "      <td id=\"T_0026f_row46_col2\" class=\"data row46 col2\" >17.111252</td>\n",
+       "      <td id=\"T_0026f_row46_col3\" class=\"data row46 col3\" >2.388479</td>\n",
+       "      <td id=\"T_0026f_row46_col4\" class=\"data row46 col4\" >33</td>\n",
+       "      <td id=\"T_0026f_row46_col5\" class=\"data row46 col5\" >46</td>\n",
+       "      <td id=\"T_0026f_row46_col6\" class=\"data row46 col6\" >-13</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row47\" class=\"row_heading level0 row47\" >evo-7b</th>\n",
+       "      <td id=\"T_0026f_row47_col0\" class=\"data row47 col0\" >1774</td>\n",
+       "      <td id=\"T_0026f_row47_col1\" class=\"data row47 col1\" >15.577437</td>\n",
+       "      <td id=\"T_0026f_row47_col2\" class=\"data row47 col2\" >16.489386</td>\n",
+       "      <td id=\"T_0026f_row47_col3\" class=\"data row47 col3\" >0.911949</td>\n",
+       "      <td id=\"T_0026f_row47_col4\" class=\"data row47 col4\" >32</td>\n",
+       "      <td id=\"T_0026f_row47_col5\" class=\"data row47 col5\" >47</td>\n",
+       "      <td id=\"T_0026f_row47_col6\" class=\"data row47 col6\" >-15</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row48\" class=\"row_heading level0 row48\" >humpback-llama2-70b</th>\n",
+       "      <td id=\"T_0026f_row48_col0\" class=\"data row48 col0\" >1107</td>\n",
+       "      <td id=\"T_0026f_row48_col1\" class=\"data row48 col1\" >10.121772</td>\n",
+       "      <td id=\"T_0026f_row48_col2\" class=\"data row48 col2\" >16.249164</td>\n",
+       "      <td id=\"T_0026f_row48_col3\" class=\"data row48 col3\" >6.127393</td>\n",
+       "      <td id=\"T_0026f_row48_col4\" class=\"data row48 col4\" >58</td>\n",
+       "      <td id=\"T_0026f_row48_col5\" class=\"data row48 col5\" >48</td>\n",
+       "      <td id=\"T_0026f_row48_col6\" class=\"data row48 col6\" >10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row49\" class=\"row_heading level0 row49\" >OpenHermes-2.5-Mistral-7B</th>\n",
+       "      <td id=\"T_0026f_row49_col0\" class=\"data row49 col0\" >1107</td>\n",
+       "      <td id=\"T_0026f_row49_col1\" class=\"data row49 col1\" >10.340416</td>\n",
+       "      <td id=\"T_0026f_row49_col2\" class=\"data row49 col2\" >16.248578</td>\n",
+       "      <td id=\"T_0026f_row49_col3\" class=\"data row49 col3\" >5.908162</td>\n",
+       "      <td id=\"T_0026f_row49_col4\" class=\"data row49 col4\" >57</td>\n",
+       "      <td id=\"T_0026f_row49_col5\" class=\"data row49 col5\" >49</td>\n",
+       "      <td id=\"T_0026f_row49_col6\" class=\"data row49 col6\" >8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row50\" class=\"row_heading level0 row50\" >deita-7b-v1.0</th>\n",
+       "      <td id=\"T_0026f_row50_col0\" class=\"data row50 col0\" >1417</td>\n",
+       "      <td id=\"T_0026f_row50_col1\" class=\"data row50 col1\" >12.646639</td>\n",
+       "      <td id=\"T_0026f_row50_col2\" class=\"data row50 col2\" >16.059014</td>\n",
+       "      <td id=\"T_0026f_row50_col3\" class=\"data row50 col3\" >3.412374</td>\n",
+       "      <td id=\"T_0026f_row50_col4\" class=\"data row50 col4\" >47</td>\n",
+       "      <td id=\"T_0026f_row50_col5\" class=\"data row50 col5\" >50</td>\n",
+       "      <td id=\"T_0026f_row50_col6\" class=\"data row50 col6\" >-3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row51\" class=\"row_heading level0 row51\" >jina-chat</th>\n",
+       "      <td id=\"T_0026f_row51_col0\" class=\"data row51 col0\" >676</td>\n",
+       "      <td id=\"T_0026f_row51_col1\" class=\"data row51 col1\" >7.786130</td>\n",
+       "      <td id=\"T_0026f_row51_col2\" class=\"data row51 col2\" >15.866004</td>\n",
+       "      <td id=\"T_0026f_row51_col3\" class=\"data row51 col3\" >8.079874</td>\n",
+       "      <td id=\"T_0026f_row51_col4\" class=\"data row51 col4\" >76</td>\n",
+       "      <td id=\"T_0026f_row51_col5\" class=\"data row51 col5\" >51</td>\n",
+       "      <td id=\"T_0026f_row51_col6\" class=\"data row51 col6\" >25</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row52\" class=\"row_heading level0 row52\" >gpt-3.5-turbo-1106_concise</th>\n",
+       "      <td id=\"T_0026f_row52_col0\" class=\"data row52 col0\" >431</td>\n",
+       "      <td id=\"T_0026f_row52_col1\" class=\"data row52 col1\" >7.415865</td>\n",
+       "      <td id=\"T_0026f_row52_col2\" class=\"data row52 col2\" >15.769521</td>\n",
+       "      <td id=\"T_0026f_row52_col3\" class=\"data row52 col3\" >8.353656</td>\n",
+       "      <td id=\"T_0026f_row52_col4\" class=\"data row52 col4\" >84</td>\n",
+       "      <td id=\"T_0026f_row52_col5\" class=\"data row52 col5\" >52</td>\n",
+       "      <td id=\"T_0026f_row52_col6\" class=\"data row52 col6\" >32</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row53\" class=\"row_heading level0 row53\" >causallm-14b</th>\n",
+       "      <td id=\"T_0026f_row53_col0\" class=\"data row53 col0\" >1391</td>\n",
+       "      <td id=\"T_0026f_row53_col1\" class=\"data row53 col1\" >11.146161</td>\n",
+       "      <td id=\"T_0026f_row53_col2\" class=\"data row53 col2\" >15.720325</td>\n",
+       "      <td id=\"T_0026f_row53_col3\" class=\"data row53 col3\" >4.574164</td>\n",
+       "      <td id=\"T_0026f_row53_col4\" class=\"data row53 col4\" >53</td>\n",
+       "      <td id=\"T_0026f_row53_col5\" class=\"data row53 col5\" >53</td>\n",
+       "      <td id=\"T_0026f_row53_col6\" class=\"data row53 col6\" >0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row54\" class=\"row_heading level0 row54\" >pairrm-zephyr-7b-beta</th>\n",
+       "      <td id=\"T_0026f_row54_col0\" class=\"data row54 col0\" >1487</td>\n",
+       "      <td id=\"T_0026f_row54_col1\" class=\"data row54 col1\" >12.841278</td>\n",
+       "      <td id=\"T_0026f_row54_col2\" class=\"data row54 col2\" >15.529867</td>\n",
+       "      <td id=\"T_0026f_row54_col3\" class=\"data row54 col3\" >2.688589</td>\n",
+       "      <td id=\"T_0026f_row54_col4\" class=\"data row54 col4\" >44</td>\n",
+       "      <td id=\"T_0026f_row54_col5\" class=\"data row54 col5\" >54</td>\n",
+       "      <td id=\"T_0026f_row54_col6\" class=\"data row54 col6\" >-10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row55\" class=\"row_heading level0 row55\" >Starling-LM-7B-alpha</th>\n",
+       "      <td id=\"T_0026f_row55_col0\" class=\"data row55 col0\" >1895</td>\n",
+       "      <td id=\"T_0026f_row55_col1\" class=\"data row55 col1\" >14.245924</td>\n",
+       "      <td id=\"T_0026f_row55_col2\" class=\"data row55 col2\" >14.690471</td>\n",
+       "      <td id=\"T_0026f_row55_col3\" class=\"data row55 col3\" >0.444548</td>\n",
+       "      <td id=\"T_0026f_row55_col4\" class=\"data row55 col4\" >35</td>\n",
+       "      <td id=\"T_0026f_row55_col5\" class=\"data row55 col5\" >55</td>\n",
+       "      <td id=\"T_0026f_row55_col6\" class=\"data row55 col6\" >-20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row56\" class=\"row_heading level0 row56\" >llama-2-70b-chat-hf</th>\n",
+       "      <td id=\"T_0026f_row56_col0\" class=\"data row56 col0\" >1790</td>\n",
+       "      <td id=\"T_0026f_row56_col1\" class=\"data row56 col1\" >13.888258</td>\n",
+       "      <td id=\"T_0026f_row56_col2\" class=\"data row56 col2\" >14.677319</td>\n",
+       "      <td id=\"T_0026f_row56_col3\" class=\"data row56 col3\" >0.789061</td>\n",
+       "      <td id=\"T_0026f_row56_col4\" class=\"data row56 col4\" >38</td>\n",
+       "      <td id=\"T_0026f_row56_col5\" class=\"data row56 col5\" >56</td>\n",
+       "      <td id=\"T_0026f_row56_col6\" class=\"data row56 col6\" >-18</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row57\" class=\"row_heading level0 row57\" >openchat-v3.1-13b</th>\n",
+       "      <td id=\"T_0026f_row57_col0\" class=\"data row57 col0\" >1484</td>\n",
+       "      <td id=\"T_0026f_row57_col1\" class=\"data row57 col1\" >11.082230</td>\n",
+       "      <td id=\"T_0026f_row57_col2\" class=\"data row57 col2\" >14.503388</td>\n",
+       "      <td id=\"T_0026f_row57_col3\" class=\"data row57 col3\" >3.421157</td>\n",
+       "      <td id=\"T_0026f_row57_col4\" class=\"data row57 col4\" >54</td>\n",
+       "      <td id=\"T_0026f_row57_col5\" class=\"data row57 col5\" >57</td>\n",
+       "      <td id=\"T_0026f_row57_col6\" class=\"data row57 col6\" >-3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row58\" class=\"row_heading level0 row58\" >wizardlm-13b-v1.2</th>\n",
+       "      <td id=\"T_0026f_row58_col0\" class=\"data row58 col0\" >1635</td>\n",
+       "      <td id=\"T_0026f_row58_col1\" class=\"data row58 col1\" >12.027480</td>\n",
