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

Claude 2.1 × MMLU (Massive Multitask Language Understanding)

점수 내역

모델 순위점수
#159 / 20560.9

성능 분석

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