Cohort Studymoderate evidence

Performance of a large language model on the reasoning tasks of a physician.

Science (New York, N.Y.)·April 30, 2026·PMID 42060751

Why it matters

LLMs may soon augment or outperform physicians in diagnostic reasoning, potentially improving accuracy and efficiency in high-stakes settings like the emergency department. Specialists should be aware of this rapidly evolving capability.

Infographic summary of Performance of a large language model on the reasoning tasks of a physician.
Visual abstract · MedLit

The papers that matter, first.

MedLit ranks the medical literature into a specialty feed with concise summaries, evidence-aware triage, and visual takeaways.

§

MedLit · Evidence, Distilled