DeepSeek V2 Chat on BBH (BIG-Bench Hard): Score Breakdown

DeepSeek V2 Chat × BBH (BIG-Bench Hard)

점수 내역

모델 순위점수
#64 / 20575.4

성능 분석

DeepSeek V2 Chat achieves 75.4 on BBH (BIG-Bench Hard).