跳到正文
Aran Komatsuzaki· @arankomatsuzaki · X·· 2 小时前同事件AI 评分78
AI 导读

Ant Ling 发布开源权重 MoE 模型 LingSante-3.1-flash,总参数 560B、每 token 激活 25B,采用 MIT 许可,支持 1M 上下文。该模型在 HealthBench Professional(65.72)、HLE(纯文本带工具 72.22)和 BrowseComp(带上下文 94.10)上均超过 GPT-6 Astra、Claude Opus 5.5 和 Gemini 4 Argon,并在 PhysicianBench(57)和 EHR-Complex(74.40)等长程医疗工作流评测中取得成绩。权重已在 Hugging Face 开放。

同一件事,精选收录的是《蚂蚁集团发布 560B 参数医疗 MoE 模型 LingSante-3.1-flash》

正文 · 原文

Ant Ling presents LingSante-3.1-flash, an opensource LLM with 25B/560B params

  • Competitive with Astra on medical / healthcare benchmarks
  • Competitive performance on non-medical tasks (e.g. HLE, BrowseComp)
  • 1M context length, MIT license

https://huggingface.co/inclusionAI/LingSante-3.1-flash

【引用 @AntLingAGI】Today, we release LingSante-3.1-flash, an open-weight MoE model with 560B total parameters and 25B activations per token. It unifies diverse medical capabilities while retaining general capabilities, including complex medical reasoning, long-horizon workflow execution, and professional behavior alignment.
LingSante-3.1-flash moves beyond medical QA toward real-world healthcare problem. The model leads on HealthBench Professional (65.72), HLE (text-only, with tools: 72.22) and BrowseComp (with context: 94.10), outperforming GPT-6 Astra, Claude Opus 5.5 and Gemini 4 Argon on all three. LingSante-3.1-flash also performs well on professional long-horizon medical workflows, such as PhysicianBench (57) and EHR-Complex (74.40).
Together, these results establish LingSante-3.1-flash as the leading open-weight models for healthcare.
The weights are available. Explore LingSante and build with it.
More below ↓

引用Ant Ling@AntLingAGI
Today, we release LingSante-3.1-flash, an open-weight MoE model with 560B total parameters and 25B activations per token. It unifies diverse medical capabilities while retaining general capabilities, including complex medical reasoning, long-horizon workflow execution, and professional behavior alignment. LingSante-3.1-flash moves beyond medical QA toward real-world healthcare problem. The model leads on HealthBench Professional (65.72), HLE (text-only, with tools: 72.22) and BrowseComp (with context: 94.10), outperforming GPT-6 Astra, Claude Opus 5.5 and Gemini 4 Argon on all three. LingSante-3.1-flash also performs well on professional long-horizon medical workflows, such as PhysicianBench (57) and EHR-Complex (74.40). Together, these results establish LingSante-3.1-flash as the leading open-weight models for healthcare. The weights are available. Explore LingSante and build with it. More below ↓
在 X 查看被引用的帖子

来源:Aran Komatsuzaki · x.com