Shanghai AI Lab jointly launched GenMedicalEval, a Chinese medical large language model evaluation framework, with Shanghai Jiaotong University, East China Normal, etc. The evaluation showed that the generalized large models all showed relatively excellent performance, in which GPT-4 performed in a balanced manner, with no obvious weak points.
Shanghai AI Lab and others launch Chinese-language medical macromodel evaluation framework
Previous: 开源中国将上线 Hugging Face 大模型社区