{"id":6679,"date":"2025-09-28T07:49:00","date_gmt":"2025-09-28T05:49:00","guid":{"rendered":"https:\/\/viva.racunalniske-novice.com\/openai-pokazal-kje-umetna-inteligenca-ze-prehiteva-cloveske-strokovnjake\/"},"modified":"2025-09-28T07:49:00","modified_gmt":"2025-09-28T05:49:00","slug":"openai-pokazal-kje-umetna-inteligenca-ze-prehiteva-cloveske-strokovnjake","status":"publish","type":"post","link":"https:\/\/viva.racunalniske-novice.com\/en\/openai-showed-where-artificial-intelligence-is-already-outperforming-human-experts\/","title":{"rendered":"OpenAI shows where artificial intelligence is already outperforming human experts"},"content":{"rendered":"<h2 class=\"wp-block-heading\">What is GDPval?<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">GDPval is based on nine industries that contribute the most to U.S. GDP, including healthcare, finance, manufacturing, and public administration. Within these areas, the test covered 44 occupations, from programmers to nurses to journalists. The first version, GDPval-v0, works by having experienced experts compare AI reports with human reports and select the better ones.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Testing results<\/h2>\n\n\n\n<ul class=\"wp-block-list\"><li>GPT-5-high (an upgraded version of GPT-5) was rated as better or equivalent to industry experts in 40.6 % cases.<\/li><li>Claude Opus 4.1 (Anthropic) was rated better or equal in 49 % cases. OpenAI attributes this to the model&#039;s ability to create engaging graphics, not necessarily its content.<\/li><li>For comparison: GPT-4o, released about 15 months ago, only achieved 13.7 %.<\/li><\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">Testing limitations<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">OpenAI acknowledges that the current version of GDPval only covers a limited set of tasks\u2014primarily research report writing. Most professions involve much more than just report writing. That\u2019s why they plan to make future versions more robust, with more industries and interactive workflows.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Importance for the future of work<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Despite the limitations, progress is evident. Dr. Aaron Chatterji, chief economist at OpenAI, believes that AI models can now offload some tasks and focus on higher-value tasks. Tejal Patwardhan of OpenAI adds that the progress over the past 15 months is encouraging and that he expects further growth in capabilities.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Silicon Valley already has a series of tests (e.g. AIME 2025 for math problems and GPQA Diamond for PhD-level science questions). But many models are already near the upper limit on these tests. GDPval could therefore become an important tool for measuring the actual utility of AI in the economy. For now, OpenAI will need to produce even larger versions before it can confidently claim that AI truly outperforms human experts.<\/p>","protected":false},"excerpt":{"rendered":"<p>Kaj je GDPval? GDPval temelji na devetih panogah, ki najve\u010d prispevajo k ameri\u0161kemu BDP-ju, med njimi zdravstvo, finance, proizvodnja in javna uprava. Znotraj teh podro\u010dij je test zajel 44 poklicev, od programerjev do medicinskih sester in novinarjev. Prva razli\u010dica, GDPval-v0, deluje tako, da izku\u0161eni strokovnjaki primerjajo UI poro\u010dila s poro\u010dili ljudi in izberejo bolj\u0161e. Rezultati [&hellip;]<\/p>","protected":false},"author":2,"featured_media":0,"comment_status":"","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[4],"tags":[192],"class_list":["post-6679","post","type-post","status-publish","format-standard","hentry","category-racunalnistvo-telefonija","tag-umetna-inteligenca"],"acf":{"subtitle":"OpenAI je razkril nov merilnik uspe\u0161nosti UI modelov, imenovan GDPval. S tem meri, kako dobro se njihovi modeli umetne inteligence odre\u017eejo v primerjavi s \u010dlove\u0161kimi strokovnjaki v razli\u010dnih panogah.","heading":"","summary":"OpenAI je razkril nov merilnik uspe\u0161nosti UI modelov, imenovan GDPval. S tem meri, kako dobro se njihovi modeli umetne inteligence odre\u017eejo v primerjavi s \u010dlove\u0161kimi strokovnjaki v razli\u010dnih