Llama 3.3 70B on BBH (BIG-Bench Hard): Score Breakdown

Llama 3.3 70B × BBH (BIG-Bench Hard)

점수 내역

모델 순위점수
#11 / 20583.9

성능 분석

Llama 3.3 70B achieves 83.9 on BBH (BIG-Bench Hard).