HyperAI超神经

Multiple Choice Question Answering Mcqa On 3

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
Gopher (few-shot, k=5)25Galactica: A Large Language Model for Science
Chinchilla (few-shot, k=5)31Galactica: A Large Language Model for Science
OPT (few-shot, k=5)21Galactica: A Large Language Model for Science
GAL 120B (zero-shot)27Galactica: A Large Language Model for Science
GAL 30B (zero-shot)33.3Galactica: A Large Language Model for Science
0 of 5 row(s) selected.