Open-weight medical MoE LingSante-3.1-flash: 560B params, claims wins over GPT-6 and Claude

DrDatta_AIIMS · x · 2026-11-22

Ant Ling released LingSante-3.1-flash, an open-weight MoE model with 560B total parameters and 25B active per token, unifying complex medical reasoning, long-horizon workflow execution, and professional behavior alignment while keeping general capabilities.

The team claims top scores 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, plus strong performance on PhysicianBench-style long-horizon clinical workflows. Physician DrDattaAIIMS called it potentially an insane jump in medical capabilities if reproduced and plans to benchmark it on his own medical reasoning eval, asking when radiology gets covered.

Original post →

More from Models

Models channel →