Add evaluation results for GPQA and MMLU-Pro

#6
by SaylorTwift HF Staff - opened

Adds .eval_results/LFM2.5-230M.yaml with GPQA Diamond (25.41) and MMLU-Pro (20.25) scores extracted from the model card benchmark table.

SaylorTwift changed pull request status to closed

Sign up or log in to comment