Claude 3.5 Sonnet (2024-10-22) on MMLU (Massive Multitask Language Understanding): Score Breakdown

Claude 3.5 Sonnet (2024-10-22) × MMLU (Massive Multitask Language Understanding)

Rincian Skor

Peringkat ModelSkor
#9 / 20587.2

Analisis Kinerja

Claude 3.5 Sonnet (2024-10-22) achieves 87.2 on MMLU (Massive Multitask Language Understanding).