[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-new-healthcare-ai-benchmark-finds-frontier-agents-fail-most-tasks":10,"sections":44},{"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":34,"tags":35,"sources":39,"feedback":43,"feedback_at":22,"cost_usd":43,"total_tokens":43},3024,"new-healthcare-ai-benchmark-finds-frontier-agents-fail-most-tasks","New Healthcare AI Benchmark Finds Frontier Agents Fail Most Tasks","HealthAgentBench, a 54-task suite spanning clinical workflows, shows even the top-performing AI agent clears fewer than half the challenges.","A new benchmark for healthcare AI agents sets a high bar — and current models clear less than half of it.\n\nResearchers introduced HealthAgentBench, a suite of 54 tasks across seven clinical workflow categories, each with its own environment. The benchmark is designed to replicate end-to-end clinical work: agents receive minimal instructions, then must navigate raw healthcare data and execute multi-step solutions. Task categories span diverse modalities along the patient journey, and performance is reported as a single task success rate. The benchmark code is available on GitHub under Microsoft's account.\n\nThe results expose how far AI agents remain from practical clinical deployment. The top-performing agent achieved only around a 42% success rate — meaning it failed on more than half the tasks. Medical imaging proved especially difficult across models, while tasks combining large search spaces with compositional reasoning defeated every agent tested.\n\nHealthAgentBench joins a growing pile of benchmarks designed to pressure-test AI in high-stakes domains. The difference here is the clinical specificity: rather than knowledge quizzes, these are workflow simulations — closer to what a deployed agent would actually face. A 42% ceiling on the best available model is a meaningful data point for anyone weighing near-term clinical AI deployment, and a useful corrective to vendor claims that frontier models are ready for healthcare.","[\"ai\",\"healthcare\",\"benchmarks\",\"agents\"]","2026-07-01T04:00:00.000Z","2026-07-01T05:28:08.068Z","2026-07-01T05:28:10.924Z","published",null,[24,30],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"The model identifier 'Codex GPT-5.5' cannot be verified against publicly confirmed releases — confirm this name is accurate before publication, per standing policy on unverified model version identifiers.","resolved",{"id":31,"reviewer":26,"round":32,"reason":33,"status":29},"editor-r2",2,"The model identifier 'Codex GPT-5.5' is still flagged in the body as 'not independently confirmed at time of publication' — this unresolved editorial hedge must be removed before publication; either confirm the name against a publicly verified release or strip the identifier entirely per standing policy.","ai",[34,36,37,38],"healthcare","benchmarks","agents",[40],{"name":41,"url":42},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.31179",0,{"sections":45},[46,50,55,60,65,70,75,80,85,90,95,99,104,109],{"name":47,"slug":34,"count":48,"latest_published_at":49},"AI",2590,"2026-07-16T04:00:00.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Security","security",294,"2026-07-15T19:59:48.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":64},"Policy","policy",158,"2026-07-16T00:02:48.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Hardware","hardware",122,"2026-07-14T19:46:26.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Consumer Tech","consumer-tech",93,"2026-07-13T13:20:48.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":79},"Software","software",70,"2026-07-13T19:52:25.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":84},"Science","science",66,"2026-07-10T10:29:37.000Z",{"name":86,"slug":87,"count":88,"latest_published_at":89},"Dev Tools","dev-tools",59,"2026-07-07T04:00:00.000Z",{"name":91,"slug":92,"count":93,"latest_published_at":94},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":96,"slug":97,"count":93,"latest_published_at":98},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":100,"slug":101,"count":102,"latest_published_at":103},"General","general",29,"2026-07-10T22:28:58.000Z",{"name":105,"slug":106,"count":107,"latest_published_at":108},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":110,"slug":111,"count":112,"latest_published_at":113},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]