{"id":8600,"date":"2023-12-22T15:36:47","date_gmt":"2023-12-22T15:36:47","guid":{"rendered":"https:\/\/dailyai.com\/?p=8600"},"modified":"2023-12-22T15:36:47","modified_gmt":"2023-12-22T15:36:47","slug":"researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo","status":"publish","type":"post","link":"https:\/\/dailyai.com\/da\/2023\/12\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\/","title":{"rendered":"Forskere finder ud af, at Gemini ikke engang kan sl\u00e5 GPT-3.5 Turbo"},"content":{"rendered":"<p><strong>Da Google annoncerede udgivelsen af sine Gemini-modeller, var der stor begejstring, da virksomheden sagde, at de var p\u00e5 niveau med tilbuddene fra OpenAI. Det er m\u00e5ske ikke helt sandt.<\/strong><\/p>\n<p>Google sagde, at dets <a href=\"https:\/\/dailyai.com\/da\/2023\/12\/google-launches-its-new-gemini-multi-modal-family-of-models\/\">Gemini Ultra<\/a> modellen er bedre end GPT-4. Modellen er endnu ikke frigivet, s\u00e5 vi bliver n\u00f8dt til at tage deres benchmark-testresultater for gode varer. Gemini Pro er blevet udgivet, og Google siger, at den er p\u00e5 niveau med GPT-3.5.<\/p>\n<p>Forskere fra Carnegie Mellon University og AI-softwareplatformen BerriAI satte Gemini Pro p\u00e5 en r\u00e6kke opgaver for at teste dens evne til at forst\u00e5 og generere sprog.<\/p>\n<p>De k\u00f8rte de samme tests med GPT-3.5 Turbo, GPT-4 Turbo og Mistral AI's nye <a href=\"https:\/\/dailyai.com\/da\/2023\/12\/the-rise-of-the-french-ai-startup-mistral\/\">Mixtral 8x7B model<\/a>.<\/p>\n<blockquote class=\"twitter-tweet\">\n<p dir=\"ltr\" lang=\"en\">Googles Gemini slog for nylig igennem som en stor konkurrent til OpenAI's GPT. Sp\u00e6ndende! Men vi undrede os:<\/p>\n<p>Hvor god er Gemini egentlig?<\/p>\n<p>P\u00e5 CMU udf\u00f8rte vi en upartisk, dybdeg\u00e5ende og reproducerbar unders\u00f8gelse, der sammenlignede Gemini, GPT og Mixtral.<\/p>\n<p>Papir: <a href=\"https:\/\/t.co\/S3T7ediQLa\">https:\/\/t.co\/S3T7ediQLa<\/a><br \/>\n\ud83e\uddf5 <a href=\"https:\/\/t.co\/NmEOeDd8pI\">pic.twitter.com\/NmEOeDd8pI<\/a><\/p>\n<p>- Graham Neubig (@gneubig) <a href=\"https:\/\/twitter.com\/gneubig\/status\/1737108966931673191?ref_src=twsrc%5Etfw\">19. december 2023<\/a><\/p><\/blockquote>\n<p><script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<h2>Resultater<\/h2>\n<p>Ikke overraskende kom GPT-4 ud p\u00e5 toppen, men Google vil v\u00e6re mindre sp\u00e6ndt p\u00e5 at se, hvordan Gemini Pro klarede sig i forhold til GPT 3.5 Turbo. I en opsummering af holdets resultater, <a href=\"https:\/\/arxiv.org\/pdf\/2312.11444.pdf\" target=\"_blank\" rel=\"noopener\">papiret<\/a> \"Geminis Pro-model opn\u00e5ede en sammenlignelig, men lidt ringere n\u00f8jagtighed sammenlignet med den nuv\u00e6rende version af OpenAI's GPT 3.5 Turbo.\"<\/p>\n<p>Her er et sammendrag af resultaterne.<\/p>\n<figure id=\"attachment_8601\" aria-describedby=\"caption-attachment-8601\" style=\"width: 1338px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-8601 size-full\" src=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Model-test-scores.png\" alt=\"\" width=\"1338\" height=\"638\" srcset=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Model-test-scores.png 1338w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Model-test-scores-300x143.png 300w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Model-test-scores-1024x488.png 1024w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Model-test-scores-768x366.png 768w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Model-test-scores-370x176.png 370w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Model-test-scores-800x381.png 800w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Model-test-scores-740x353.png 740w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Model-test-scores-20x10.png 20w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Model-test-scores-101x48.png 101w\" sizes=\"auto, (max-width: 1338px) 100vw, 1338px\" \/><figcaption id=\"caption-attachment-8601\" class=\"wp-caption-text\">Sammenligning af modelresultater for forskellige opgaver. Kilde: arXiv<\/figcaption><\/figure>\n<p>Modellerne blev bedt om at bruge BerriAI's LiteLLM-gr\u00e6nseflade, og hver model fik n\u00f8jagtig de samme beskeder og den samme evalueringsprotokol.<\/p>\n<p>Modellerne blev testet p\u00e5 multiple choice-sp\u00f8rgsm\u00e5l, generelle r\u00e6sonnementer, matematiske r\u00e6sonnementer, kodegenerering, sprogovers\u00e6ttelse og som webagent.<\/p>\n<p>En af grundene til, at Gemini Pro klarede sig d\u00e5rligt i multiple choice-sp\u00f8rgsm\u00e5lene, er, at den havde en st\u00e6rk positionel bias. Den valgte ofte svaret i position D, uanset om det var korrekt eller ej. Interessant nok er dette noget, som Microsofts <a href=\"https:\/\/dailyai.com\/da\/2023\/12\/microsoft-shades-gemini-with-gpt-4-boosted-by-medprompt\/\">Medprompt<\/a> l\u00f8ses med blanding.<\/p>\n<p>P\u00e5 trods af at Gemini Pro tabte nogle af testene, slog den GPT-3.5 Turbo p\u00e5 to omr\u00e5der, nemlig ordsortering og symbolmanipulation og -overs\u00e6ttelse.<\/p>\n<p>I alle de overs\u00e6ttelsesopgaver, Gemini Pro gennemf\u00f8rte, klarede den sig bedre end alle de andre modeller, inklusive GPT-4. Gemini Pros endelige score p\u00e5 overs\u00e6ttelsestestene var dog lavere end GPT-3.5, fordi den afviste at gennemf\u00f8re nogle anmodninger, da dens overivrige indholdsmoderation blev sat i gang.