Spaces:

open-llm-leaderboard
/

open_llm_leaderboard

Running on CPU Upgrade

Which accuracy rate does IFEval finally use?

#822

by HaoxuFang - opened Jul 4

Jul 4

•

In IFEval's original paper, they utilize four different accuracy rates to evaluate results. Which one of these is used on the leaderboard?

HaoxuFang changed discussion status to closed Jul 5

Jul 30

+1 on this question

Open LLM Leaderboard org Jul 31

Hi!
We use the mean of the 2 strict metrics (more info in our doc).

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment