HyperAI超神经

Multiple Choice Question Answering Mcqa On 25

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

比较表格
模型名称Accuracy
towards-expert-level-medical-question92.3
towards-expert-level-medical-question95.2
biomedgpt-open-multimodal-generative-pre51.1
towards-expert-level-medical-question93.4
llama-2-open-foundation-and-fine-tuned-chat43.38
llama-2-open-foundation-and-fine-tuned-chat40.07