HyperAI초신경

Question Answering On Obqa

평가 지표

Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

비교 표
모델 이름Accuracy
llama-open-and-efficient-foundation-language-157.2
llama-open-and-efficient-foundation-language-156.4
finetuned-language-models-are-zero-shot78.2
palm-scaling-language-modeling-with-pathways-153.4
finetuned-language-models-are-zero-shot78.4
palm-scaling-language-modeling-with-pathways-150.4
language-models-are-few-shot-learners57.6
llama-open-and-efficient-foundation-language-160.2
llama-open-and-efficient-foundation-language-158.6