[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fWUQMZNt0b5ltwaFJsiwAJK3-emCPWLzqbfHxAWbyDBc":3},{"locale":4,"topic":5,"relatedTrends":54},"en",{"topic":6,"slug":7,"canonicalSlug":8,"topicAliases":9,"nicheKey":11,"nicheName":12,"nicheNameEn":12,"nicheIcon":13,"country":14,"countries":15,"agentKey":16,"score":17,"type":18,"isFresh":19,"isPublic":20,"detectedAt":21,"sources":22,"evidence":50},"General-purpose LLMs outperform specialized clinical AI tools on benchmarks","general-purpose-llms-outperforming-specialized-clinical-ai-tools-on-medical-benchmarks","general-purpose-llms-outperform-specialized-clinical-ai-tools-on-benchmarks",[10],"General-purpose LLMs outperforming specialized clinical AI tools on medical benchmarks","ai-engineering","AI Engineering & LLM Ops","⚙️","TR",[14],"ai-engineering-TR",96,"spiking",true,false,"2026-06-14T00:21:59.178Z",[23,29,35,40,45],{"title":24,"url":25,"domain":26,"snippet":27,"content":28},"General-purpose large language models outperform specialized clinical AI tools on medical benchmarks","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41591-026-04431-5","nature.com","A quantitative evaluation finds general-purpose large language models outperform specialized clinical AI tools on medical benchmarks.","We use essential cookies to make sure the site can function. We also use optional cookies for advertising, personalisation of content, usage analysis, and social media, as well as to allow video information to be shared for both marketing, analytics and editorial purposes.\n\nBy accepting optional cookies, you consent to the processing of your personal data - including transfers to third parties. Some third parties are outside of the European Economic Area, with varying standards of data protection.\n\nSee our  for more information on the use of your personal data.\n\nManage preferences for further information and to change your choices.\n\nAccept all cookies Reject optional cookies\n\nThank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.\n\nAdvertisement\n\n General-purpose large language models outperform specialized clinical AI tools on medical benchmarks \n\nSpecialized 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) ",{"title":30,"url":31,"domain":32,"snippet":33,"content":34},"Nature Medicine study finds general-purpose LLMs outperform dedicated medical AI tools","https:\u002F\u002Fcryptobriefing.com\u002Fgeneral-purpose-llms-outperform-medical-ai\u002F","cryptobriefing.com","A Nature Medicine study shows GPT-5.2, Gemini 3.1, and Claude Opus 4.6 outperform specialized medical AI tools on clinical benchmarks and clinician.",null,{"title":36,"url":37,"domain":38,"snippet":39,"content":34},"Medical AI Just Lost to a General Model","https:\u002F\u002Fwww.psychologytoday.com\u002Fnz\u002Fblog\u002Fthe-digital-self\u002F202606\u002Fmedical-ai-just-lost-to-a-general-model","psychologytoday.com","General models now rival—or outperform—specialized healthcare tools, says a new study.",{"title":41,"url":42,"domain":43,"snippet":44,"content":34},"Doktorların Yeni Yapay Zeka Sırdaşı","https:\u002F\u002Fwww.winally.com\u002Fdoktorlarin-yeni-yapay-zeka-sirdasi\u002F","winally.com","Amerika'da ona iki doktordan biri artık klinik karar alarak yapay zekâya başvuruyor. Bu tablo, tıp dünyasında sessiz ama temel bir uygulamanın işareti.",{"title":46,"url":47,"domain":48,"snippet":49,"content":34},"Vivek Subbiah: General-Purpose Frontier LLMs Outperform Specialized Clinical AI Tools","https:\u002F\u002Foncodaily.com\u002Fvoices\u002Fvivek-subbiah-521000","oncodaily.com","Vivek Subbiah: General-Purpose Frontier LLMs Outperform Specialized Clinical AI Tools \u002F Aakaash Varma, Ali Hage, Anton Alyakin, cancer, Cordelia Orillac, D.",{"mentionsLast7Days":51,"mentionsLast30Days":51,"firstSeen":21,"lastSeen":52,"relatedEntities":53},2,"2026-06-15T08:19:46.912Z",[25,42,47,31,37],[55,59,62,65,68,71],{"topic":56,"slug":57,"score":58,"type":18,"country":14,"nicheIcon":13},"Lumai Iris optical inference server for real-time LLMs","lumai-iris-optical-inference-server-for-real-time-llms",100,{"topic":60,"slug":61,"score":58,"type":18,"country":14,"nicheIcon":13},"Generative AI agents producing 600,000 lines of code","generative-ai-agents-producing-600-000-lines-of-code",{"topic":63,"slug":64,"score":58,"type":18,"country":14,"nicheIcon":13},"Comparison of top AI coding agents and developer platforms 2026","comparison-of-top-ai-coding-agents-and-developer-platforms-2026",{"topic":66,"slug":67,"score":58,"type":18,"country":14,"nicheIcon":13},"Comparison of AI coding agents and development platforms in 2026","comparison-of-ai-coding-agents-and-development-platforms-in-2026",{"topic":69,"slug":70,"score":58,"type":18,"country":14,"nicheIcon":13},"2026 comparison of AI coding agents and development platforms","2026-comparison-of-ai-coding-agents-and-development-platforms",{"topic":72,"slug":73,"score":58,"type":18,"country":14,"nicheIcon":13},"Top AI engineering intelligence platforms for measuring engineering outcomes","top-ai-engineering-intelligence-platforms-for-measuring-engineering-outcomes"]