醫療 AI 助理要回答醫師的真實問題,也可能得查詢醫院病歷;這些工作需要不同能力。
- Ant Group 發布了 560B 引數的醫療 MoE 模型 LingSante-3.1-flash,並表示它在 HealthBench Professional、HLE、BrowseComp 和 EHR-Complex 四項基準上超越 GPT-6 Astra、Claude Opus 5.5 和 Gemini 4 Argon。EHR-Complex 測試模型查詢醫院病歷資料庫的能力。
- 模型權重已放在 Hugging Face,採用 MIT 授權。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
LingSante-3.1-flash在四項醫療與通用基準上領先多個模型,呈現醫療推理、病歷查詢與工具使用能力的比較結果。
Ant Group released LingSante-3.1-flash, a 560B-parameter medical MoE model, and it tops GPT-6 Astra, Claude Opus 5.5 and Gemini 4 Argon on HealthBench Professional, HLE, BrowseComp and EHR-Complex.
HealthBench Professional cover answering real clinician requests that real doctors bring to chatbots. EHR-Complex tests an agent querying a hospital records database.
weights on Huggingface, with MIT-license.
Ant mixed medical and general data from pretraining onward, trained medical reasoning, tool use, search and clinician-style behavior as separate skills with their own RL rewards on physician- and verifier-checked tasks, then merged those specialists into one model through multi-teacher on-policy distillation.