Ant Group releases open medical reasoning model Ling-3.0-flash-Sante (124B MoE, MIT)
AdinaYakup · x · 2026-10-23
Ant Group keeps shipping: it released weights for Ling-3.0-flash-Sante, a new open medical reasoning model.
- Architecture: 124B total / 5.1B active MoE, 256K context, MIT license.
- Capabilities: agentic deep research and tool use.
- Benchmarks: official charts show comparisons against DeepSeek-V4-Flash, GLM-5.3-Flash, MiniMax-M2.7, Kimi 4.5 and Gemini 2.6 Flash across HealthBench Professional, MedXpertQA, MedQA-USMLE, AFUMED, BrowseComp, DeepSearchQA, HLE (w/ tools), GDPval, Tau3-Banking, MCP Atlas and AA-LCR, leading or matching on several medical benchmarks.
(Benchmark figures are from the official release; no third-party replication yet.)
Related event: Ant Group Open-Sources Medical MoE Model Ling-3.0-flash-Sante(5 posts)→
More from Models
- Artificial Analysis launches AA-PersonalityBench model personality benchmark — ArtificialAnlys · 2026-10-23
- AA-PersonalityBench: pairwise LLM judges score 30 personality traits across 40 models — ArtificialAnlys · 2026-10-23
- OpenAI's Dot UX: Speech Is Linear, Real Value Is Multithreaded — cocktailpeanut · 2026-10-23
- Interpolation and hallucination: why sampling outside training data yields AI slop — gerardsans · 2026-10-23
- Sam Altman: models now find bugs outside any hacker threat model, 'we can't just patch them all' — ns123abc · 2026-10-23
- Omnii Genome: single generalist model beats AlphaGenome at linking variants to gene activity — BenSiranosian · 2026-10-23