+       "      <td id=\"T_0026f_row58_col2\" class=\"data row58 col2\" >14.462591</td>\n",
+       "      <td id=\"T_0026f_row58_col3\" class=\"data row58 col3\" >2.435110</td>\n",
+       "      <td id=\"T_0026f_row58_col4\" class=\"data row58 col4\" >49</td>\n",
+       "      <td id=\"T_0026f_row58_col5\" class=\"data row58 col5\" >58</td>\n",
+       "      <td id=\"T_0026f_row58_col6\" class=\"data row58 col6\" >-9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row59\" class=\"row_heading level0 row59\" >ultralm-13b-v2.0-best-of-16</th>\n",
+       "      <td id=\"T_0026f_row59_col0\" class=\"data row59 col0\" >1720</td>\n",
+       "      <td id=\"T_0026f_row59_col1\" class=\"data row59 col1\" >13.853373</td>\n",
+       "      <td id=\"T_0026f_row59_col2\" class=\"data row59 col2\" >14.198988</td>\n",
+       "      <td id=\"T_0026f_row59_col3\" class=\"data row59 col3\" >0.345614</td>\n",
+       "      <td id=\"T_0026f_row59_col4\" class=\"data row59 col4\" >39</td>\n",
+       "      <td id=\"T_0026f_row59_col5\" class=\"data row59 col5\" >59</td>\n",
+       "      <td id=\"T_0026f_row59_col6\" class=\"data row59 col6\" >-20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row60\" class=\"row_heading level0 row60\" >wizardlm-13b-v1.1</th>\n",
+       "      <td id=\"T_0026f_row60_col0\" class=\"data row60 col0\" >1525</td>\n",
+       "      <td id=\"T_0026f_row60_col1\" class=\"data row60 col1\" >11.233910</td>\n",
+       "      <td id=\"T_0026f_row60_col2\" class=\"data row60 col2\" >13.915721</td>\n",
+       "      <td id=\"T_0026f_row60_col3\" class=\"data row60 col3\" >2.681811</td>\n",
+       "      <td id=\"T_0026f_row60_col4\" class=\"data row60 col4\" >52</td>\n",
+       "      <td id=\"T_0026f_row60_col5\" class=\"data row60 col5\" >60</td>\n",
+       "      <td id=\"T_0026f_row60_col6\" class=\"data row60 col6\" >-8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row61\" class=\"row_heading level0 row61\" >zephyr-7b-beta</th>\n",
+       "      <td id=\"T_0026f_row61_col0\" class=\"data row61 col0\" >1444</td>\n",
+       "      <td id=\"T_0026f_row61_col1\" class=\"data row61 col1\" >10.992886</td>\n",
+       "      <td id=\"T_0026f_row61_col2\" class=\"data row61 col2\" >13.203198</td>\n",
+       "      <td id=\"T_0026f_row61_col3\" class=\"data row61 col3\" >2.210313</td>\n",
+       "      <td id=\"T_0026f_row61_col4\" class=\"data row61 col4\" >55</td>\n",
+       "      <td id=\"T_0026f_row61_col5\" class=\"data row61 col5\" >61</td>\n",
+       "      <td id=\"T_0026f_row61_col6\" class=\"data row61 col6\" >-6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row62\" class=\"row_heading level0 row62\" >dolphin-2.2.1-mistral-7b</th>\n",
+       "      <td id=\"T_0026f_row62_col0\" class=\"data row62 col0\" >1130</td>\n",
+       "      <td id=\"T_0026f_row62_col1\" class=\"data row62 col1\" >9.039800</td>\n",
+       "      <td id=\"T_0026f_row62_col2\" class=\"data row62 col2\" >13.121478</td>\n",
+       "      <td id=\"T_0026f_row62_col3\" class=\"data row62 col3\" >4.081678</td>\n",
+       "      <td id=\"T_0026f_row62_col4\" class=\"data row62 col4\" >68</td>\n",
+       "      <td id=\"T_0026f_row62_col5\" class=\"data row62 col5\" >62</td>\n",
+       "      <td id=\"T_0026f_row62_col6\" class=\"data row62 col6\" >6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row63\" class=\"row_heading level0 row63\" >humpback-llama-65b</th>\n",
+       "      <td id=\"T_0026f_row63_col0\" class=\"data row63 col0\" >1232</td>\n",
+       "      <td id=\"T_0026f_row63_col1\" class=\"data row63 col1\" >9.425139</td>\n",
+       "      <td id=\"T_0026f_row63_col2\" class=\"data row63 col2\" >12.799860</td>\n",
+       "      <td id=\"T_0026f_row63_col3\" class=\"data row63 col3\" >3.374721</td>\n",
+       "      <td id=\"T_0026f_row63_col4\" class=\"data row63 col4\" >62</td>\n",
+       "      <td id=\"T_0026f_row63_col5\" class=\"data row63 col5\" >63</td>\n",
+       "      <td id=\"T_0026f_row63_col6\" class=\"data row63 col6\" >-1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row64\" class=\"row_heading level0 row64\" >openbuddy-llama2-70b-v10.1</th>\n",
+       "      <td id=\"T_0026f_row64_col0\" class=\"data row64 col0\" >1077</td>\n",
+       "      <td id=\"T_0026f_row64_col1\" class=\"data row64 col1\" >8.096422</td>\n",
+       "      <td id=\"T_0026f_row64_col2\" class=\"data row64 col2\" >12.572173</td>\n",
+       "      <td id=\"T_0026f_row64_col3\" class=\"data row64 col3\" >4.475751</td>\n",
+       "      <td id=\"T_0026f_row64_col4\" class=\"data row64 col4\" >74</td>\n",
+       "      <td id=\"T_0026f_row64_col5\" class=\"data row64 col5\" >64</td>\n",
+       "      <td id=\"T_0026f_row64_col6\" class=\"data row64 col6\" >10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row65\" class=\"row_heading level0 row65\" >openbuddy-llama-65b-v8</th>\n",
+       "      <td id=\"T_0026f_row65_col0\" class=\"data row65 col0\" >1162</td>\n",
+       "      <td id=\"T_0026f_row65_col1\" class=\"data row65 col1\" >8.770650</td>\n",
+       "      <td id=\"T_0026f_row65_col2\" class=\"data row65 col2\" >12.469356</td>\n",
+       "      <td id=\"T_0026f_row65_col3\" class=\"data row65 col3\" >3.698706</td>\n",
+       "      <td id=\"T_0026f_row65_col4\" class=\"data row65 col4\" >69</td>\n",
+       "      <td id=\"T_0026f_row65_col5\" class=\"data row65 col5\" >65</td>\n",
+       "      <td id=\"T_0026f_row65_col6\" class=\"data row65 col6\" >4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row66\" class=\"row_heading level0 row66\" >Qwen-14B-Chat</th>\n",
+       "      <td id=\"T_0026f_row66_col0\" class=\"data row66 col0\" >1013</td>\n",
+       "      <td id=\"T_0026f_row66_col1\" class=\"data row66 col1\" >7.502333</td>\n",
+       "      <td id=\"T_0026f_row66_col2\" class=\"data row66 col2\" >12.378742</td>\n",
+       "      <td id=\"T_0026f_row66_col3\" class=\"data row66 col3\" >4.876408</td>\n",
+       "      <td id=\"T_0026f_row66_col4\" class=\"data row66 col4\" >81</td>\n",
+       "      <td id=\"T_0026f_row66_col5\" class=\"data row66 col5\" >66</td>\n",
+       "      <td id=\"T_0026f_row66_col6\" class=\"data row66 col6\" >15</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row67\" class=\"row_heading level0 row67\" >gpt4_gamed</th>\n",
+       "      <td id=\"T_0026f_row67_col0\" class=\"data row67 col0\" >68</td>\n",
+       "      <td id=\"T_0026f_row67_col1\" class=\"data row67 col1\" >3.738337</td>\n",
+       "      <td id=\"T_0026f_row67_col2\" class=\"data row67 col2\" >12.188764</td>\n",
+       "      <td id=\"T_0026f_row67_col3\" class=\"data row67 col3\" >8.450427</td>\n",
+       "      <td id=\"T_0026f_row67_col4\" class=\"data row67 col4\" >112</td>\n",
+       "      <td id=\"T_0026f_row67_col5\" class=\"data row67 col5\" >67</td>\n",
+       "      <td id=\"T_0026f_row67_col6\" class=\"data row67 col6\" >45</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row68\" class=\"row_heading level0 row68\" >cut-13b</th>\n",
+       "      <td id=\"T_0026f_row68_col0\" class=\"data row68 col0\" >1637</td>\n",
+       "      <td id=\"T_0026f_row68_col1\" class=\"data row68 col1\" >10.779089</td>\n",
+       "      <td id=\"T_0026f_row68_col2\" class=\"data row68 col2\" >12.154782</td>\n",
+       "      <td id=\"T_0026f_row68_col3\" class=\"data row68 col3\" >1.375693</td>\n",
+       "      <td id=\"T_0026f_row68_col4\" class=\"data row68 col4\" >56</td>\n",
+       "      <td id=\"T_0026f_row68_col5\" class=\"data row68 col5\" >68</td>\n",
+       "      <td id=\"T_0026f_row68_col6\" class=\"data row68 col6\" >-12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row69\" class=\"row_heading level0 row69\" >openchat-v2-w-13b</th>\n",
+       "      <td id=\"T_0026f_row69_col0\" class=\"data row69 col0\" >1566</td>\n",
+       "      <td id=\"T_0026f_row69_col1\" class=\"data row69 col1\" >9.615344</td>\n",
+       "      <td id=\"T_0026f_row69_col2\" class=\"data row69 col2\" >12.030428</td>\n",
+       "      <td id=\"T_0026f_row69_col3\" class=\"data row69 col3\" >2.415084</td>\n",
+       "      <td id=\"T_0026f_row69_col4\" class=\"data row69 col4\" >61</td>\n",
+       "      <td id=\"T_0026f_row69_col5\" class=\"data row69 col5\" >69</td>\n",
+       "      <td id=\"T_0026f_row69_col6\" class=\"data row69 col6\" >-8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row70\" class=\"row_heading level0 row70\" >tulu-2-dpo-13b</th>\n",
+       "      <td id=\"T_0026f_row70_col0\" class=\"data row70 col0\" >1614</td>\n",
+       "      <td id=\"T_0026f_row70_col1\" class=\"data row70 col1\" >10.119788</td>\n",