panogah.","thumbnail_small":"https:\/\/racunalniske-novice.com\/wp-content\/uploads\/2023\/11\/mojahid-mottakin-xS83vCmnWog-unsplash-560x315.jpg","thumbnail_large":"https:\/\/racunalniske-novice.com\/wp-content\/uploads\/2023\/11\/mojahid-mottakin-xS83vCmnWog-unsplash-1024x683.jpg","thumbnail_caption":"","gallery":"","video_gallery":null,"author":"","links":null,"sources":[{"title":"Tech Crunch","url":"https:\/\/techcrunch.com\/2025\/09\/25\/openai-says-gpt-5-stacks-up-to-humans-in-a-wide-range-of-jobs\/?utm_campaign=daily_linkedin"}],"skip_language":[]},"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v22.8 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>OpenAI pokazal, kje umetna inteligenca \u017ee prehiteva \u010dlove\u0161ke strokovnjake - Ra\u010dunalni\u0161ke novice<\/title>\n<meta name=\"description\" content=\"OpenAI je razkril nov merilnik uspe\u0161nosti UI modelov, imenovan GDPval. S tem meri, kako dobro se njihovi modeli umetne inteligence odre\u017eejo v primerjavi s \u010dlove\u0161kimi strokovnjaki v razli\u010dnih panogah.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/viva.racunalniske-novice.com\/en\/wp-json\/wp\/v2\/posts\/6679\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"OpenAI pokazal, kje umetna inteligenca \u017ee prehiteva \u010dlove\u0161ke strokovnjake - Ra\u010dunalni\u0161ke novice\" \/>\n<meta property=\"og:description\" content=\"Kaj je GDPval? GDPval temelji na devetih panogah, ki najve\u010d prispevajo k ameri\u0161kemu BDP-ju, med njimi zdravstvo, finance, proizvodnja in javna uprava. Znotraj teh podro\u010dij je test zajel 44 poklicev, od programerjev do medicinskih sester in novinarjev. Prva razli\u010dica, GDPval-v0, deluje tako, da izku\u0161eni strokovnjaki primerjajo UI poro\u010dila s poro\u010dili ljudi in izberejo bolj\u0161e. Rezultati [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/viva.racunalniske-novice.com\/en\/openai-showed-where-artificial-intelligence-is-already-outperforming-human-experts\/\" \/>\n<meta property=\"og:site_name\" content=\"Ra\u010dunalni\u0161ke novice\" \/>\n<meta property=\"article:published_time\" content=\"2025-09-28T05:49:00+00:00\" \/>\n<meta name=\"author\" content=\"sinusiks\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"sinusiks\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/viva.racunalniske-novice.com\/openai-pokazal-kje-umetna-inteligenca-ze-prehiteva-cloveske-strokovnjake\/\",\"url\":\"https:\/\/viva.racunalniske-novice.com\/openai-pokazal-kje-umetna-inteligenca-ze-prehiteva-cloveske-strokovnjake\/\",\"name\":\"OpenAI pokazal, kje umetna inteligenca \u017ee prehiteva \u010dlove\u0161ke strokovnjake - Ra\u010dunalni\u0161ke novice\",\"isPartOf\":{\"@id\":\"https:\/\/viva.racunalniske-novice.com\/en\/#website\"},\"datePublished\":\"2025-09-28T05:49:00+00:00\",\"dateModified\":\"2025-09-28T05:49:00+00:00\",\"author\":{\"@id\":\"https:\/\/viva.racunalniske-novice.com\/en\/#\/schema\/person\/afb62e36efa34516d50249517e4cdbb4\"},\"breadcrumb\":{\"@id\":\"https:\/\/viva.racunalniske-novice.com\/openai-pokazal-kje-umetna-inteligenca-ze-prehiteva-cloveske-strokovnjake\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/viva.racunalniske-novice.com\/openai-pokazal-kje-umetna-inteligenca-ze-prehiteva-cloveske-strokovnjake\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/viva.racunalniske-novice.com\/openai-pokazal-kje-umetna-inteligenca-ze-prehiteva-cloveske-strokovnjake\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/viva.racunalniske-novice.com\/en\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"OpenAI pokazal, kje umetna inteligenca \u017ee prehiteva \u010dlove\u0161ke strokovnjake\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/viva.racunalniske-novice.com\/en\/#website\",\"url\":\"https:\/\/viva.racunalniske-novice.com\/en\/\",\"name\":\"Ra\u010dunalni\u0161ke novice\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/viva.racunalniske-novice.com\/en\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/viva.racunalniske-novice.com\/en\/#\/schema\/person\/afb62e36efa34516d50249517e4cdbb4\",\"name\":\"sinusiks\",\"sameAs\":[\"https:\/\/ml.racunalniske-novice.com\"],\"url\":\"https:\/\/viva.racunalniske-novice.com\/en\/author\/sinusiks\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"OpenAI pokazal, kje umetna inteligenca \u017ee prehiteva \u010dlove\u0161ke strokovnjake - Ra\u010dunalni\u0161ke novice","description":"OpenAI je razkril nov merilnik uspe\u0161nosti UI modelov, imenovan GDPval. S tem meri, kako dobro se njihovi modeli umetne inteligence odre\u017eejo v primerjavi s \u010dlove\u0161kimi strokovnjaki v razli\u010dnih panogah.