Microsoft's MAI-DxO beats generalist doctors 83.2% vs 36.1% on complex diagnosis, Science study finds
emmanuelvivier · x · 2026-10-31
A peer-reviewed Science study shows Microsoft's MAI Diagnostic Orchestrator (MAI-DxO), running on OpenAI's GPT-5, correctly diagnosed 83.2% of 304 complex NEJM cases versus 36.1% for generalist physicians with textbook/internet access. It also scored 80.3% vs 46.8% on 325 ER admissions, works by step-by-step clinical reasoning like an expert panel, and reportedly costs less per diagnostic work-up.
More from Models
- OpenAI reportedly to train on users' private sessions with no opt-out — evilsocket · 2026-10-31
- Heavy users burn $700 of compute on a $20 ChatGPT plan: subscription pricing is a bet — faraz0x · 2026-10-31
- High schooler's "Image-Space Rule Discovery" paper accepted to ACCV 2026 — HirokatuKataoka · 2026-10-31
- 19 LLMs play 376 games of Codenames-style word game; Gemini 3.8 Flash guesses 93% right — Hardicecream17 · 2026-10-31
- LLMs are fluent in others' work but unreliable when pressed on details — AlexTensor · 2026-10-31
- 576GB 'go f*ck yourself Sam Altman' mirror spreads as OpenAI docs leak — retr0jirachi · 2026-10-31