+       "      <td id=\"T_0026f_row70_col2\" class=\"data row70 col2\" >11.554479</td>\n",
+       "      <td id=\"T_0026f_row70_col3\" class=\"data row70 col3\" >1.434691</td>\n",
+       "      <td id=\"T_0026f_row70_col4\" class=\"data row70 col4\" >59</td>\n",
+       "      <td id=\"T_0026f_row70_col5\" class=\"data row70 col5\" >70</td>\n",
+       "      <td id=\"T_0026f_row70_col6\" class=\"data row70 col6\" >-11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row71\" class=\"row_heading level0 row71\" >claude2-alpaca-13b</th>\n",
+       "      <td id=\"T_0026f_row71_col0\" class=\"data row71 col0\" >1127</td>\n",
+       "      <td id=\"T_0026f_row71_col1\" class=\"data row71 col1\" >7.437351</td>\n",
+       "      <td id=\"T_0026f_row71_col2\" class=\"data row71 col2\" >11.498898</td>\n",
+       "      <td id=\"T_0026f_row71_col3\" class=\"data row71 col3\" >4.061547</td>\n",
+       "      <td id=\"T_0026f_row71_col4\" class=\"data row71 col4\" >83</td>\n",
+       "      <td id=\"T_0026f_row71_col5\" class=\"data row71 col5\" >71</td>\n",
+       "      <td id=\"T_0026f_row71_col6\" class=\"data row71 col6\" >12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row72\" class=\"row_heading level0 row72\" >minotaur-13b</th>\n",
+       "      <td id=\"T_0026f_row72_col0\" class=\"data row72 col0\" >881</td>\n",
+       "      <td id=\"T_0026f_row72_col1\" class=\"data row72 col1\" >5.738964</td>\n",
+       "      <td id=\"T_0026f_row72_col2\" class=\"data row72 col2\" >11.458819</td>\n",
+       "      <td id=\"T_0026f_row72_col3\" class=\"data row72 col3\" >5.719855</td>\n",
+       "      <td id=\"T_0026f_row72_col4\" class=\"data row72 col4\" >100</td>\n",
+       "      <td id=\"T_0026f_row72_col5\" class=\"data row72 col5\" >72</td>\n",
+       "      <td id=\"T_0026f_row72_col6\" class=\"data row72 col6\" >28</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row73\" class=\"row_heading level0 row73\" >airoboros-65b</th>\n",
+       "      <td id=\"T_0026f_row73_col0\" class=\"data row73 col0\" >1512</td>\n",
+       "      <td id=\"T_0026f_row73_col1\" class=\"data row73 col1\" >9.388950</td>\n",
+       "      <td id=\"T_0026f_row73_col2\" class=\"data row73 col2\" >11.007642</td>\n",
+       "      <td id=\"T_0026f_row73_col3\" class=\"data row73 col3\" >1.618692</td>\n",
+       "      <td id=\"T_0026f_row73_col4\" class=\"data row73 col4\" >64</td>\n",
+       "      <td id=\"T_0026f_row73_col5\" class=\"data row73 col5\" >73</td>\n",
+       "      <td id=\"T_0026f_row73_col6\" class=\"data row73 col6\" >-9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row74\" class=\"row_heading level0 row74\" >cohere</th>\n",
+       "      <td id=\"T_0026f_row74_col0\" class=\"data row74 col0\" >1983</td>\n",
+       "      <td id=\"T_0026f_row74_col1\" class=\"data row74 col1\" >12.901455</td>\n",
+       "      <td id=\"T_0026f_row74_col2\" class=\"data row74 col2\" >10.893021</td>\n",
+       "      <td id=\"T_0026f_row74_col3\" class=\"data row74 col3\" >-2.008434</td>\n",
+       "      <td id=\"T_0026f_row74_col4\" class=\"data row74 col4\" >43</td>\n",
+       "      <td id=\"T_0026f_row74_col5\" class=\"data row74 col5\" >74</td>\n",
+       "      <td id=\"T_0026f_row74_col6\" class=\"data row74 col6\" >-31</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row75\" class=\"row_heading level0 row75\" >vicuna-13b-v1.3</th>\n",
+       "      <td id=\"T_0026f_row75_col0\" class=\"data row75 col0\" >1132</td>\n",
+       "      <td id=\"T_0026f_row75_col1\" class=\"data row75 col1\" >7.137240</td>\n",
+       "      <td id=\"T_0026f_row75_col2\" class=\"data row75 col2\" >10.843165</td>\n",
+       "      <td id=\"T_0026f_row75_col3\" class=\"data row75 col3\" >3.705925</td>\n",
+       "      <td id=\"T_0026f_row75_col4\" class=\"data row75 col4\" >87</td>\n",
+       "      <td id=\"T_0026f_row75_col5\" class=\"data row75 col5\" >75</td>\n",
+       "      <td id=\"T_0026f_row75_col6\" class=\"data row75 col6\" >12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row76\" class=\"row_heading level0 row76\" >xwinlm-7b-v0.1</th>\n",
+       "      <td id=\"T_0026f_row76_col0\" class=\"data row76 col0\" >1894</td>\n",
+       "      <td id=\"T_0026f_row76_col1\" class=\"data row76 col1\" >11.245652</td>\n",
+       "      <td id=\"T_0026f_row76_col2\" class=\"data row76 col2\" >10.812206</td>\n",
+       "      <td id=\"T_0026f_row76_col3\" class=\"data row76 col3\" >-0.433446</td>\n",
+       "      <td id=\"T_0026f_row76_col4\" class=\"data row76 col4\" >51</td>\n",
+       "      <td id=\"T_0026f_row76_col5\" class=\"data row76 col5\" >76</td>\n",
+       "      <td id=\"T_0026f_row76_col6\" class=\"data row76 col6\" >-25</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row77\" class=\"row_heading level0 row77\" >airoboros-33b</th>\n",
+       "      <td id=\"T_0026f_row77_col0\" class=\"data row77 col0\" >1514</td>\n",
+       "      <td id=\"T_0026f_row77_col1\" class=\"data row77 col1\" >9.053160</td>\n",
+       "      <td id=\"T_0026f_row77_col2\" class=\"data row77 col2\" >10.719003</td>\n",
+       "      <td id=\"T_0026f_row77_col3\" class=\"data row77 col3\" >1.665842</td>\n",
+       "      <td id=\"T_0026f_row77_col4\" class=\"data row77 col4\" >67</td>\n",
+       "      <td id=\"T_0026f_row77_col5\" class=\"data row77 col5\" >77</td>\n",
+       "      <td id=\"T_0026f_row77_col6\" class=\"data row77 col6\" >-10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row78\" class=\"row_heading level0 row78\" >platolm-7b</th>\n",
+       "      <td id=\"T_0026f_row78_col0\" class=\"data row78 col0\" >1344</td>\n",
+       "      <td id=\"T_0026f_row78_col1\" class=\"data row78 col1\" >6.320828</td>\n",
+       "      <td id=\"T_0026f_row78_col2\" class=\"data row78 col2\" >10.532885</td>\n",
+       "      <td id=\"T_0026f_row78_col3\" class=\"data row78 col3\" >4.212057</td>\n",
+       "      <td id=\"T_0026f_row78_col4\" class=\"data row78 col4\" >93</td>\n",
+       "      <td id=\"T_0026f_row78_col5\" class=\"data row78 col5\" >78</td>\n",
+       "      <td id=\"T_0026f_row78_col6\" class=\"data row78 col6\" >15</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row79\" class=\"row_heading level0 row79\" >vicuna-13b-v1.5</th>\n",
+       "      <td id=\"T_0026f_row79_col0\" class=\"data row79 col0\" >1061</td>\n",
+       "      <td id=\"T_0026f_row79_col1\" class=\"data row79 col1\" >6.722122</td>\n",
+       "      <td id=\"T_0026f_row79_col2\" class=\"data row79 col2\" >10.484438</td>\n",
+       "      <td id=\"T_0026f_row79_col3\" class=\"data row79 col3\" >3.762316</td>\n",
+       "      <td id=\"T_0026f_row79_col4\" class=\"data row79 col4\" >90</td>\n",
+       "      <td id=\"T_0026f_row79_col5\" class=\"data row79 col5\" >79</td>\n",
+       "      <td id=\"T_0026f_row79_col6\" class=\"data row79 col6\" >11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row80\" class=\"row_heading level0 row80\" >gemma-7b-it</th>\n",
+       "      <td id=\"T_0026f_row80_col0\" class=\"data row80 col0\" >1115</td>\n",
+       "      <td id=\"T_0026f_row80_col1\" class=\"data row80 col1\" >6.937294</td>\n",
+       "      <td id=\"T_0026f_row80_col2\" class=\"data row80 col2\" >10.425760</td>\n",
+       "      <td id=\"T_0026f_row80_col3\" class=\"data row80 col3\" >3.488466</td>\n",
+       "      <td id=\"T_0026f_row80_col4\" class=\"data row80 col4\" >88</td>\n",
+       "      <td id=\"T_0026f_row80_col5\" class=\"data row80 col5\" >80</td>\n",
+       "      <td id=\"T_0026f_row80_col6\" class=\"data row80 col6\" >8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row81\" class=\"row_heading level0 row81\" >openchat-v2-13b</th>\n",
+       "      <td id=\"T_0026f_row81_col0\" class=\"data row81 col0\" >1564</td>\n",
+       "      <td id=\"T_0026f_row81_col1\" class=\"data row81 col1\" >8.435076</td>\n",
+       "      <td id=\"T_0026f_row81_col2\" class=\"data row81 col2\" >10.399607</td>\n",
+       "      <td id=\"T_0026f_row81_col3\" class=\"data row81 col3\" >1.964532</td>\n",
+       "      <td id=\"T_0026f_row81_col4\" class=\"data row81 col4\" >71</td>\n",
+       "      <td id=\"T_0026f_row81_col5\" class=\"data row81 col5\" >81</td>\n",
+       "      <td id=\"T_0026f_row81_col6\" class=\"data row81 col6\" >-10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row82\" class=\"row_heading level0 row82\" >zephyr-7b-alpha</th>\n",
+       "      <td id=\"T_0026f_row82_col0\" class=\"data row82 col0\" >1302</td>\n",
+       "      <td id=\"T_0026f_row82_col1\" class=\"data row82 col1\" >8.352664</td>\n",
+       "      <td id=\"T_0026f_row82_col2\" class=\"data row82 col2\" >10.289761</td>\n",
