{"id":370510,"date":"2026-06-19T06:04:00","date_gmt":"2026-06-19T13:04:00","guid":{"rendered":"https:\/\/cms-articles.softonic.io\/en\/?p=370510"},"modified":"2026-06-19T06:04:11","modified_gmt":"2026-06-19T13:04:11","slug":"chatgpt-gets-a-health-upgrade-openai-says-it-beats-doctors-in-internal-tests","status":"publish","type":"post","link":"https:\/\/cms-articles.softonic.io\/en\/chatgpt-gets-a-health-upgrade-openai-says-it-beats-doctors-in-internal-tests\/","title":{"rendered":"ChatGPT gets a health upgrade: OpenAI says it beats doctors in internal tests"},"content":{"rendered":"

OpenAI just updated ChatGPT<\/a> with GPT-5.5 Instant, and the company says the new model gave healthcare answers that scored higher than doctors\u2019 answers<\/strong> in OpenAI\u2019s own tests for accuracy, clarity, and completeness.<\/p>\n

\r\n
\r\n
\r\n
\r\n \"ChatGPT\"\r\n <\/div>\r\n
\r\n ChatGPT<\/span>\r\n Download<\/a>\r\n <\/div>\r\n
\r\n <\/path><\/path><\/text><\/svg>\r\n <\/div>\r\n <\/div>\r\n
\r\n <\/span>\r\n <\/div>\r\n
\r\n \r\n <\/div>\r\n <\/a>\r\n <\/div>\r\n<\/div>\n\n\n\n

OpenAI also says the error rate in medical statements has fallen by 71%<\/strong> over the past two months. It says GPT-5.5 Instant is better at picking up on cases where you may need urgent care, asking for missing context, and admitting uncertainty instead of sounding more confident than it should.<\/p>\n\n

That matters if the scale is anywhere near what OpenAI reports: 230 million<\/strong> people use ChatGPT every week for health-related questions. In a small independent check using 18 medical prompts, GPT-5.5 Instant produced 54.5% fewer hallucinated claims than GPT-5.3 Instant.<\/p>\n\n

OpenAI says those results fit a broader review process in which more than 260 physicians<\/strong> from 60 countries evaluated over 700,000 responses.<\/p>\n\n

If you use ChatGPT for health questions, this is an update you\u2019ll probably want to look at. Still, be careful. Internal benchmarks can make OpenAI\u2019s model look stronger than it really is, and fewer hallucinations don\u2019t erase the risk of dangerous mistakes. Under-triage<\/strong>, delayed visits to a clinician, privacy issues, and bias are all still real concerns.<\/p>\n\n

You can use GPT-5.5 Instant in ChatGPT now, but OpenAI is still presenting it as a tool to help you make sense of symptoms, questions, or treatment options before talking to a qualified medical professional, not as a replacement for medical care<\/strong>.<\/p>","protected":false},"excerpt":{"rendered":"

OpenAI just updated ChatGPT with GPT-5.5 Instant, and the company says the new model gave healthcare answers that scored higher than doctors\u2019 answers in OpenAI\u2019s own tests for accuracy, clarity, and completeness. OpenAI also says the error rate in medical statements has fallen by 71% over the past two months. It says GPT-5.5 Instant is … Continue reading “ChatGPT gets a health upgrade: OpenAI says it beats doctors in internal tests”<\/span><\/a><\/p>\n","protected":false},"author":9330,"featured_media":370509,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","wpcf-pageviews":0},"categories":[1015],"tags":[],"usertag":[],"vertical":[],"content-category":[6771],"class_list":["post-370510","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news","content-category-ai"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/posts\/370510","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/users\/9330"}],"replies":[{"embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/comments?post=370510"}],"version-history":[{"count":1,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/posts\/370510\/revisions"}],"predecessor-version":[{"id":370511,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/posts\/370510\/revisions\/370511"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/media\/370509"}],"wp:attachment":[{"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/media?parent=370510"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/categories?post=370510"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/tags?post=370510"},{"taxonomy":"usertag","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/usertag?post=370510"},{"taxonomy":"vertical","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/vertical?post=370510"},{"taxonomy":"content-category","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/content-category?post=370510"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}