Scientists tested a

nature medicine Search Log in Content About Publish brief communications article Brief Communication Open access Published: 12 June 2026 General-purpose large language models outperform specialized clinical AI tools on medical benchmarks Krithik Vishwanath Anton Alyakin Eric Karl Oermann Show authors Nature Medicine (2026) Cite this article 103k Accesses 158 Altmetric Metrics TECH OpenEvidence, the 'ChatGPT for doctors,' doubles valuation to $12 billion UPDATED WED, JAN 21 2026-7:30 AM EST Kate Rooney @KROONEY WATCH LIVE KEY POINTS OpenEvidence raised money at a valuation of $12 billion in a round led by Thrive and DST. The startup is widely known as "ChatGPT for doctors" and has seen meteoric Wolters Kluwer UpToDate Expert AI Clearly sourced, evidence-backed GenAI built for clinical care. AI Assist what can I do for you today? Exactly GPT-5.2 Gemini 3.1 Pro Preview Claude Opus 4.6 OpenEvidence UpToDate Expert AI Google AI Overview $1.75/$14.00 per 1M input/out $2.00/$12.00 per 1M input/out $5.00/$25.00 per 1M input/out Free for verified U.S. clinicians -$699/year (UpToDate Pro Plus Free (integrated into Google S Specialized clinical artificial intelligence (AI) tools are entering medical practice despite scarce independent evaluation. We quantitatively evaluate two clinical AI tools, OpenEvidence and UpToDate Expert AI, built on large language models (LLMs) against three frontier LLMs: GPT-5.2, Gemini 3.1 Pro and Claude Opus 4.6. Our evaluation has three stages: (1) 500 MedQA questions testing medical knowledge, (2) 500 HealthBench items measuring alignment with clinicians and (3) the real clinical queries (RCQ) benchmark, built from 100 de-identified queries from physicians to a general-purpose language model in a live clinical environment. For the RCQ benchmark, 12 US clinicians performed randomized, blinded review of model outputs, producing 1,800 model-question annotations. Frontier LLMs outperformed clinical AI tools in all three evaluations. Clinical AI tools performed comparably to auto-enabled Google Search AI Comparison of Normal Knee and Osteoarthritic Knees. N Engl J Med. January 6, 2020. N Engl J Knees. Used under license from The New England Journal of Medicine. like me to summarize the current used approaches for diagnosing arthritis, including the roles of clinical assessment and imaging modalities? Helpful Copy Text