{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T22:11:43Z","timestamp":1793657503740,"version":"4.5.1"},"reference-count":16,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T00:00:00Z","timestamp":1781222400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T00:00:00Z","timestamp":1781222400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Med"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1038\/s41591-026-04431-5","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T09:04:52Z","timestamp":1781255092000},"page":"2405-2409","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":63,"title":["General-purpose large language models outperform specialized clinical AI tools on medical benchmarks"],"prefix":"10.1038","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6894-1796","authenticated-orcid":false,"given":"Krithik","family":"Vishwanath","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anton","family":"Alyakin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2310-3411","authenticated-orcid":false,"given":"Mrigayu","family":"Ghosh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Hage","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sean N.","family":"Neifert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cordelia","family":"Orillac","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nataniel J.","family":"Mandelberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hammad A.","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8961-0125","authenticated-orcid":false,"given":"Jin Vivian","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie J.","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3105-6495","authenticated-orcid":false,"given":"William Robert","family":"Small","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aakaash","family":"Varma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"D. Brock","family":"Hewitt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8605-5392","authenticated-orcid":false,"given":"Yindalon","family":"Aphinyanaphongs","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7957-5170","authenticated-orcid":false,"given":"Daniel Alexander","family":"Alber","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1876-5963","authenticated-orcid":false,"given":"Eric Karl","family":"Oermann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,12]]},"reference":[{"key":"4431_CR1","unstructured":"OpenEvidence, the fastest-growing application for physicians in history, announces 210 million round at 3.5 billion valuation. Cision PR Newswire https:\/\/www.prnewswire.com\/news-releases\/openevidence-the-fastest-growing-application-for-physicians-in-history-announces-210-million-round-at-3-5-billion-valuation-302505806.html (2025)."},{"key":"4431_CR2","unstructured":"HLTH 2025: Wolters Kluwer showcases UpToDate Expert AI and workflow innovations. Wolterskluwer https:\/\/www.wolterskluwer.com\/en\/news\/uptodate-expert-ai-workflow-hlth-2025 (2025)."},{"key":"4431_CR3","doi-asserted-by":"publisher","first-page":"e0000877","DOI":"10.1371\/journal.pdig.0000877","volume":"4","author":"LM Amugongo","year":"2025","unstructured":"Amugongo, L. M., Mascheroni, P., Brooks, S., Doering, S. & Seidel, J. Retrieval augmented generation for large language models in healthcare: a systematic review. PLOS Digit. Health 4, e0000877 (2025).","journal-title":"PLOS Digit. Health"},{"key":"4431_CR4","doi-asserted-by":"publisher","first-page":"6421","DOI":"10.3390\/app11146421","volume":"11","author":"D Jin","year":"2021","unstructured":"Jin, D. et al. What disease does this patient have? A large-scale open domain question answering dataset from medical exams. Appl. Sci. (Basel) 11, 6421 (2021).","journal-title":"Appl. Sci. (Basel)"},{"key":"4431_CR5","doi-asserted-by":"publisher","unstructured":"Arora, R. K. et al. HealthBench: evaluating large language models towards improved human health. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2505.08775 (2025).","DOI":"10.48550\/arXiv.2505.08775"},{"key":"4431_CR6","doi-asserted-by":"publisher","unstructured":"Vishwanath, K. et al. Medical large language models are easily distracted. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2504.01201 (2025).","DOI":"10.48550\/arXiv.2504.01201"},{"key":"4431_CR7","doi-asserted-by":"publisher","first-page":"e000068","DOI":"10.1136\/bmjdhai-2025-000068","volume":"1","author":"K Vishwanath","year":"2025","unstructured":"Vishwanath, K., Stryker, J., Alyakin, A., Alber, D. A. & Oermann, E. K. MedMobile: a mobile-sized language model with clinical capabilities. BMJ Digit. Health AI 1, e000068 (2025).","journal-title":"BMJ Digit. Health AI"},{"key":"4431_CR8","doi-asserted-by":"crossref","unstructured":"Wu, E., Wu, K. & Zou, J. ClashEval: quantifying the tug-of-war between an LLM\u2019s internal prior and external evidence. In Advances in Neural Information Processing Systems 37 33402\u201333422 (Neural Information Processing Systems Foundation, 2024).","DOI":"10.52202\/079017-1053"},{"key":"4431_CR9","doi-asserted-by":"publisher","unstructured":"Alyakin, A. et al. CNS-Obsidian: a neurosurgical vision-language model built from scientific publications. Neurosurgery https:\/\/doi.org\/10.1227\/neu.0000000000004070 (2026).","DOI":"10.1227\/neu.0000000000004070"},{"key":"4431_CR10","doi-asserted-by":"publisher","first-page":"616","DOI":"10.1038\/s41591-025-04190-9","volume":"32","author":"JW O\u2019Sullivan","year":"2026","unstructured":"O\u2019Sullivan, J. W. et al. A large language model for complex cardiology care. Nat. Med. 32, 616\u2013623 (2026).","journal-title":"Nat. Med."},{"key":"4431_CR11","doi-asserted-by":"publisher","unstructured":"Nori, H. et al. Sequential diagnosis with language models. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2506.22405 (2025).","DOI":"10.48550\/arXiv.2506.22405"},{"key":"4431_CR12","doi-asserted-by":"publisher","unstructured":"Wu, D. et al. First, do NOHARM: towards clinically safe large language models. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2512.01241 (2025).","DOI":"10.48550\/arXiv.2512.01241"},{"key":"4431_CR13","doi-asserted-by":"publisher","unstructured":"Jiang, L. Y. et al. Generalist foundation models are not clinical enough for hospital operations. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2511.13703 (2025).","DOI":"10.48550\/arXiv.2511.13703"},{"key":"4431_CR14","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/s41586-023-06160-y","volume":"619","author":"LY Jiang","year":"2023","unstructured":"Jiang, L. Y. et al. Health system-scale language models are all-purpose prediction engines. Nature 619, 357\u2013362 (2023).","journal-title":"Nature"},{"key":"4431_CR15","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1038\/s41591-024-03445-1","volume":"31","author":"DA Alber","year":"2025","unstructured":"Alber, D. A. et al. Medical large language models are vulnerable to data-poisoning attacks. Nat. Med. 31, 618\u2013626 (2025).","journal-title":"Nat. Med."},{"key":"4431_CR16","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1093\/jamia\/ocae285","volume":"32","author":"K Malhotra","year":"2025","unstructured":"Malhotra, K. et al. Health system-wide access to generative artificial intelligence: the New York University Langone Health experience. J. Am. Med. Inform. Assoc. 32, 268\u2013274 (2025).","journal-title":"J. Am. Med. Inform. Assoc."}],"container-title":["Nature Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41591-026-04431-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41591-026-04431-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41591-026-04431-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T05:27:48Z","timestamp":1787894868000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41591-026-04431-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,12]]},"references-count":16,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["4431"],"URL":"https:\/\/doi.org\/10.1038\/s41591-026-04431-5","relation":{},"ISSN":["1078-8956","1546-170X"],"issn-type":[{"value":"1078-8956","type":"print"},{"value":"1546-170X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,12]]},"assertion":[{"value":"1 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"E.K.O. reports equity in MarchAI and Artisight, spousal employment by Eikon Therapeutics, and consulting for Sofinnova Partners and Google. The remaining authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}]}}