HyperAI超神经

Multiple Choice Question Answering Mcqa On 17

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

模型名称
Accuracy
Paper TitleRepository
GAL 120B (zero-shot)62.8Galactica: A Large Language Model for Science
BLOOM (few-shot, k=5)32.4Galactica: A Large Language Model for Science
Gopher (few-shot, k=5)60Galactica: A Large Language Model for Science
Chinchilla (few-shot, k=5)62.1Galactica: A Large Language Model for Science
OPT (few-shot, k=5)36.6Galactica: A Large Language Model for Science
0 of 5 row(s) selected.