List your company

Massive Multitask Language Understanding on MMLU Full Text

64.9Normalized Log AccuracyT-Free
62.19662.89863.664.302Mar 16, 2026

Evaluation results

MethodLinks
T-Freeshots=5-shot2026.0364.95.31
HATifiedshots=5-shot2026.0363.85.31
Llamashots=5-shot2026.0362.34.56