Xunfei Xinghuo medical large model tops the MedBench list, ranking first in multiple core abilities.

The medical large-scale model evaluation platform MedBench has released the latest ranking results, with the iFLYTEK Starfire medical large model ranking first with an outstanding comprehensive score of 95.4, leading in various core abilities such as complex medical reasoning, medical language understanding, medical safety, and ethics. As an authoritative evaluation system and platform for Chinese medical large models jointly created by the Shanghai Artificial Intelligence Laboratory and multiple institutions, MedBench integrates a vast amount of medical knowledge and the rich experience of medical experts from medical institutions, establishing a scientific evaluation system covering five dimensions: medical language understanding, medical language generation, medical knowledge question answering, complex medical reasoning, medical safety, and ethics.