[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-ai-still-trails-doctors-by-37-points-on-psychiatric-evals":10,"sections":34},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":24,"tags":25,"sources":29,"feedback":33,"feedback_at":22,"cost_usd":33,"total_tokens":33},4556,"ai-still-trails-doctors-by-37-points-on-psychiatric-evals","AI Still Trails Doctors by 37 Points on Psychiatric Evals","A new benchmark simulating full clinical psychiatric encounters finds even the best LLMs fall well short of human clinician performance.","A research team has built a virtual psychiatric ward to find out how badly AI fails at real clinical work — and the answer is: considerably.\n\nThe benchmark, called MentalHospital, runs AI models through complete psychiatric encounters rather than isolated tasks like writing a diagnosis or drafting a treatment note. It draws on 1,193 de-identified patient records covering 76 disorders across all major ICD-11 categories, and structures each encounter around the standard clinical S.O.A.P. workflow — Subjective Interviewing, Objective Examination, Diagnostic Assessment, and Treatment Planning. To score results without bottlenecking on scarce human reviewers, the researchers also built MentalEval, a set of five AI evaluators trained to assess communication empathy, professionalism, note quality, diagnostic rigor, and treatment appropriateness. Those evaluators achieved a 0.944 weighted kappa score against expert raters — strong agreement.\n\nThe gap between AI and clinicians is the headline number: the best-performing model trailed human doctors by 37.28 percentage points on objective psychiatric competence. Mental status assessment — reading a patient's current psychological state in real time — emerged as the single biggest bottleneck. That matters because it is precisely the skill that resists rote pattern-matching; it requires reading affect, coherence, and context together.\n\nMost AI psychiatric benchmarks test piece parts: can the model name the right diagnosis, or generate a plausible note? MentalHospital tests the full encounter, which is harder and more honest. Twenty-two clinicians rated the environment's fidelity at 3.88 out of 5 — decent, not glowing. Whether that ceiling on simulated fidelity limits the benchmark's real-world conclusions is a question the paper does not fully resolve.","[\"ai\",\"mental health\",\"benchmarks\",\"research\"]","2026-07-10T04:00:00.000Z","2026-07-10T04:42:40.777Z","2026-07-10T04:42:43.987Z","published",null,[],"ai",[24,26,27,28],"mental health","benchmarks","research",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.08257",0,{"sections":35},[36,40,45,50,55,60,65,70,75,80,85,89,94,99],{"name":37,"slug":24,"count":38,"latest_published_at":39},"AI",2590,"2026-07-16T04:00:00.000Z",{"name":41,"slug":42,"count":43,"latest_published_at":44},"Security","security",294,"2026-07-15T19:59:48.000Z",{"name":46,"slug":47,"count":48,"latest_published_at":49},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Policy","policy",158,"2026-07-16T00:02:48.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Hardware","hardware",122,"2026-07-14T19:46:26.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":64},"Consumer Tech","consumer-tech",93,"2026-07-13T13:20:48.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Software","software",70,"2026-07-13T19:52:25.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Science","science",66,"2026-07-10T10:29:37.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":79},"Dev Tools","dev-tools",59,"2026-07-07T04:00:00.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":84},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":86,"slug":87,"count":83,"latest_published_at":88},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":90,"slug":91,"count":92,"latest_published_at":93},"General","general",29,"2026-07-10T22:28:58.000Z",{"name":95,"slug":96,"count":97,"latest_published_at":98},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":100,"slug":101,"count":102,"latest_published_at":103},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]