HyperAI超神经

Multiple Choice Question Answering Mcqa On 14

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)23.2Galactica: A Large Language Model for Science
OPT (few-shot, k=5)21.7Galactica: A Large Language Model for Science
GAL 120B (zero-shot)47.8Galactica: A Large Language Model for Science
Chinchilla (few-shot, k=5)58.1Galactica: A Large Language Model for Science
0 of 4 row(s) selected.