From 29329762dea825789dc0301e2e8bee282f5a46f6 Mon Sep 17 00:00:00 2001 From: Yann Dubois Date: Sun, 1 Oct 2023 17:21:32 -0700 Subject: [PATCH] add alpaca_eval_gpt4_fn --- README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index e529153f..e3553b13 100644 --- a/README.md +++ b/README.md @@ -280,7 +280,8 @@ See [here](https://github.com/tatsu-lab/alpaca_eval/tree/main/src/alpaca_eval/ev evaluators that are available out of the box and their associated metrics. | | Human agreement [%] | Price [$/1000 examples] | Time [seconds/1000 examples] | Bias | Variance | Proba. prefer longer | -|:------------------------|--------------------:|------------------------:|-----------------------------:|-----:|---------:|---------------------:| +|:------------------------|--------------------:|------------------------:|-----------------------------:|-----:|---------:|--------------------:| +| alpaca_eval_gpt4_fn | 71.0 | 14.5 | 5046 | 27.6 | 11.1 | 0.75 | | alpaca_eval_gpt4 | 69.2 | 13.6 | 1455 | 28.4 | 14.6 | 0.68 | | aviary_gpt4 | 69.1 | 12.8 | 1869 | 29.5 | 13.1 | 0.70 | | gpt4 | 66.9 | 12.5 | 1037 | 31.5 | 14.6 | 0.65 |