Baichuan AI· @BaichuanAI · X·· 2026-01-16AI 评分55
AI 导读
百川智能正式开源新一代医疗大模型 Baichuan-M3，HealthBench 得分 65.1，HealthBench Hard 得分 44.4 排名第一。官方称其在医疗领域全面超过 GPT-5.2，图中还给出 3.5 的幻觉率对比数据。
正文
We have officially open-sourced the new-generation medical LLM Baichuan-M3, which scored 65.1 on HealthBench and claimed the championship with 44.4 on HealthBench Hard. It has comprehensively outperformed GPT-5.2 across the board in the medical field. @OpenAI @claudeai
来源：Baichuan AI · x.com