Llama 3.1 8B on BBH (BIG-Bench Hard): Score Breakdown

Llama 3.1 8B × BBH (BIG-Bench Hard)

점수 내역

모델 순위점수
#121 / 20567.1

성능 분석

Llama 3.1 8B achieves 67.1 on BBH (BIG-Bench Hard).