+       "      <td id=\"T_0026f_row82_col3\" class=\"data row82 col3\" >1.937097</td>\n",
+       "      <td id=\"T_0026f_row82_col4\" class=\"data row82 col4\" >72</td>\n",
+       "      <td id=\"T_0026f_row82_col5\" class=\"data row82 col5\" >82</td>\n",
+       "      <td id=\"T_0026f_row82_col6\" class=\"data row82 col6\" >-10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row83\" class=\"row_heading level0 row83\" >openbuddy-llama-30b-v7.1</th>\n",
+       "      <td id=\"T_0026f_row83_col0\" class=\"data row83 col0\" >968</td>\n",
+       "      <td id=\"T_0026f_row83_col1\" class=\"data row83 col1\" >6.130015</td>\n",
+       "      <td id=\"T_0026f_row83_col2\" class=\"data row83 col2\" >10.214495</td>\n",
+       "      <td id=\"T_0026f_row83_col3\" class=\"data row83 col3\" >4.084480</td>\n",
+       "      <td id=\"T_0026f_row83_col4\" class=\"data row83 col4\" >96</td>\n",
+       "      <td id=\"T_0026f_row83_col5\" class=\"data row83 col5\" >83</td>\n",
+       "      <td id=\"T_0026f_row83_col6\" class=\"data row83 col6\" >13</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row84\" class=\"row_heading level0 row84\" >ultralm-13b-best-of-16</th>\n",
+       "      <td id=\"T_0026f_row84_col0\" class=\"data row84 col0\" >1980</td>\n",
+       "      <td id=\"T_0026f_row84_col1\" class=\"data row84 col1\" >11.307315</td>\n",
+       "      <td id=\"T_0026f_row84_col2\" class=\"data row84 col2\" >9.876089</td>\n",
+       "      <td id=\"T_0026f_row84_col3\" class=\"data row84 col3\" >-1.431226</td>\n",
+       "      <td id=\"T_0026f_row84_col4\" class=\"data row84 col4\" >50</td>\n",
+       "      <td id=\"T_0026f_row84_col5\" class=\"data row84 col5\" >84</td>\n",
+       "      <td id=\"T_0026f_row84_col6\" class=\"data row84 col6\" >-34</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row85\" class=\"row_heading level0 row85\" >oasst-sft-llama-33b</th>\n",
+       "      <td id=\"T_0026f_row85_col0\" class=\"data row85 col0\" >748</td>\n",
+       "      <td id=\"T_0026f_row85_col1\" class=\"data row85 col1\" >4.770391</td>\n",
+       "      <td id=\"T_0026f_row85_col2\" class=\"data row85 col2\" >9.866412</td>\n",
+       "      <td id=\"T_0026f_row85_col3\" class=\"data row85 col3\" >5.096021</td>\n",
+       "      <td id=\"T_0026f_row85_col4\" class=\"data row85 col4\" >106</td>\n",
+       "      <td id=\"T_0026f_row85_col5\" class=\"data row85 col5\" >85</td>\n",
+       "      <td id=\"T_0026f_row85_col6\" class=\"data row85 col6\" >21</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row86\" class=\"row_heading level0 row86\" >wizardlm-13b</th>\n",
+       "      <td id=\"T_0026f_row86_col0\" class=\"data row86 col0\" >985</td>\n",
+       "      <td id=\"T_0026f_row86_col1\" class=\"data row86 col1\" >5.878153</td>\n",
+       "      <td id=\"T_0026f_row86_col2\" class=\"data row86 col2\" >9.828151</td>\n",
+       "      <td id=\"T_0026f_row86_col3\" class=\"data row86 col3\" >3.949998</td>\n",
+       "      <td id=\"T_0026f_row86_col4\" class=\"data row86 col4\" >98</td>\n",
+       "      <td id=\"T_0026f_row86_col5\" class=\"data row86 col5\" >86</td>\n",
+       "      <td id=\"T_0026f_row86_col6\" class=\"data row86 col6\" >12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row87\" class=\"row_heading level0 row87\" >nous-hermes-13b</th>\n",
+       "      <td id=\"T_0026f_row87_col0\" class=\"data row87 col0\" >844</td>\n",
+       "      <td id=\"T_0026f_row87_col1\" class=\"data row87 col1\" >5.411879</td>\n",
+       "      <td id=\"T_0026f_row87_col2\" class=\"data row87 col2\" >9.717863</td>\n",
+       "      <td id=\"T_0026f_row87_col3\" class=\"data row87 col3\" >4.305984</td>\n",
+       "      <td id=\"T_0026f_row87_col4\" class=\"data row87 col4\" >101</td>\n",
+       "      <td id=\"T_0026f_row87_col5\" class=\"data row87 col5\" >87</td>\n",
+       "      <td id=\"T_0026f_row87_col6\" class=\"data row87 col6\" >14</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row88\" class=\"row_heading level0 row88\" >vicuna-13b</th>\n",
+       "      <td id=\"T_0026f_row88_col0\" class=\"data row88 col0\" >1037</td>\n",
+       "      <td id=\"T_0026f_row88_col1\" class=\"data row88 col1\" >5.831103</td>\n",
+       "      <td id=\"T_0026f_row88_col2\" class=\"data row88 col2\" >9.222060</td>\n",
+       "      <td id=\"T_0026f_row88_col3\" class=\"data row88 col3\" >3.390957</td>\n",
+       "      <td id=\"T_0026f_row88_col4\" class=\"data row88 col4\" >99</td>\n",
+       "      <td id=\"T_0026f_row88_col5\" class=\"data row88 col5\" >88</td>\n",
+       "      <td id=\"T_0026f_row88_col6\" class=\"data row88 col6\" >11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row89\" class=\"row_heading level0 row89\" >tulu-2-dpo-7b</th>\n",
+       "      <td id=\"T_0026f_row89_col0\" class=\"data row89 col0\" >1663</td>\n",
+       "      <td id=\"T_0026f_row89_col1\" class=\"data row89 col1\" >8.197515</td>\n",
+       "      <td id=\"T_0026f_row89_col2\" class=\"data row89 col2\" >9.200266</td>\n",
+       "      <td id=\"T_0026f_row89_col3\" class=\"data row89 col3\" >1.002750</td>\n",
+       "      <td id=\"T_0026f_row89_col4\" class=\"data row89 col4\" >73</td>\n",
+       "      <td id=\"T_0026f_row89_col5\" class=\"data row89 col5\" >89</td>\n",
+       "      <td id=\"T_0026f_row89_col6\" class=\"data row89 col6\" >-16</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row90\" class=\"row_heading level0 row90\" >openbuddy-llama2-13b-v11.1</th>\n",
+       "      <td id=\"T_0026f_row90_col0\" class=\"data row90 col0\" >1057</td>\n",
+       "      <td id=\"T_0026f_row90_col1\" class=\"data row90 col1\" >6.174716</td>\n",
+       "      <td id=\"T_0026f_row90_col2\" class=\"data row90 col2\" >9.159090</td>\n",
+       "      <td id=\"T_0026f_row90_col3\" class=\"data row90 col3\" >2.984373</td>\n",
+       "      <td id=\"T_0026f_row90_col4\" class=\"data row90 col4\" >95</td>\n",
+       "      <td id=\"T_0026f_row90_col5\" class=\"data row90 col5\" >90</td>\n",
+       "      <td id=\"T_0026f_row90_col6\" class=\"data row90 col6\" >5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row91\" class=\"row_heading level0 row91\" >ultralm-13b-v2.0</th>\n",
+       "      <td id=\"T_0026f_row91_col0\" class=\"data row91 col0\" >1399</td>\n",
+       "      <td id=\"T_0026f_row91_col1\" class=\"data row91 col1\" >7.504623</td>\n",
+       "      <td id=\"T_0026f_row91_col2\" class=\"data row91 col2\" >9.129018</td>\n",
+       "      <td id=\"T_0026f_row91_col3\" class=\"data row91 col3\" >1.624396</td>\n",
+       "      <td id=\"T_0026f_row91_col4\" class=\"data row91 col4\" >80</td>\n",
+       "      <td id=\"T_0026f_row91_col5\" class=\"data row91 col5\" >91</td>\n",
+       "      <td id=\"T_0026f_row91_col6\" class=\"data row91 col6\" >-11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row92\" class=\"row_heading level0 row92\" >text_davinci_001</th>\n",
+       "      <td id=\"T_0026f_row92_col0\" class=\"data row92 col0\" >296</td>\n",
+       "      <td id=\"T_0026f_row92_col1\" class=\"data row92 col1\" >2.764005</td>\n",
+       "      <td id=\"T_0026f_row92_col2\" class=\"data row92 col2\" >9.020601</td>\n",
+       "      <td id=\"T_0026f_row92_col3\" class=\"data row92 col3\" >6.256596</td>\n",
+       "      <td id=\"T_0026f_row92_col4\" class=\"data row92 col4\" >122</td>\n",
+       "      <td id=\"T_0026f_row92_col5\" class=\"data row92 col5\" >92</td>\n",
+       "      <td id=\"T_0026f_row92_col6\" class=\"data row92 col6\" >30</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row93\" class=\"row_heading level0 row93\" >openbuddy-falcon-40b-v9</th>\n",
+       "      <td id=\"T_0026f_row93_col0\" class=\"data row93 col0\" >1089</td>\n",
+       "      <td id=\"T_0026f_row93_col1\" class=\"data row93 col1\" >5.955743</td>\n",
+       "      <td id=\"T_0026f_row93_col2\" class=\"data row93 col2\" >8.988937</td>\n",
+       "      <td id=\"T_0026f_row93_col3\" class=\"data row93 col3\" >3.033194</td>\n",
+       "      <td id=\"T_0026f_row93_col4\" class=\"data row93 col4\" >97</td>\n",
+       "      <td id=\"T_0026f_row93_col5\" class=\"data row93 col5\" >93</td>\n",
+       "      <td id=\"T_0026f_row93_col6\" class=\"data row93 col6\" >4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row94\" class=\"row_heading level0 row94\" >openchat-13b</th>\n",
+       "      <td id=\"T_0026f_row94_col0\" class=\"data row94 col0\" >1632</td>\n",
+       "      <td id=\"T_0026f_row94_col1\" class=\"data row94 col1\" >8.022386</td>\n",
+       "      <td id=\"T_0026f_row94_col2\" class=\"data row94 col2\" >8.806053</td>\n",
