Claude 3 Sonnet on MMLU (Massive Multitask Language Understanding): Score Breakdown

Claude 3 Sonnet × MMLU (Massive Multitask Language Understanding)

Rincian Skor

Peringkat ModelSkor
#42 / 20581.5

Analisis Kinerja

Claude 3 Sonnet achieves 81.5 on MMLU (Massive Multitask Language Understanding).