List your company

Multitask Language Understanding on MMLU f_clean o=5

67Acc (Exact)baseline
44.22450.13756.0561.963Jan 27, 2026

Evaluation results

MethodLinks
baselineModel=Qwen 2.5, Access=–2026.016767.167.3
baselineModel=LLaMA-3, Access=–2026.0157.656.554.9
baselineModel=Mistral, Access=–2026.0145.143.440.6