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.
More from Models
- Sakana AI announces its own pretrained LLM series Sakana Sawara, first model due spring 2027 — SakanaAILabs · 2026-11-22
- Sakana AI announces Sakana Sawara, a from-scratch LLM series built at its RSI Lab — SakanaAILabs · 2026-11-22
- HF's harness adapters lift Qwen3.8-27B from 39% to 55% on Terminal-Bench 2.1 with half the tokens — SergioPaniego · 2026-11-22
- KOL: a month on, none of China's four flagship models comes close to US frontier — kimmonismus · 2026-11-22
- The Information: Kimi K3.1 Pro and DeepSeek V4.1-Flash both distilled from GPT-6 Astra — kimmonismus · 2026-11-22
- OpenAI and Anthropic week 47: GPT-6.2 Astra/Sol launch, Anthropic's Nasdaq debut, watermarking — btibor91 · 2026-11-22