Checked fact 244723 Oct 2026Research

Microsoft says the gains persisted when the evaluation was repeated with newer models including GPT-5.5, with the orchestration method unchanged.

the company says This is the company's own statement about itself, not something we found out ourselves.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

repeated the evaluation with newer models, including GPT-5.5, without changing the orchestration method

What the source said when we opened it, on 23 Oct 2026.

The source

Building Medical Superintelligence
Microsoft AI · 2026-10-22

Open the source archived copy

Checked

Checked by the notis newsroom on 23 Oct 2026, against the source above.

In the story

Microsoft says MAI-DxO reached 83% accuracy on 304 NEJM cases, against 36% for physicians with resources. 23 Oct 2026

Cite this fact

Short permanent address

In a sentence

The company says: “Microsoft says the gains persisted when the evaluation was repeated with newer models including GPT-5.5, with the orchestration method unchanged.” ai notis, checked 23 Oct 2026. Source: Building Medical Superintelligence (Microsoft AI). https://ainotis.com/c/2447

As a reference (APA style)

ai notis. (2026, October 23). The company says: Microsoft says the gains persisted when the evaluation was repeated with newer models including GPT-5.5, with the orchestration method unchanged [Checked claim 2447]. ai notis. https://ainotis.com/c/2447

Anyone may quote this address. It does not change; if we correct the story, this page says so.