{"id":11543,"date":"2024-04-14T16:29:00","date_gmt":"2024-04-14T16:29:00","guid":{"rendered":"https:\/\/dailyai.com\/?p=11543"},"modified":"2024-04-15T11:48:24","modified_gmt":"2024-04-15T11:48:24","slug":"xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa","status":"publish","type":"post","link":"https:\/\/dailyai.com\/pt\/2024\/04\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\/","title":{"rendered":"A xAI pr\u00e9-visualiza o Grok-1.5 e cria um novo par\u00e2metro de refer\u00eancia chamado RealWorldQA"},"content":{"rendered":"<p><strong>A xAI de Elon Musk revelou o Grok-1.5, um modelo de IA multimodal concebido para vencer a concorr\u00eancia na compreens\u00e3o de cen\u00e1rios do mundo real.\u00a0<\/strong><\/p>\n<p><span style=\"font-weight: 400;\">Seguindo os passos de outros, como o GPT-4V, o novo Grok-1.5 introduz o processamento visual para analisar tudo, desde documentos e diagramas a gr\u00e1ficos, capturas de ecr\u00e3 e fotografias.<\/span><\/p>\n<p><a href=\"https:\/\/x.ai\/blog\/grok-1.5\" target=\"_blank\" rel=\"noopener\"><span style=\"font-weight: 400;\">Grok-1.5<\/span><\/a><span style=\"font-weight: 400;\"> tamb\u00e9m ganha terreno em tarefas de texto, codifica\u00e7\u00e3o e matem\u00e1tica, obtendo 50,6% no par\u00e2metro de refer\u00eancia MATH, 90% no par\u00e2metro de refer\u00eancia GSM8K e 74,1% no par\u00e2metro de refer\u00eancia HumanEval.\u00a0<\/span><\/p>\n<p>Isto coloca o Grok-1.5 diretamente na categoria de pesos pesados do LLM, com uma m\u00e9dia de pontua\u00e7\u00f5es ligeiramente inferior \u00e0 do Gemini Pro 1.5, GPT-4 e Claude 3 Opus.<\/p>\n<figure id=\"attachment_11546\" aria-describedby=\"caption-attachment-11546\" style=\"width: 1024px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-11546 size-large\" src=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/GrokBenchmarks2-1024x343.png\" alt=\"Grok\" width=\"1024\" height=\"343\" srcset=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/GrokBenchmarks2-1024x343.png 1024w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/GrokBenchmarks2-300x100.png 300w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/GrokBenchmarks2-768x257.png 768w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/GrokBenchmarks2-1536x515.png 1536w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/GrokBenchmarks2-60x20.png 60w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/GrokBenchmarks2.png 1633w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption id=\"caption-attachment-11546\" class=\"wp-caption-text\">Os benchmarks competitivos de texto, matem\u00e1tica e codifica\u00e7\u00e3o do Grok-1.5. Fonte: xAI<\/figcaption><\/figure>\n<p><span style=\"font-weight: 400;\">O Grok-1.5 tamb\u00e9m oferece uma compreens\u00e3o de contexto mais longa, at\u00e9 128 mil tokens, um aumento de 16 vezes em compara\u00e7\u00e3o com o seu antecessor, embora muito aqu\u00e9m dos apresentados pelo Claude 3 Opus e Gemini 1.5 Pro.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">A avalia\u00e7\u00e3o Needle In A Haystack (NIAH) demonstrou a capacidade do Grok-1.5 para localizar texto incorporado em contextos com um comprimento m\u00e1ximo de 128K tokens.<\/span><\/p>\n<p>No entanto, \u00e9 nas capacidades de vis\u00e3o do Grok-1.5 que a xAI est\u00e1 a apostar mais.<\/p>\n<p><span style=\"font-weight: 400;\">Demonstra\u00e7\u00f5es <\/span><span style=\"font-weight: 400;\">mostram o Grok-1.5 a converter esquemas de blocos em c\u00f3digo Python, a gerar hist\u00f3rias de embalar inspiradas em pinturas de crian\u00e7as, a criar conjuntos de dados CSV a partir de capturas de ecr\u00e3 e at\u00e9 a \"expandir\" memes.\u00a0<\/span><\/p>\n<p>O Grok-1.5 lidera a tabela de classifica\u00e7\u00e3o em algumas refer\u00eancias estabelecidas, como o Mathvista e o TextVQA, e obt\u00e9m as melhores pontua\u00e7\u00f5es na nova refer\u00eancia estabelecida pela xAI, o RealWorldQA.<\/p>\n<figure id=\"attachment_11544\" aria-describedby=\"caption-attachment-11544\" style=\"width: 1024px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-11544 size-large\" src=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/GrokBenchmarks-1024x695.png\" alt=\"\" width=\"1024\" height=\"695\" srcset=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/GrokBenchmarks-1024x695.png 1024w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/GrokBenchmarks-300x204.png 300w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/GrokBenchmarks-768x522.png 768w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/GrokBenchmarks-60x41.png 60w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/GrokBenchmarks.png 1309w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption id=\"caption-attachment-11544\" class=\"wp-caption-text\">Os impressionantes benchmarks de vis\u00e3o do Grok-1.5. Fonte: xAI<\/figcaption><\/figure>\n<p><span style=\"font-weight: 400;\">Por baixo do cap\u00f4, o Grok-1.5 \u00e9 alimentado por uma estrutura de treinamento distribu\u00edda personalizada que permite que a equipe da xAI crie prot\u00f3tipos de ideias e treine novas arquiteturas em escala com o m\u00ednimo de esfor\u00e7o.