+       "      <td id=\"T_0026f_row94_col3\" class=\"data row94 col3\" >0.783667</td>\n",
+       "      <td id=\"T_0026f_row94_col4\" class=\"data row94 col4\" >75</td>\n",
+       "      <td id=\"T_0026f_row94_col5\" class=\"data row94 col5\" >94</td>\n",
+       "      <td id=\"T_0026f_row94_col6\" class=\"data row94 col6\" >-19</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row95\" class=\"row_heading level0 row95\" >llama-2-13b-chat-hf</th>\n",
+       "      <td id=\"T_0026f_row95_col0\" class=\"data row95 col0\" >1513</td>\n",
+       "      <td id=\"T_0026f_row95_col1\" class=\"data row95 col1\" >7.702310</td>\n",
+       "      <td id=\"T_0026f_row95_col2\" class=\"data row95 col2\" >8.436015</td>\n",
+       "      <td id=\"T_0026f_row95_col3\" class=\"data row95 col3\" >0.733705</td>\n",
+       "      <td id=\"T_0026f_row95_col4\" class=\"data row95 col4\" >78</td>\n",
+       "      <td id=\"T_0026f_row95_col5\" class=\"data row95 col5\" >95</td>\n",
+       "      <td id=\"T_0026f_row95_col6\" class=\"data row95 col6\" >-17</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row96\" class=\"row_heading level0 row96\" >guanaco-65b</th>\n",
+       "      <td id=\"T_0026f_row96_col0\" class=\"data row96 col0\" >1249</td>\n",
+       "      <td id=\"T_0026f_row96_col1\" class=\"data row96 col1\" >6.858495</td>\n",
+       "      <td id=\"T_0026f_row96_col2\" class=\"data row96 col2\" >8.252917</td>\n",
+       "      <td id=\"T_0026f_row96_col3\" class=\"data row96 col3\" >1.394422</td>\n",
+       "      <td id=\"T_0026f_row96_col4\" class=\"data row96 col4\" >89</td>\n",
+       "      <td id=\"T_0026f_row96_col5\" class=\"data row96 col5\" >96</td>\n",
+       "      <td id=\"T_0026f_row96_col6\" class=\"data row96 col6\" >-7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row97\" class=\"row_heading level0 row97\" >opencoderplus-15b</th>\n",
+       "      <td id=\"T_0026f_row97_col0\" class=\"data row97 col0\" >1628</td>\n",
+       "      <td id=\"T_0026f_row97_col1\" class=\"data row97 col1\" >7.406222</td>\n",
+       "      <td id=\"T_0026f_row97_col2\" class=\"data row97 col2\" >8.152410</td>\n",
+       "      <td id=\"T_0026f_row97_col3\" class=\"data row97 col3\" >0.746188</td>\n",
+       "      <td id=\"T_0026f_row97_col4\" class=\"data row97 col4\" >85</td>\n",
+       "      <td id=\"T_0026f_row97_col5\" class=\"data row97 col5\" >97</td>\n",
+       "      <td id=\"T_0026f_row97_col6\" class=\"data row97 col6\" >-12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row98\" class=\"row_heading level0 row98\" >oasst-rlhf-llama-33b</th>\n",
+       "      <td id=\"T_0026f_row98_col0\" class=\"data row98 col0\" >1079</td>\n",
+       "      <td id=\"T_0026f_row98_col1\" class=\"data row98 col1\" >6.296435</td>\n",
+       "      <td id=\"T_0026f_row98_col2\" class=\"data row98 col2\" >7.970922</td>\n",
+       "      <td id=\"T_0026f_row98_col3\" class=\"data row98 col3\" >1.674487</td>\n",
+       "      <td id=\"T_0026f_row98_col4\" class=\"data row98 col4\" >94</td>\n",
+       "      <td id=\"T_0026f_row98_col5\" class=\"data row98 col5\" >98</td>\n",
+       "      <td id=\"T_0026f_row98_col6\" class=\"data row98 col6\" >-4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row99\" class=\"row_heading level0 row99\" >openchat8192-13b</th>\n",
+       "      <td id=\"T_0026f_row99_col0\" class=\"data row99 col0\" >1664</td>\n",
+       "      <td id=\"T_0026f_row99_col1\" class=\"data row99 col1\" >7.472767</td>\n",
+       "      <td id=\"T_0026f_row99_col2\" class=\"data row99 col2\" >7.897062</td>\n",
+       "      <td id=\"T_0026f_row99_col3\" class=\"data row99 col3\" >0.424295</td>\n",
+       "      <td id=\"T_0026f_row99_col4\" class=\"data row99 col4\" >82</td>\n",
+       "      <td id=\"T_0026f_row99_col5\" class=\"data row99 col5\" >99</td>\n",
+       "      <td id=\"T_0026f_row99_col6\" class=\"data row99 col6\" >-17</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row100\" class=\"row_heading level0 row100\" >phi-2-dpo</th>\n",
+       "      <td id=\"T_0026f_row100_col0\" class=\"data row100 col0\" >1687</td>\n",
+       "      <td id=\"T_0026f_row100_col1\" class=\"data row100 col1\" >7.757096</td>\n",
+       "      <td id=\"T_0026f_row100_col2\" class=\"data row100 col2\" >7.770895</td>\n",
+       "      <td id=\"T_0026f_row100_col3\" class=\"data row100 col3\" >0.013799</td>\n",
+       "      <td id=\"T_0026f_row100_col4\" class=\"data row100 col4\" >77</td>\n",
+       "      <td id=\"T_0026f_row100_col5\" class=\"data row100 col5\" >100</td>\n",
+       "      <td id=\"T_0026f_row100_col6\" class=\"data row100 col6\" >-23</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row101\" class=\"row_heading level0 row101\" >minichat-1.5-3b</th>\n",
+       "      <td id=\"T_0026f_row101_col0\" class=\"data row101 col0\" >1545</td>\n",
+       "      <td id=\"T_0026f_row101_col1\" class=\"data row101 col1\" >6.553443</td>\n",
+       "      <td id=\"T_0026f_row101_col2\" class=\"data row101 col2\" >7.701633</td>\n",
+       "      <td id=\"T_0026f_row101_col3\" class=\"data row101 col3\" >1.148190</td>\n",
+       "      <td id=\"T_0026f_row101_col4\" class=\"data row101 col4\" >92</td>\n",
+       "      <td id=\"T_0026f_row101_col5\" class=\"data row101 col5\" >101</td>\n",
+       "      <td id=\"T_0026f_row101_col6\" class=\"data row101 col6\" >-9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row102\" class=\"row_heading level0 row102\" >vicuna-7b-v1.5</th>\n",
+       "      <td id=\"T_0026f_row102_col0\" class=\"data row102 col0\" >1083</td>\n",
+       "      <td id=\"T_0026f_row102_col1\" class=\"data row102 col1\" >4.797494</td>\n",
+       "      <td id=\"T_0026f_row102_col2\" class=\"data row102 col2\" >7.616893</td>\n",
+       "      <td id=\"T_0026f_row102_col3\" class=\"data row102 col3\" >2.819399</td>\n",
+       "      <td id=\"T_0026f_row102_col4\" class=\"data row102 col4\" >105</td>\n",
+       "      <td id=\"T_0026f_row102_col5\" class=\"data row102 col5\" >102</td>\n",
+       "      <td id=\"T_0026f_row102_col6\" class=\"data row102 col6\" >3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row103\" class=\"row_heading level0 row103\" >llama-2-chat-7b-evol70k-neft</th>\n",
+       "      <td id=\"T_0026f_row103_col0\" class=\"data row103 col0\" >1612</td>\n",
+       "      <td id=\"T_0026f_row103_col1\" class=\"data row103 col1\" >7.602384</td>\n",
+       "      <td id=\"T_0026f_row103_col2\" class=\"data row103 col2\" >7.533053</td>\n",
+       "      <td id=\"T_0026f_row103_col3\" class=\"data row103 col3\" >-0.069331</td>\n",
+       "      <td id=\"T_0026f_row103_col4\" class=\"data row103 col4\" >79</td>\n",
+       "      <td id=\"T_0026f_row103_col5\" class=\"data row103 col5\" >103</td>\n",
+       "      <td id=\"T_0026f_row103_col6\" class=\"data row103 col6\" >-24</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row104\" class=\"row_heading level0 row104\" >recycled-wizardlm-7b-v2.0</th>\n",
+       "      <td id=\"T_0026f_row104_col0\" class=\"data row104 col0\" >1583</td>\n",
+       "      <td id=\"T_0026f_row104_col1\" class=\"data row104 col1\" >7.337129</td>\n",
+       "      <td id=\"T_0026f_row104_col2\" class=\"data row104 col2\" >7.521610</td>\n",
+       "      <td id=\"T_0026f_row104_col3\" class=\"data row104 col3\" >0.184481</td>\n",
+       "      <td id=\"T_0026f_row104_col4\" class=\"data row104 col4\" >86</td>\n",
+       "      <td id=\"T_0026f_row104_col5\" class=\"data row104 col5\" >104</td>\n",
+       "      <td id=\"T_0026f_row104_col6\" class=\"data row104 col6\" >-18</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row105\" class=\"row_heading level0 row105\" >vicuna-7b-v1.3</th>\n",
+       "      <td id=\"T_0026f_row105_col0\" class=\"data row105 col0\" >1110</td>\n",
+       "      <td id=\"T_0026f_row105_col1\" class=\"data row105 col1\" >4.642512</td>\n",
+       "      <td id=\"T_0026f_row105_col2\" class=\"data row105 col2\" >7.156461</td>\n",
+       "      <td id=\"T_0026f_row105_col3\" class=\"data row105 col3\" >2.513949</td>\n",
+       "      <td id=\"T_0026f_row105_col4\" class=\"data row105 col4\" >107</td>\n",
+       "      <td id=\"T_0026f_row105_col5\" class=\"data row105 col5\" >105</td>\n",
+       "      <td id=\"T_0026f_row105_col6\" class=\"data row105 col6\" >2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row106\" class=\"row_heading level0 row106\" >alpaca-farm-ppo-sim-gpt4-20k</th>\n",
+       "      <td id=\"T_0026f_row106_col0\" class=\"data row106 col0\" >511</td>\n",
+       "      <td id=\"T_0026f_row106_col1\" class=\"data row106 col1\" >3.450342</td>\n",
