Microsoft says MAI-DxO beat generalist doctors on hard cases
Original title: Microsoft’s Mustafa Suleyman says its AI outperforms doctors on hard cases as he chases ‘medical superintelligence’
In a simulation of complex NEJM cases, MAI-DxO was correct 83% of the time versus 36% for generalists.
Microsoft AI’s MAI-DxO coordinates several agents and, in a Science study, correctly diagnosed complex New England Journal of Medicine cases 83% of the time versus 36% for primary care doctors and general internists working alone with references. Specialists were not in that comparison. The best results used OpenAI’s GPT-5 and GPT-5.5, with DxO adding smaller gains on stronger models. Mustafa Suleyman said Microsoft is training a healthcare foundation model with Mayo Clinic for next year and will evaluate DxO with Beth Israel Deaconess Medical Center.
Unconfirmed: The physician comparison excluded specialists, and Suleyman’s claims about 2027 capability are forward-looking.
- GPT-5 alone scored 78.9% on complex cases 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 complex-case accuracy from 72% to nearly 87%.
- Gemini 2.5 Flash rose from 46.4% alone to nearly 69% with DxO.
- Emergency department cases showed little DxO gain over GPT-5 or GPT-5.5.
- Vendors
- Microsoft
- AI models
- MAI-DxOGPT-5GPT-5.5Gemini 2.5 Flash
From the original article
5 min read at techcrunch.com
Microsoft’s new AI diagnostic system beat generalist doctors on hard cases, according to a study in Science. But most of the improvement seems to come from the AI models underneath, not from Microsoft’s system itself.
By Rebecca Bellan · techcrunch.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.