HyperAI超神经

Multiple Choice Question Answering Mcqa On 9

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
BLOOM (few-shot, k=5)25.7Galactica: A Large Language Model for Science
GAL 120B (zero-shot)65.1Galactica: A Large Language Model for Science
Gopher (few-shot, k=5)65.8Galactica: A Large Language Model for Science
OPT (few-shot, k=5)23.0Galactica: A Large Language Model for Science
Chinchilla (few-shot, k=5)73.0Galactica: A Large Language Model for Science
0 of 5 row(s) selected.