<\/p>\n<h2>Og hvad s\u00e5?<\/h2>\n<p>Google bestrider de tal, som forskerne kom frem til, og insisterer p\u00e5, at deres tal viser, at Gemini Pro er p\u00e5 niveau med eller bedre end GPT-3.5. Hvis vi tager h\u00f8jde for de utallige variabler og giver Google lidt spillerum, kan vi dele forskellen og sige, at Gemini Pro og GPT-3.5 stort set er ens.<\/p>\n<p>Det vigtigste her er, at Gemini Pro, en helt ny model, som Google har brugt m\u00e5neder p\u00e5 at udvikle, ikke sl\u00e5r en model, der har v\u00e6ret ude i mere end et \u00e5r og er gratis at bruge via ChatGPT.<\/p>\n<p>Gemini Ultra forventes at blive udgivet i begyndelsen af 2024. Vil den leve op til sin p\u00e5stand om at v\u00e6re bedre end GPT-4? Lad os h\u00e5be, at professor Graham Neubig og hans team snart f\u00e5r mulighed for at k\u00f8re lignende benchmarking-tests.<\/p>","protected":false},"excerpt":{"rendered":"<p>Da Google annoncerede udgivelsen af sine Gemini-modeller, var der stor begejstring, da virksomheden sagde, at de var p\u00e5 niveau med tilbuddene fra OpenAI. Det er m\u00e5ske ikke helt sandt. Google sagde, at deres Gemini Ultra-model er bedre end GPT-4. Modellen er endnu ikke frigivet, s\u00e5 vi bliver n\u00f8dt til at tage deres benchmark-testresultater for p\u00e5lydende. Gemini Pro er blevet udgivet, og Google siger, at den er p\u00e5 niveau med GPT-3.5. Forskere fra Carnegie Mellon University og AI-softwareplatformen BerriAI udsatte Gemini Pro for en r\u00e6kke opgaver for at teste dens sprog.<\/p>","protected":false},"author":6,"featured_media":8602,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[99,102,93],"class_list":["post-8600","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-ai-race","tag-google","tag-openai"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Researchers find that Gemini can&#039;t even beat GPT-3.5 Turbo | DailyAI<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/dailyai.com\/da\/2023\/12\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\/\" \/>\n<meta property=\"og:locale\" content=\"da_DK\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Researchers find that Gemini can&#039;t even beat GPT-3.5 Turbo | DailyAI\" \/>\n<meta property=\"og:description\" content=\"When Google announced the release of its Gemini models there was a lot of excitement as the company said these were on par with offerings from OpenAI. That may not be completely true. Google said that its Gemini Ultra model is better than GPT-4. The model is yet to be released so we\u2019ll have to take their benchmark test results at face value. Gemini Pro has been released and Google says it is on par with GPT-3.5. Researchers from Carnegie Mellon University and the AI software platform BerriAI put Gemini Pro through a series of tasks to test its language\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/da\/2023\/12\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2023-12-22T15:36:47+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Google-Gemini.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"667\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Eugene van der Watt\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:site\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:label1\" content=\"Skrevet af\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Estimeret l\u00e6setid\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutter\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"Researchers find that Gemini can&#8217;t even beat GPT-3.5 Turbo\",\"datePublished\":\"2023-12-22T15:36:47+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\\\/\"},\"wordCount\":556,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/12\\\/Google-Gemini.jpg\",\"keywords\":[\"AI race\",\"Google\",\"OpenAI\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"da-DK\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\\\/\",\"name\":\"Researchers find that Gemini can't even beat GPT-3.5 Turbo | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/12\\\/Google-Gemini.jpg\",\"datePublished\":\"2023-12-22T15:36:47+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\\\/#breadcrumb\"},\"inLanguage\":\"da-DK\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"da-DK\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/12\\\/Google-Gemini.jpg\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/12\\\/Google-Gemini.jpg\",\"width\":1000,\"height\":667},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Researchers find that Gemini can&#8217;t even beat GPT-3.5 Turbo\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"name\":\"DailyAI\",\"description\":\"Your Daily Dose of AI News\",\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/dailyai.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"da-DK\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"da-DK\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"width\":4501,\"height\":934,\"caption\":\"DailyAI\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/DailyAIOfficial\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/dailyaiofficial\\\/\",\"https:\\\/\\\/www.youtube.com\\\/@DailyAIOfficial\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\",\"name\":\"Eugene van der Watt\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"da-DK\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"caption\":\"Eugene van der Watt\"},\"description\":\"Eugene comes from an electronic engineering background and loves all things tech. When he takes a break from consuming AI news you'll find him at the snooker table.