HyperAI超神経

Multiple Choice Question Answering Mcqa On 13

評価指標

Accuracy

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名
Accuracy
Paper TitleRepository
Chinchilla (few-shot, k=5)51Galactica: A Large Language Model for Science
BLOOM (few-shot, k=5)19Galactica: A Large Language Model for Science
GAL 120B (zero-shot)46Galactica: A Large Language Model for Science
OPT (few-shot, k=5)30Galactica: A Large Language Model for Science
Gopher (few-shot, k=5)45Galactica: A Large Language Model for Science
0 of 5 row(s) selected.