Claude 3.5 Sonnet (2024-10-22) on BBH (BIG-Bench Hard): Score Breakdown

Claude 3.5 Sonnet (2024-10-22) × BBH (BIG-Bench Hard)

점수 내역

모델 순위점수
#8 / 20584.2

성능 분석

Claude 3.5 Sonnet (2024-10-22) achieves 84.2 on BBH (BIG-Bench Hard).