HyperAI초신경

Multiple Choice Question Answering Mcqa On 16

평가 지표

Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
Accuracy
Paper TitleRepository
Gopher (few-shot, k=5)23.7Galactica: A Large Language Model for Science
Chinchilla (few-shot, k=5)31.9Galactica: A Large Language Model for Science
BLOOM (few-shot, k=5)27Galactica: A Large Language Model for Science
GAL 120B (zero-shot)32.6Galactica: A Large Language Model for Science
OPT (few-shot, k=5)24.4Galactica: A Large Language Model for Science
0 of 5 row(s) selected.