GPT-4o (2024-05-13) on BBH (BIG-Bench Hard): Score Breakdown

GPT-4o (2024-05-13) × BBH (BIG-Bench Hard)

점수 내역

모델 순위점수
#3 / 20586.7

성능 분석

GPT-4o (2024-05-13) achieves 86.7 on BBH (BIG-Bench Hard).