Claude 3 Opus (2024-02-29) on MMLU (Massive Multitask Language Understanding): Score Breakdown

Claude 3 Opus (2024-02-29) × MMLU (Massive Multitask Language Understanding)

Rincian Skor

Peringkat ModelSkor
#18 / 20585.7

Analisis Kinerja

Claude 3 Opus (2024-02-29) achieves 85.7 on MMLU (Massive Multitask Language Understanding).