Spaces:

open-llm-leaderboard

/

open_llm_leaderboard

like 11.7k

Running on CPU Upgrade

Hi @huu-ontocord ,

MATH Lvl 5 is a challenging benchmark for many models, I suppose this may be the case with microsoft/Phi-3-small-128k-instruct as well. To double-check the results, I re-ran the evaluation with the last commit and the numbers remained the same.

You can investigate the results here, in the Details, if you want to. Plus, this discussion can be also helpful, I described there how to access a details dataset.

Feel free to open a new discussion in case of any questions!