OpenLLMFrenchLeaderboard

Running on CPU Upgrade

Doubts about the reliability of the IFEval-fr dataset.

by LeMoussel - opened Mar 21

Mar 21

When looking at the results on this OpenLLMFrenchleaderboard, I am somewhat surprised by the low scores for the IFEval-fr metric. None of the models score above 17 points. This raises. Is the data of poor quality? Could there be a bug in the evaluation code?

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