Baichuan Intelligent jointly with Tsinghua releases medical-enhanced large model Baichuan-M4, topping OpenAI medical benchmark
The model ranks first in the world simultaneously on the three leaderboards HealthBench, HealthBench Hard, and HealthBench Professional, comprehensively surpassing GPT-5.5, Claude Opus 4.7, DeepSeek-V4-Pro, with hallucination rate as low as 3.3%.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open the original article on ITHome