+       "      <td id=\"T_0026f_row106_col2\" class=\"data row106 col2\" >7.121808</td>\n",
+       "      <td id=\"T_0026f_row106_col3\" class=\"data row106 col3\" >3.671466</td>\n",
+       "      <td id=\"T_0026f_row106_col4\" class=\"data row106 col4\" >115</td>\n",
+       "      <td id=\"T_0026f_row106_col5\" class=\"data row106 col5\" >106</td>\n",
+       "      <td id=\"T_0026f_row106_col6\" class=\"data row106 col6\" >9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row107\" class=\"row_heading level0 row107\" >ultralm-13b</th>\n",
+       "      <td id=\"T_0026f_row107_col0\" class=\"data row107 col0\" >1087</td>\n",
+       "      <td id=\"T_0026f_row107_col1\" class=\"data row107 col1\" >5.074590</td>\n",
+       "      <td id=\"T_0026f_row107_col2\" class=\"data row107 col2\" >7.108191</td>\n",
+       "      <td id=\"T_0026f_row107_col3\" class=\"data row107 col3\" >2.033601</td>\n",
+       "      <td id=\"T_0026f_row107_col4\" class=\"data row107 col4\" >102</td>\n",
+       "      <td id=\"T_0026f_row107_col5\" class=\"data row107 col5\" >107</td>\n",
+       "      <td id=\"T_0026f_row107_col6\" class=\"data row107 col6\" >-5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row108\" class=\"row_heading level0 row108\" >baize-v2-13b</th>\n",
+       "      <td id=\"T_0026f_row108_col0\" class=\"data row108 col0\" >930</td>\n",
+       "      <td id=\"T_0026f_row108_col1\" class=\"data row108 col1\" >4.590545</td>\n",
+       "      <td id=\"T_0026f_row108_col2\" class=\"data row108 col2\" >7.012247</td>\n",
+       "      <td id=\"T_0026f_row108_col3\" class=\"data row108 col3\" >2.421702</td>\n",
+       "      <td id=\"T_0026f_row108_col4\" class=\"data row108 col4\" >108</td>\n",
+       "      <td id=\"T_0026f_row108_col5\" class=\"data row108 col5\" >108</td>\n",
+       "      <td id=\"T_0026f_row108_col6\" class=\"data row108 col6\" >0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row109\" class=\"row_heading level0 row109\" >recycled-wizardlm-7b-v1.0</th>\n",
+       "      <td id=\"T_0026f_row109_col0\" class=\"data row109 col0\" >1494</td>\n",
+       "      <td id=\"T_0026f_row109_col1\" class=\"data row109 col1\" >6.632750</td>\n",
+       "      <td id=\"T_0026f_row109_col2\" class=\"data row109 col2\" >6.901477</td>\n",
+       "      <td id=\"T_0026f_row109_col3\" class=\"data row109 col3\" >0.268727</td>\n",
+       "      <td id=\"T_0026f_row109_col4\" class=\"data row109 col4\" >91</td>\n",
+       "      <td id=\"T_0026f_row109_col5\" class=\"data row109 col5\" >109</td>\n",
+       "      <td id=\"T_0026f_row109_col6\" class=\"data row109 col6\" >-18</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row110\" class=\"row_heading level0 row110\" >alpaca-7b_verbose</th>\n",
+       "      <td id=\"T_0026f_row110_col0\" class=\"data row110 col0\" >537</td>\n",
+       "      <td id=\"T_0026f_row110_col1\" class=\"data row110 col1\" >2.933102</td>\n",
+       "      <td id=\"T_0026f_row110_col2\" class=\"data row110 col2\" >6.818464</td>\n",
+       "      <td id=\"T_0026f_row110_col3\" class=\"data row110 col3\" >3.885363</td>\n",
+       "      <td id=\"T_0026f_row110_col4\" class=\"data row110 col4\" >120</td>\n",
+       "      <td id=\"T_0026f_row110_col5\" class=\"data row110 col5\" >110</td>\n",
+       "      <td id=\"T_0026f_row110_col6\" class=\"data row110 col6\" >10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row111\" class=\"row_heading level0 row111\" >alpaca-farm-ppo-human</th>\n",
+       "      <td id=\"T_0026f_row111_col0\" class=\"data row111 col0\" >803</td>\n",
+       "      <td id=\"T_0026f_row111_col1\" class=\"data row111 col1\" >4.100427</td>\n",
+       "      <td id=\"T_0026f_row111_col2\" class=\"data row111 col2\" >6.418603</td>\n",
+       "      <td id=\"T_0026f_row111_col3\" class=\"data row111 col3\" >2.318176</td>\n",
+       "      <td id=\"T_0026f_row111_col4\" class=\"data row111 col4\" >110</td>\n",
+       "      <td id=\"T_0026f_row111_col5\" class=\"data row111 col5\" >111</td>\n",
+       "      <td id=\"T_0026f_row111_col6\" class=\"data row111 col6\" >-1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row112\" class=\"row_heading level0 row112\" >vicuna-7b</th>\n",
+       "      <td id=\"T_0026f_row112_col0\" class=\"data row112 col0\" >1044</td>\n",
+       "      <td id=\"T_0026f_row112_col1\" class=\"data row112 col1\" >4.162611</td>\n",
+       "      <td id=\"T_0026f_row112_col2\" class=\"data row112 col2\" >6.277218</td>\n",
+       "      <td id=\"T_0026f_row112_col3\" class=\"data row112 col3\" >2.114607</td>\n",
+       "      <td id=\"T_0026f_row112_col4\" class=\"data row112 col4\" >109</td>\n",
+       "      <td id=\"T_0026f_row112_col5\" class=\"data row112 col5\" >112</td>\n",
+       "      <td id=\"T_0026f_row112_col6\" class=\"data row112 col6\" >-3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row113\" class=\"row_heading level0 row113\" >alpaca-7b</th>\n",
+       "      <td id=\"T_0026f_row113_col0\" class=\"data row113 col0\" >396</td>\n",
+       "      <td id=\"T_0026f_row113_col1\" class=\"data row113 col1\" >2.591451</td>\n",
+       "      <td id=\"T_0026f_row113_col2\" class=\"data row113 col2\" >5.875487</td>\n",
+       "      <td id=\"T_0026f_row113_col3\" class=\"data row113 col3\" >3.284037</td>\n",
+       "      <td id=\"T_0026f_row113_col4\" class=\"data row113 col4\" >124</td>\n",
+       "      <td id=\"T_0026f_row113_col5\" class=\"data row113 col5\" >113</td>\n",
+       "      <td id=\"T_0026f_row113_col6\" class=\"data row113 col6\" >11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row114\" class=\"row_heading level0 row114\" >phi-2-sft</th>\n",
+       "      <td id=\"T_0026f_row114_col0\" class=\"data row114 col0\" >1068</td>\n",
+       "      <td id=\"T_0026f_row114_col1\" class=\"data row114 col1\" >3.977568</td>\n",
+       "      <td id=\"T_0026f_row114_col2\" class=\"data row114 col2\" >5.853788</td>\n",
+       "      <td id=\"T_0026f_row114_col3\" class=\"data row114 col3\" >1.876220</td>\n",
+       "      <td id=\"T_0026f_row114_col4\" class=\"data row114 col4\" >111</td>\n",
+       "      <td id=\"T_0026f_row114_col5\" class=\"data row114 col5\" >114</td>\n",
+       "      <td id=\"T_0026f_row114_col6\" class=\"data row114 col6\" >-3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row115\" class=\"row_heading level0 row115\" >minichat-3b</th>\n",
+       "      <td id=\"T_0026f_row115_col0\" class=\"data row115 col0\" >868</td>\n",
+       "      <td id=\"T_0026f_row115_col1\" class=\"data row115 col1\" >3.007151</td>\n",
+       "      <td id=\"T_0026f_row115_col2\" class=\"data row115 col2\" >5.729333</td>\n",
+       "      <td id=\"T_0026f_row115_col3\" class=\"data row115 col3\" >2.722182</td>\n",
+       "      <td id=\"T_0026f_row115_col4\" class=\"data row115 col4\" >119</td>\n",
+       "      <td id=\"T_0026f_row115_col5\" class=\"data row115 col5\" >115</td>\n",
+       "      <td id=\"T_0026f_row115_col6\" class=\"data row115 col6\" >4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row116\" class=\"row_heading level0 row116\" >guanaco-33b</th>\n",
+       "      <td id=\"T_0026f_row116_col0\" class=\"data row116 col0\" >1311</td>\n",
+       "      <td id=\"T_0026f_row116_col1\" class=\"data row116 col1\" >5.002494</td>\n",
+       "      <td id=\"T_0026f_row116_col2\" class=\"data row116 col2\" >5.690019</td>\n",
+       "      <td id=\"T_0026f_row116_col3\" class=\"data row116 col3\" >0.687525</td>\n",
+       "      <td id=\"T_0026f_row116_col4\" class=\"data row116 col4\" >103</td>\n",
+       "      <td id=\"T_0026f_row116_col5\" class=\"data row116 col5\" >116</td>\n",
+       "      <td id=\"T_0026f_row116_col6\" class=\"data row116 col6\" >-13</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row117\" class=\"row_heading level0 row117\" >falcon-40b-instruct</th>\n",
+       "      <td id=\"T_0026f_row117_col0\" class=\"data row117 col0\" >662</td>\n",
+       "      <td id=\"T_0026f_row117_col1\" class=\"data row117 col1\" >3.342919</td>\n",
+       "      <td id=\"T_0026f_row117_col2\" class=\"data row117 col2\" >5.607533</td>\n",
+       "      <td id=\"T_0026f_row117_col3\" class=\"data row117 col3\" >2.264614</td>\n",
+       "      <td id=\"T_0026f_row117_col4\" class=\"data row117 col4\" >118</td>\n",
+       "      <td id=\"T_0026f_row117_col5\" class=\"data row117 col5\" >117</td>\n",
+       "      <td id=\"T_0026f_row117_col6\" class=\"data row117 col6\" >1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row118\" class=\"row_heading level0 row118\" >gemma-2b-it</th>\n",
