Microsoft’s Mustafa Suleyman says its AI outperforms doctors on hard cases as he chases ‘medical superintelligence’

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.

Microsoft’s Mustafa Suleyman says its AI outperforms doctors on hard cases as he chases ‘medical superintelligence’

TL;DR

  • Microsoft's AI diagnostic system, MAI-DxO, correctly diagnosed complex medical cases in simulations 83% of the time, compared to 36% for generalist physicians.
  • The study indicates that the performance gains are primarily driven by advanced AI models such as OpenAI's GPT-5 and GPT-5.5, with MAI-DxO offering supplementary improvements.
  • Microsoft is partnering with Mayo Clinic to develop a healthcare foundation model and with Beth Israel Deaconess Medical Center to evaluate MAI-DxO in real-world clinical settings.
  • Mustafa Suleyman, CEO of Microsoft AI, aims for 'medical superintelligence,' believing AI capabilities in healthcare will improve significantly in the coming years.
  • The MAI-DxO system coordinates multiple AI agents to question patients, order tests, and debate diagnoses, showing particular benefits in complex cases rather than emergency department scenarios.