Skip to content
NewA calmer, faster ZeroHour
StoryAI industryinfo

Microsoft's MAI-DxO beats generalists on complex NEJM cases

2 sources · 2 articlesFirst reported Updated ()
What's new

First merged summary.

Merged summary · x-ai/grok-4.7 · rewritten as coverage arrivesSummaries by Vani AI

Microsoft's MAI-DxO scored 83% on complex NEJM cases versus 36% for generalist physicians in a Science study.

Microsoft unveiled MAI-DxO, also called Diagnostic Orchestrator, which uses multiple agents to gather history, order tests, and reach diagnoses. In a Science study of complex New England Journal of Medicine cases, it was correct 83% of the time versus 36% for primary care doctors and general internists working alone with references; The Verge also reports 22% without references, and TechCrunch says specialists were not compared. The strongest runs used OpenAI's GPT-5 and GPT-5.5, with smaller DxO gains on stronger models. The Verge reports 80% versus 47% for doctors on Beth Israel Deaconess emergency data and lower estimated costs, while TechCrunch says emergency cases showed little DxO gain over GPT-5 or GPT-5.5. Mustafa Suleyman said Microsoft is training a healthcare foundation model with Mayo Clinic for next year and will evaluate DxO with Beth Israel Deaconess.

Key facts
  • MAI-DxO scored 83% on complex NEJM cases versus 36% for referenced generalists.
  • TechCrunch says specialists were not included in that physician comparison.
  • GPT-5 alone scored 78.9% at about $8,400 per case.
  • DxO cut that cost by about $3,000 and raised accuracy by about four points.
  • With GPT-5.5, DxO lifted accuracy from 72% to nearly 87%.
  • Gemini 2.5 Flash rose from 46.4% alone to nearly 69% with DxO.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

What each outlet adds

beyond the shared facts
  • The VergeReports 22% without references, ED 80% versus 47%, and an SDBench open-source plan.
  • TechCrunchAdds model costs, GPT-5.5 and Gemini gains, and the Mayo Clinic plan.
Vendors
Microsoft
Products
Diagnostic Orchestrator
Organizations
Beth Israel Deaconess Medical CenterMayo ClinicOpenAI
AI models
MAI-DxOGPT-5GPT-5.5Gemini 2.5 Flash

Coverage

oldest first · one row per article · UTC
  1. · 3d ago The Verge · AIFirst report

    Microsoft AI tool outperforms doctors in medical diagnosis

    Diagnostic Orchestrator AI achieves 83% accuracy on case reports versus 36% for physicians, using multiple reasoning agents.

  2. · 3d ago TechCrunch · AI

    Microsoft says MAI-DxO beat generalist doctors on hard cases

    In a simulation of complex NEJM cases, MAI-DxO was correct 83% of the time versus 36% for generalists.