HyperAI초신경

Multiple Choice Question Answering Mcqa On 20

평가 지표

Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
Accuracy
Paper TitleRepository
Gopher (few-shot, k=5)50Galactica: A Large Language Model for Science
OPT (few-shot, k=5)43.5Galactica: A Large Language Model for Science
Chinchilla (few-shot, k=5)58.8Galactica: A Large Language Model for Science
GAL 120B (zero-shot)41.2Galactica: A Large Language Model for Science
BLOOM (few-shot, k=5)19.4Galactica: A Large Language Model for Science
0 of 5 row(s) selected.