Claude 2.1 on MMLU (Massive Multitask Language Understanding): Score Breakdown

Claude 2.1 × MMLU (Massive Multitask Language Understanding)

Rincian Skor

Peringkat ModelSkor
#159 / 20560.9

Analisis Kinerja

Claude 2.1 achieves 60.9 on MMLU (Massive Multitask Language Understanding).