+       "      <td id=\"T_0026f_row118_col0\" class=\"data row118 col0\" >1041</td>\n",
+       "      <td id=\"T_0026f_row118_col1\" class=\"data row118 col1\" >3.401971</td>\n",
+       "      <td id=\"T_0026f_row118_col2\" class=\"data row118 col2\" >5.596482</td>\n",
+       "      <td id=\"T_0026f_row118_col3\" class=\"data row118 col3\" >2.194511</td>\n",
+       "      <td id=\"T_0026f_row118_col4\" class=\"data row118 col4\" >117</td>\n",
+       "      <td id=\"T_0026f_row118_col5\" class=\"data row118 col5\" >118</td>\n",
+       "      <td id=\"T_0026f_row118_col6\" class=\"data row118 col6\" >-1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row119\" class=\"row_heading level0 row119\" >llama-2-7b-chat-hf</th>\n",
+       "      <td id=\"T_0026f_row119_col0\" class=\"data row119 col0\" >1479</td>\n",
+       "      <td id=\"T_0026f_row119_col1\" class=\"data row119 col1\" >4.961340</td>\n",
+       "      <td id=\"T_0026f_row119_col2\" class=\"data row119 col2\" >5.354821</td>\n",
+       "      <td id=\"T_0026f_row119_col3\" class=\"data row119 col3\" >0.393482</td>\n",
+       "      <td id=\"T_0026f_row119_col4\" class=\"data row119 col4\" >104</td>\n",
+       "      <td id=\"T_0026f_row119_col5\" class=\"data row119 col5\" >119</td>\n",
+       "      <td id=\"T_0026f_row119_col6\" class=\"data row119 col6\" >-15</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row120\" class=\"row_heading level0 row120\" >openbuddy-falcon-7b-v6</th>\n",
+       "      <td id=\"T_0026f_row120_col0\" class=\"data row120 col0\" >1152</td>\n",
+       "      <td id=\"T_0026f_row120_col1\" class=\"data row120 col1\" >3.521174</td>\n",
+       "      <td id=\"T_0026f_row120_col2\" class=\"data row120 col2\" >4.826124</td>\n",
+       "      <td id=\"T_0026f_row120_col3\" class=\"data row120 col3\" >1.304950</td>\n",
+       "      <td id=\"T_0026f_row120_col4\" class=\"data row120 col4\" >113</td>\n",
+       "      <td id=\"T_0026f_row120_col5\" class=\"data row120 col5\" >120</td>\n",
+       "      <td id=\"T_0026f_row120_col6\" class=\"data row120 col6\" >-7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row121\" class=\"row_heading level0 row121\" >alpaca-7b_concise</th>\n",
+       "      <td id=\"T_0026f_row121_col0\" class=\"data row121 col0\" >351</td>\n",
+       "      <td id=\"T_0026f_row121_col1\" class=\"data row121 col1\" >1.991176</td>\n",
+       "      <td id=\"T_0026f_row121_col2\" class=\"data row121 col2\" >4.463108</td>\n",
+       "      <td id=\"T_0026f_row121_col3\" class=\"data row121 col3\" >2.471931</td>\n",
+       "      <td id=\"T_0026f_row121_col4\" class=\"data row121 col4\" >129</td>\n",
+       "      <td id=\"T_0026f_row121_col5\" class=\"data row121 col5\" >121</td>\n",
+       "      <td id=\"T_0026f_row121_col6\" class=\"data row121 col6\" >8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row122\" class=\"row_heading level0 row122\" >phi-2</th>\n",
+       "      <td id=\"T_0026f_row122_col0\" class=\"data row122 col0\" >626</td>\n",
+       "      <td id=\"T_0026f_row122_col1\" class=\"data row122 col1\" >2.350210</td>\n",
+       "      <td id=\"T_0026f_row122_col2\" class=\"data row122 col2\" >4.395548</td>\n",
+       "      <td id=\"T_0026f_row122_col3\" class=\"data row122 col3\" >2.045338</td>\n",
+       "      <td id=\"T_0026f_row122_col4\" class=\"data row122 col4\" >126</td>\n",
+       "      <td id=\"T_0026f_row122_col5\" class=\"data row122 col5\" >122</td>\n",
+       "      <td id=\"T_0026f_row122_col6\" class=\"data row122 col6\" >4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row123\" class=\"row_heading level0 row123\" >baize-v2-7b</th>\n",
+       "      <td id=\"T_0026f_row123_col0\" class=\"data row123 col0\" >1127</td>\n",
+       "      <td id=\"T_0026f_row123_col1\" class=\"data row123 col1\" >3.404815</td>\n",
+       "      <td id=\"T_0026f_row123_col2\" class=\"data row123 col2\" >4.382565</td>\n",
+       "      <td id=\"T_0026f_row123_col3\" class=\"data row123 col3\" >0.977750</td>\n",
+       "      <td id=\"T_0026f_row123_col4\" class=\"data row123 col4\" >116</td>\n",
+       "      <td id=\"T_0026f_row123_col5\" class=\"data row123 col5\" >123</td>\n",
+       "      <td id=\"T_0026f_row123_col6\" class=\"data row123 col6\" >-7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row124\" class=\"row_heading level0 row124\" >chatglm2-6b</th>\n",
+       "      <td id=\"T_0026f_row124_col0\" class=\"data row124 col0\" >1027</td>\n",
+       "      <td id=\"T_0026f_row124_col1\" class=\"data row124 col1\" >2.762185</td>\n",
+       "      <td id=\"T_0026f_row124_col2\" class=\"data row124 col2\" >4.359283</td>\n",
+       "      <td id=\"T_0026f_row124_col3\" class=\"data row124 col3\" >1.597098</td>\n",
+       "      <td id=\"T_0026f_row124_col4\" class=\"data row124 col4\" >123</td>\n",
+       "      <td id=\"T_0026f_row124_col5\" class=\"data row124 col5\" >124</td>\n",
+       "      <td id=\"T_0026f_row124_col6\" class=\"data row124 col6\" >-1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row125\" class=\"row_heading level0 row125\" >pythia-12b-mix-sft</th>\n",
+       "      <td id=\"T_0026f_row125_col0\" class=\"data row125 col0\" >913</td>\n",
+       "      <td id=\"T_0026f_row125_col1\" class=\"data row125 col1\" >2.578090</td>\n",
+       "      <td id=\"T_0026f_row125_col2\" class=\"data row125 col2\" >4.221362</td>\n",
+       "      <td id=\"T_0026f_row125_col3\" class=\"data row125 col3\" >1.643272</td>\n",
+       "      <td id=\"T_0026f_row125_col4\" class=\"data row125 col4\" >125</td>\n",
+       "      <td id=\"T_0026f_row125_col5\" class=\"data row125 col5\" >125</td>\n",
+       "      <td id=\"T_0026f_row125_col6\" class=\"data row125 col6\" >0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row126\" class=\"row_heading level0 row126\" >falcon-7b-instruct</th>\n",
+       "      <td id=\"T_0026f_row126_col0\" class=\"data row126 col0\" >478</td>\n",
+       "      <td id=\"T_0026f_row126_col1\" class=\"data row126 col1\" >2.146618</td>\n",
+       "      <td id=\"T_0026f_row126_col2\" class=\"data row126 col2\" >4.036938</td>\n",
+       "      <td id=\"T_0026f_row126_col3\" class=\"data row126 col3\" >1.890320</td>\n",
+       "      <td id=\"T_0026f_row126_col4\" class=\"data row126 col4\" >127</td>\n",
+       "      <td id=\"T_0026f_row126_col5\" class=\"data row126 col5\" >126</td>\n",
+       "      <td id=\"T_0026f_row126_col6\" class=\"data row126 col6\" >1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row127\" class=\"row_heading level0 row127\" >oasst-sft-pythia-12b</th>\n",
+       "      <td id=\"T_0026f_row127_col0\" class=\"data row127 col0\" >726</td>\n",
+       "      <td id=\"T_0026f_row127_col1\" class=\"data row127 col1\" >1.790114</td>\n",
+       "      <td id=\"T_0026f_row127_col2\" class=\"data row127 col2\" >3.270102</td>\n",
+       "      <td id=\"T_0026f_row127_col3\" class=\"data row127 col3\" >1.479988</td>\n",
+       "      <td id=\"T_0026f_row127_col4\" class=\"data row127 col4\" >130</td>\n",
+       "      <td id=\"T_0026f_row127_col5\" class=\"data row127 col5\" >127</td>\n",
+       "      <td id=\"T_0026f_row127_col6\" class=\"data row127 col6\" >3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row128\" class=\"row_heading level0 row128\" >guanaco-13b</th>\n",
+       "      <td id=\"T_0026f_row128_col0\" class=\"data row128 col0\" >1774</td>\n",
+       "      <td id=\"T_0026f_row128_col1\" class=\"data row128 col1\" >3.469597</td>\n",
+       "      <td id=\"T_0026f_row128_col2\" class=\"data row128 col2\" >3.003787</td>\n",
+       "      <td id=\"T_0026f_row128_col3\" class=\"data row128 col3\" >-0.465810</td>\n",
+       "      <td id=\"T_0026f_row128_col4\" class=\"data row128 col4\" >114</td>\n",
+       "      <td id=\"T_0026f_row128_col5\" class=\"data row128 col5\" >128</td>\n",
+       "      <td id=\"T_0026f_row128_col6\" class=\"data row128 col6\" >-14</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row129\" class=\"row_heading level0 row129\" >guanaco-7b</th>\n",
+       "      <td id=\"T_0026f_row129_col0\" class=\"data row129 col0\" >1364</td>\n",
+       "      <td id=\"T_0026f_row129_col1\" class=\"data row129 col1\" >2.880002</td>\n",
+       "      <td id=\"T_0026f_row129_col2\" class=\"data row129 col2\" >2.871117</td>\n",
+       "      <td id=\"T_0026f_row129_col3\" class=\"data row129 col3\" >-0.008885</td>\n",
+       "      <td id=\"T_0026f_row129_col4\" class=\"data row129 col4\" >121</td>\n",
+       "      <td id=\"T_0026f_row129_col5\" class=\"data row129 col5\" >129</td>\n",
