Today, we’re introducing Ling-3.0-flash-Sante — an MoE model enhanced for…
- Source
- Ant Ling
- Date
Today, we’re introducing Ling-3.0-flash-Sante — an MoE model enhanced for health and medicine, built on Ling-3.0-flash. Inspired by the French word “santé,” meaning “health,” Sante is built for real-world healthcare tasks spanning medical reasoning, professional healthcare tasks, deep research, and evidence-based retrieval. Sante shows competitive results across MedXpertQA-Text, DiagnosisArena-MCQ, AFUMED-Drug, HealthBench Professional, and BrowseComp, with leading performance among open-source models and results competitive with flagship models. Here’s to better health — Santé! More below ↓
Context
Ant Ling builds the Ling family of models. Ling-3.0-flash-Sante is a version of its Ling-3.0-flash model additionally tuned for healthcare tasks such as medical reasoning, professional clinical questions, and evidence-based literature retrieval, following the same team's release of a finance-tuned Ling-3.0-flash-Fin model a day earlier as part of a pattern of building domain-specific versions of its flash model.
The announcement says Sante leads open-source models and performs competitively with flagship closed models across five named benchmarks: MedXpertQA-Text, DiagnosisArena-MCQ, AFUMED-Drug, HealthBench Professional and BrowseComp. No specific scores accompany that claim in this post, so the comparison should be read as the lab's own summary rather than an independently reported result.
- mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
Checking sign-in…
Loading comments…