# Ant open-sources LingSante-3.1-flash, a medical MoE model with 560B total and 25B active parameters and a 1M context



Ant Group



Ant's Ling team has open-sourced LingSante-3.1-flash, a medical model built on Ling-3.1-flash's hybrid-linear MoE architecture, with 560B total parameters, 25B active per token and a 1M-token context window. It combines complex medical reasoning, long-horizon medical workflows, tool use, evidence retrieval and interactive consultation while keeping general skills. Ant says it leads the HBP medical-behavior benchmark \(65.72\) and trails only GPT-6 Astra on the three-benchmark medical-behavior average, and that contribution-aware multi-agent search training improves accuracy while cutting total search steps by over 20%. Weights are on Hugging Face and ModelScope under the MIT license, in the original FP8 version and an MXFP4 quantized version; SGLang is the recommended way to serve it, and vLLM is also supported. Ant says the model is for research and evaluation only, is not a medical device and must not be used as an independent basis for diagnosis, prescriptions or treatment.


## Availability

Open weights under the MIT license on Hugging Face and ModelScope, in the original FP8 and an MXFP4 quantized version; also available via API on Computrix.
- Launched: Nov 22, 2026 23:22 · Beijing Time (UTC+8)

## Sources

- Source excerpt: https://x.com/AntLingAGI/status/2124523916819648945
- Source excerpt: https://x.com/AntLingAGI/status/2124523946360053771

Canonical entry: https://www.ailyre.com/source/?id=ant-group-inclusionai-lingsante-3-1-flash&lang=en