+       "      <td id=\"T_0026f_row129_col6\" class=\"data row129 col6\" >-8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th id=\"T_0026f_level0_row130\" class=\"row_heading level0 row130\" >baichuan-13b-chat</th>\n",
+       "      <td id=\"T_0026f_row130_col0\" class=\"data row130 col0\" >1727</td>\n",
+       "      <td id=\"T_0026f_row130_col1\" class=\"data row130 col1\" >1.992146</td>\n",
+       "      <td id=\"T_0026f_row130_col2\" class=\"data row130 col2\" >2.062170</td>\n",
+       "      <td id=\"T_0026f_row130_col3\" class=\"data row130 col3\" >0.070025</td>\n",
+       "      <td id=\"T_0026f_row130_col4\" class=\"data row130 col4\" >128</td>\n",
+       "      <td id=\"T_0026f_row130_col5\" class=\"data row130 col5\" >130</td>\n",
+       "      <td id=\"T_0026f_row130_col6\" class=\"data row130 col6\" >-2</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n"
       ],
       "text/plain": [
-       "<pandas.io.formats.style.Styler at 0x15fa5a990>"
+       "<pandas.io.formats.style.Styler at 0x1b84eb0d0>"
       ]
      },
      "execution_count": 27,
@@ -6053,7 +6121,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 28,
    "id": "dc3b8c58-a686-47b2-a4dd-d9e6cc8089f2",
    "metadata": {},
    "outputs": [],
@@ -6094,7 +6162,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 30,
    "id": "4ba44847-8e03-486c-bb39-2148a7f2cbf0",
    "metadata": {},
    "outputs": [
@@ -6104,7 +6172,7 @@
        "0.4972910406584219"
       ]
      },
-     "execution_count": 34,
+     "execution_count": 30,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -6125,7 +6193,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 31,
    "id": "e5482374-61a4-409d-9993-bac7c79a3c9d",
    "metadata": {},
    "outputs": [],
@@ -6135,7 +6203,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 32,
    "id": "dd2e8f6a-f702-46ad-b24f-e705b8a686ec",
    "metadata": {},
    "outputs": [
@@ -6144,19 +6212,19 @@
       "text/plain": [
        "gpt4_1106_preview_verbose    1264.947899\n",
        "gpt4_1106_preview            1254.000000\n",
-       "gpt4_1106_preview_concise    1197.190903\n",
+       "gpt4_1106_preview_concise    1197.190905\n",
        "claude-3-opus-20240229       1186.394707\n",
-       "gpt4                         1169.900608\n",
+       "gpt4                         1169.900609\n",
        "                                ...     \n",
-       "falcon-7b-instruct            703.579173\n",
+       "falcon-7b-instruct            703.579174\n",
        "oasst-sft-pythia-12b          665.600234\n",
        "guanaco-13b                   650.365762\n",
        "guanaco-7b                    642.280987\n",
-       "baichuan-13b-chat             583.349617\n",
-       "Name: np.tanh(rand_delta_len_std_only) + instruction_difficulty + not_gamed_baseline.astype(float) - 1, Length: 129, dtype: float64"
+       "baichuan-13b-chat             583.349616\n",
+       "Name: np.tanh(rand_delta_len_std_only) + instruction_difficulty + not_gamed_baseline.astype(float) - 1, Length: 131, dtype: float64"
       ]
      },
-     "execution_count": 44,
+     "execution_count": 32,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -6167,17 +6235,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": 33,
    "id": "c3cc7204-d14c-4d40-828f-2c0ebc9c90a8",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "PearsonRResult(statistic=0.9551930453734696, pvalue=6.035381315868855e-18)"
+       "PearsonRResult(statistic=0.956960109042506, pvalue=7.650929551873686e-20)"
       ]
      },
-     "execution_count": 45,
+     "execution_count": 33,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -6229,6 +6297,14 @@
     "\n",
     "$$min_{\\mathbf{w'}_l[m], \\mathbf{w'}_{x}[m], \\mathbf{w'}_{m}[m]} \\sum_i  \\mathcal{L}_i(logistic( \\mathbf{w'}_l[m]  * tanh(standardized(length(m(x_i)) - length(b(x_i)))) + \\mathbf{w'}_x[m] * embedding(x_i)  + \\mathbf{w}'_m[m] ) + \\lambda' \\mathcal{L}_i(logistic( \\mathbf{w'}_l[m]  * tanh(standardized(length(b'(x_i)) - length(b(x_i))))$$\n"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6ebb64fb-4bbd-4abb-ad89-99812f21d60a",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
diff --git a/src/alpaca_eval/constants.py b/src/alpaca_eval/constants.py
index 7cbacf2e..cf617bf3 100644
--- a/src/alpaca_eval/constants.py
+++ b/src/alpaca_eval/constants.py
@@ -206,26 +206,29 @@ def ALPACAFARM_GOLD_ANNOTATIONS():
 # maps models to Arena Elo rating
 CHATBOT_ARENA_LEADERBOARD = {
     "gpt4_1106_preview": 1252,
-    "gpt4_0314": 1190,
-    "gpt4_0613": 1162,
-    "mistral-medium": 1150,
-    "claude": 1149,
-    "claude-2": 1132,
-    "claude-2.1": 1119,
-    "Mixtral-8x7B-Instruct-v0.1": 1118,
-    "gpt-3.5-turbo-0613": 1118,
+    "claude-3-opus-20240229": 1233,
+    "gpt4_0314": 1185,
+    "claude-3-sonnet-20240229": 1180,
+    "gpt4_0613": 1161,
+    "mistral-large-2402": 1155,
+    "mistral-medium": 1147,
+    "claude": 1146,
+    "claude-2": 1127,
+    "claude-2.1": 1117,
+    "Mixtral-8x7B-Instruct-v0.1": 1116,
+    "gpt-3.5-turbo-0613": 1115,
     "Yi-34B-Chat": 1115,
-    "gemini-pro": 1114,
-    "claude-instant-1.2": 1109,
-    "gpt-3.5-turbo-0301": 1105,
-    "wizardlm-70b": 1105,
-    "tulu-2-dpo-70b": 1104,
-    "vicuna-33b-v1.3": 1093,
-    "Starling-LM-7B-alpha": 1090,
+    "gemini-pro": 1112,
+    "claude-instant-1.2": 1105,
+    "gpt-3.5-turbo-0301": 1103,
+    "wizardlm-70b": 1103,
+    "tulu-2-dpo-70b": 1099,
+    "vicuna-33b-v1.3": 1090,
+    "Starling-LM-7B-alpha": 1085,
     "deepseek-llm-67b-chat": 1082,
     "llama-2-70b-chat-hf": 1082,
-    "OpenHermes-2.5-Mistral-7B": 1078,
-    "gpt-3.5-turbo-1106": 1071,
+    "OpenHermes-2.5-Mistral-7B": 1073,
+    "gpt-3.5-turbo-1106": 1069,
     "dolphin-2.2.1-mistral-7b": 1065,
     "wizardlm-13b-v1.2": 1058,
     "zephyr-7b-beta": 1051,
diff --git a/src/alpaca_eval/leaderboards/data_AlpacaEval_2/weighted_alpaca_eval_gpt4_turbo_leaderboard.csv b/src/alpaca_eval/leaderboards/data_AlpacaEval_2/weighted_alpaca_eval_gpt4_turbo_leaderboard.csv
index 86b639a0..413db3e8 100644
--- a/src/alpaca_eval/leaderboards/data_AlpacaEval_2/weighted_alpaca_eval_gpt4_turbo_leaderboard.csv
+++ b/src/alpaca_eval/leaderboards/data_AlpacaEval_2/weighted_alpaca_eval_gpt4_turbo_leaderboard.csv
@@ -8,9 +8,11 @@ Qwen1.5-72B-Chat,26.49828339562733,1.304236164893057,201,600,4,805,25.2173913043
 gpt4_0314,22.073258928708075,1.2466725494608204,172,627,6,805,21.73913043478261,verified,1371,35.30706121640206
 claude-3-sonnet-20240229,25.556325292273296,1.3419811051815638,193,608,4,805,24.22360248447205,verified,1420,34.87247436243302
 gpt4_0613_verbose,23.237360043453418,1.283539505582624,171,630,4,805,21.490683229813666,dev,1473,33.82126688658535
+mistral-large-2402,21.43877598137888,1.2485232545097724,166,638,1,805,20.6832298136646,verified,1362,32.65207998531868
 claude-2.1_verbose,24.35407109006212,1.293586209982439,191,613,1,805,23.7888198757764,dev,1414,30.29117916664986
 gpt4_0613,15.75503808763975,1.0754642482396215,117,684,4,805,14.782608695652174,verified,1140,30.18332231673423
 Snorkel-Mistral-PairRM-DPO-best-of-16,34.8601328912795,1.3599450436840308,270,533,2,805,33.66459627329193,community,2616,29.974321613074405
+Contextual-KTO-Mistral-PairRM,33.227355200024846,1.3779687477923963,260,544,1,805,32.36024844720497,verified,2521,29.705808939683976
 pairrm-Yi-34B-Chat,31.24128294680746,1.34824373994879,239,563,3,805,29.87577639751553,community,2195,28.81484086684313
 mistral-medium,21.855772543652176,1.2682402187223842,164,639,2,805,20.496894409937887,minimal,1500,28.614337401726104
 claude-2,17.188240356708075,1.17482825615589,131,673,1,805,16.335403726708076,minimal,1069,28.155196141629148
@@ -124,7 +126,7 @@ baize-v2-7b,3.404814977515528,0.5826293992489878,26,779,0,805,3.229813664596273,
 chatglm2-6b,2.7621847964596284,0.5020758950625489,19,781,5,805,2.670807453416149,community,1027,4.35928292679035
 pythia-12b-mix-sft,2.5780902809689445,0.5127326717340586,19,786,0,805,2.360248447204969,verified,913,4.221361861408184
 falcon-7b-instruct,2.146617553167702,0.454225792894195,16,787,2,805,2.111801242236025,verified,478,4.036937566812824
-oasst-sft-pythia-12b,1.790114083180124,0.39855808830493417,13,790,2,805,1.7391304347826086,verified,726,3.2701021144567473
+oasst-sft-pythia-12b,1.790114083180124,0.3985580883049341,13,790,2,805,1.7391304347826086,verified,726,3.270102114456748
 guanaco-13b,3.469596859739131,0.5518606725700214,22,780,3,805,2.919254658385093,verified,1774,3.003787329611614
 guanaco-7b,2.880002266173913,0.5202924149314048,21,783,1,805,2.670807453416149,verified,1364,2.871116813131697
 baichuan-13b-chat,1.9921455615279504,0.4176985079331233,14,790,1,805,1.8012422360248446,community,1727,2.062170253598568