HyperAI超神経

Multiple Choice Question Answering Mcqa On 19

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
OPT (few-shot, k=5)29.8Galactica: A Large Language Model for Science
GAL 120B (zero-shot)33.8Galactica: A Large Language Model for Science
BLOOM (few-shot, k=5)25.2Galactica: A Large Language Model for Science
Chinchilla (few-shot, k=5)36.4Galactica: A Large Language Model for Science
0 of 4 row(s) selected.