\",\"sameAs\":[\"www.linkedin.com\\\/in\\\/eugene-van-der-watt-16828119\"],\"url\":\"https:\\\/\\\/dailyai.com\\\/da\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Forskere finder ud af, at Gemini ikke engang kan sl\u00e5 GPT-3.5 Turbo | DailyAI","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:\/\/dailyai.com\/da\/2023\/12\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\/","og_locale":"da_DK","og_type":"article","og_title":"Researchers find that Gemini can't even beat GPT-3.5 Turbo | DailyAI","og_description":"When Google announced the release of its Gemini models there was a lot of excitement as the company said these were on par with offerings from OpenAI. That may not be completely true. Google said that its Gemini Ultra model is better than GPT-4. The model is yet to be released so we\u2019ll have to take their benchmark test results at face value. Gemini Pro has been released and Google says it is on par with GPT-3.5. Researchers from Carnegie Mellon University and the AI software platform BerriAI put Gemini Pro through a series of tasks to test its language","og_url":"https:\/\/dailyai.com\/da\/2023\/12\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\/","og_site_name":"DailyAI","article_published_time":"2023-12-22T15:36:47+00:00","og_image":[{"width":1000,"height":667,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Google-Gemini.jpg","type":"image\/jpeg"}],"author":"Eugene van der Watt","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"Skrevet af":"Eugene van der Watt","Estimeret l\u00e6setid":"3 minutter"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2023\/12\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2023\/12\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"Researchers find that Gemini can&#8217;t even beat GPT-3.5 Turbo","datePublished":"2023-12-22T15:36:47+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2023\/12\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\/"},"wordCount":556,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2023\/12\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Google-Gemini.jpg","keywords":["AI race","Google","OpenAI"],"articleSection":["Industry"],"inLanguage":"da-DK"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2023\/12\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\/","url":"https:\/\/dailyai.com\/2023\/12\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\/","name":"Forskere finder ud af, at Gemini ikke engang kan sl\u00e5 GPT-3.5 Turbo | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2023\/12\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2023\/12\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Google-Gemini.jpg","datePublished":"2023-12-22T15:36:47+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2023\/12\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\/#breadcrumb"},"inLanguage":"da-DK","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2023\/12\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\/"]}]},{"@type":"ImageObject","inLanguage":"da-DK","@id":"https:\/\/dailyai.com\/2023\/12\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Google-Gemini.jpg","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/12\/Google-Gemini.jpg","width":1000,"height":667},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2023\/12\/researchers-find-that-gemini-cant-even-beat-gpt-3-5-turbo\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"Researchers find that Gemini can&#8217;t even beat GPT-3.5 Turbo"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DailyAI","description":"Din daglige dosis af AI-nyheder","publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/dailyai.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"da-DK"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"da-DK","@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","width":4501,"height":934,"caption":"DailyAI"},"image":{"@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/DailyAIOfficial","https:\/\/www.linkedin.com\/company\/dailyaiofficial\/","https:\/\/www.youtube.com\/@DailyAIOfficial"]},{"@type":"Person","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa","name":"Eugene van der Watt","image":{"@type":"ImageObject","inLanguage":"da-DK","@id":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","caption":"Eugene van der Watt"},"description":"Eugene har en baggrund som elektronikingeni\u00f8r og elsker alt, hvad der har med teknologi at g\u00f8re. N\u00e5r han tager en pause fra at l\u00e6se AI-nyheder, kan du finde ham ved snookerbordet.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/da\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts\/8600","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/comments?post=8600"}],"version-history":[{"count":2,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts\/8600\/revisions"}],"predecessor-version":[{"id":8604,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts\/8600\/revisions\/8604"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/media\/8602"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/media?parent=8600"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/categories?post=8600"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/tags?post=8600"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}