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/viva.racunalniske-novice.com\/en\/wp-json\/wp\/v2\/posts\/6679","og_locale":"en_US","og_type":"article","og_title":"OpenAI pokazal, kje umetna inteligenca \u017ee prehiteva \u010dlove\u0161ke strokovnjake - Ra\u010dunalni\u0161ke novice","og_description":"Kaj je GDPval? GDPval temelji na devetih panogah, ki najve\u010d prispevajo k ameri\u0161kemu BDP-ju, med njimi zdravstvo, finance, proizvodnja in javna uprava. Znotraj teh podro\u010dij je test zajel 44 poklicev, od programerjev do medicinskih sester in novinarjev. Prva razli\u010dica, GDPval-v0, deluje tako, da izku\u0161eni strokovnjaki primerjajo UI poro\u010dila s poro\u010dili ljudi in izberejo bolj\u0161e. Rezultati [&hellip;]","og_url":"https:\/\/viva.racunalniske-novice.com\/en\/openai-showed-where-artificial-intelligence-is-already-outperforming-human-experts\/","og_site_name":"Ra\u010dunalni\u0161ke novice","article_published_time":"2025-09-28T05:49:00+00:00","author":"sinusiks","twitter_card":"summary_large_image","twitter_misc":{"Written by":"sinusiks","Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/viva.racunalniske-novice.com\/openai-pokazal-kje-umetna-inteligenca-ze-prehiteva-cloveske-strokovnjake\/","url":"https:\/\/viva.racunalniske-novice.com\/openai-pokazal-kje-umetna-inteligenca-ze-prehiteva-cloveske-strokovnjake\/","name":"OpenAI pokazal, kje umetna inteligenca \u017ee prehiteva \u010dlove\u0161ke strokovnjake - Ra\u010dunalni\u0161ke novice","isPartOf":{"@id":"https:\/\/viva.racunalniske-novice.com\/en\/#website"},"datePublished":"2025-09-28T05:49:00+00:00","dateModified":"2025-09-28T05:49:00+00:00","author":{"@id":"https:\/\/viva.racunalniske-novice.com\/en\/#\/schema\/person\/afb62e36efa34516d50249517e4cdbb4"},"breadcrumb":{"@id":"https:\/\/viva.racunalniske-novice.com\/openai-pokazal-kje-umetna-inteligenca-ze-prehiteva-cloveske-strokovnjake\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/viva.racunalniske-novice.com\/openai-pokazal-kje-umetna-inteligenca-ze-prehiteva-cloveske-strokovnjake\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/viva.racunalniske-novice.com\/openai-pokazal-kje-umetna-inteligenca-ze-prehiteva-cloveske-strokovnjake\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/viva.racunalniske-novice.com\/en\/"},{"@type":"ListItem","position":2,"name":"OpenAI pokazal, kje umetna inteligenca \u017ee prehiteva \u010dlove\u0161ke strokovnjake"}]},{"@type":"WebSite","@id":"https:\/\/viva.racunalniske-novice.com\/en\/#website","url":"https:\/\/viva.racunalniske-novice.com\/en\/","name":"Ra\u010dunalni\u0161ke novice","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/viva.racunalniske-novice.com\/en\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/viva.racunalniske-novice.com\/en\/#\/schema\/person\/afb62e36efa34516d50249517e4cdbb4","name":"sinusiks","sameAs":["https:\/\/ml.racunalniske-novice.com"],"url":"https:\/\/viva.racunalniske-novice.com\/en\/author\/sinusiks\/"}]}},"_links":{"self":[{"href":"https:\/\/viva.racunalniske-novice.com\/en\/wp-json\/wp\/v2\/posts\/6679","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/viva.racunalniske-novice.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/viva.racunalniske-novice.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/viva.racunalniske-novice.com\/en\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/viva.racunalniske-novice.com\/en\/wp-json\/wp\/v2\/comments?post=6679"}],"version-history":[{"count":0,"href":"https:\/\/viva.racunalniske-novice.com\/en\/wp-json\/wp\/v2\/posts\/6679\/revisions"}],"wp:attachment":[{"href":"https:\/\/viva.racunalniske-novice.com\/en\/wp-json\/wp\/v2\/media?parent=6679"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/viva.racunalniske-novice.com\/en\/wp-json\/wp\/v2\/categories?post=6679"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/viva.racunalniske-novice.com\/en\/wp-json\/wp\/v2\/tags?post=6679"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}