Models

LingSante-3.1-air-VL:124B 参数开源医疗模型超越 GPT-6.1 Sol

Why we picked it

124B 的开源医疗模型居然在四项医疗基准上赢了 GPT-6.1 Sol 和 Gemini 3.8 Flash,做医疗 AI 的朋友值得看看能不能拿来自己部署,开源权重意味着不用付 API 费用。

LingSante-3.1-air-VL 是一个 124B 参数的开源权重医疗模型,在四项医疗基准上的成绩超过 GPT-6.

Body

1 Sol 和 Gemini 3.8 Flash。

它同时在浏览和工具使用任务上也给出了较强的表现,说明医疗垂直能力没有以牺牲通用能力为代价。模型采用开源权重发布,开发者可以自行下载部署。

医疗领域此前主要由闭源模型主导,这个成绩表明开源医疗模型在专项评测上已经具备竞争力。对医疗 AI 产品团队来说,多了一个可以私有化部署的选择。

Original · Ate-a-Pi

This is impressive!

LingSante-3.1-air-VL is a 124B-parameter open-weight medical model that outperforms GPT-6.1 Sol and Gemini 3.8 Flash across four medical benchmarks, while also delivering strong results in browsing and tool use.

Open-source medical AI is getting seriously competitive.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison and AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include LingSante-3.1-air-VL, GPT-6.1 Sol, Gemini 3.8 Flash, open-source models.

Source attribution: curated from Ate-a-Pi (@svpino). Cross-source corroboration: 2 independent sources have covered this development (including IT之家), confirming industry-wide signal strength.