<\/span><\/p>\n<p><span style=\"font-weight: 400;\"> xAI foi <\/span><a href=\"http:\/\/v\"><span style=\"font-weight: 400;\">fundada no ano passado<\/span><\/a><span style=\"font-weight: 400;\"> e inclui alguns dos melhores investigadores de IA do mundo com o objetivo ultra-ambicioso de \"Compreender o universo\".\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">At\u00e9 agora, temos o espirituoso e estranho Grok-1 que diz \u00e0s pessoas como sintetizar narc\u00f3ticos e <\/span><a href=\"https:\/\/dailyai.com\/pt\/2023\/12\/xais-grok-drops-an-awkward-blooper-by-referring-to-openai\/\"><span style=\"font-weight: 400;\">critica Musk e a Tesla<\/span><\/a><span style=\"font-weight: 400;\">.<\/span><\/p>\n<p><span style=\"font-weight: 400;\"> O Grok tamb\u00e9m est\u00e1 ligado \u00e0 base de dados de posts do X, o que, entre outras particularidades \u00fanicas, lhe deu um grande n\u00famero de seguidores, apesar de n\u00e3o incomodar os l\u00edderes em termos de desempenho puro.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">O projeto xAI de Musk desafia o ecossistema de c\u00f3digo fechado da IA generativa, tornando os seus modelos geralmente dispon\u00edveis sob verdadeiros <\/span><a href=\"https:\/\/dailyai.com\/pt\/2024\/03\/elon-musks-xai-open-sources-its-llm-grok-1\/\"><span style=\"font-weight: 400;\">licen\u00e7as de fonte aberta<\/span><\/a><span style=\"font-weight: 400;\">.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Em conjunto com a Meta, que tem uma inten\u00e7\u00e3o semelhante de ir contra a corrente dos concorrentes, a tese aberta da xAI pode tornar-se um espinho nos esfor\u00e7os de rentabiliza\u00e7\u00e3o da OpenAI, Microsoft, Anthropic e Google.<\/span><\/p>\n<h2>RealWorldQA<\/h2>\n<p>A pr\u00e9-visualiza\u00e7\u00e3o do Grok-1.5 tamb\u00e9m viu a xAI revelar o RealWorldQA, um novo par\u00e2metro de refer\u00eancia que consiste em mais de 700 imagens, cada uma acompanhada por uma pergunta e uma resposta verific\u00e1vel.<\/p>\n<p><span style=\"font-weight: 400;\">O conjunto de dados inclui principalmente imagens an\u00f3nimas capturadas de ve\u00edculos e outras situa\u00e7\u00f5es do mundo real.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">O conjunto de dados RealWorldQA foi concebido para avaliar as capacidades de compreens\u00e3o espacial do Grok 1.5 e de outros modelos de IA multimodal.\u00a0<\/span><\/p>\n<figure id=\"attachment_11545\" aria-describedby=\"caption-attachment-11545\" style=\"width: 1024px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-11545 size-large\" src=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/realworld-1024x258.png\" alt=\"Grok\" width=\"1024\" height=\"258\" srcset=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/realworld-1024x258.png 1024w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/realworld-300x76.png 300w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/realworld-768x193.png 768w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/realworld-1536x387.png 1536w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/realworld-60x15.png 60w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/realworld.png 1947w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption id=\"caption-attachment-11545\" class=\"wp-caption-text\">O conjunto de dados de refer\u00eancia RealWorldQA tem como objetivo testar a capacidade dos modelos para compreenderem cenas naturais. Fonte: xAI<\/figcaption><\/figure>\n<p>O Grok-1.5 supera os concorrentes no RealWorldQA, e ser\u00e1 interessante ver se ele se populariza.<\/p>\n<p><span style=\"font-weight: 400;\">Embora n\u00e3o chegue a compreender o universo, o Grok-1.5 ser\u00e1 mais um modelo de topo numa gama cada vez maior. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Isto tamb\u00e9m mostra como a IA generativa, na sua forma atual, est\u00e1 a atingir os picos dos seus poderes - embora talvez n\u00e3o por muito tempo.\u00a0<\/span><\/p>","protected":false},"excerpt":{"rendered":"<p>A xAI de Elon Musk revelou o Grok-1.5, um modelo de IA multimodal concebido para vencer a concorr\u00eancia na compreens\u00e3o de cen\u00e1rios do mundo real.  Seguindo os passos de outros, como o GPT-4V, o novo Grok-1.5 introduz o processamento visual para analisar tudo, desde documentos e diagramas a gr\u00e1ficos, capturas de ecr\u00e3 e fotografias. O Grok-1.5 tamb\u00e9m ganha terreno em tarefas de texto, codifica\u00e7\u00e3o e matem\u00e1tica, obtendo 50,6% no benchmark MATH, 90% no benchmark GSM8K e 74,1% no benchmark HumanEval.  Isto coloca o Grok-1.5 diretamente na categoria de pesos pesados do LLM, com uma m\u00e9dia de pontua\u00e7\u00f5es ligeiramente inferior \u00e0 do Gemini Pro 1.5, GPT-4 e Claude 3 Opus. O Grok-1.5 tamb\u00e9m oferece uma compreens\u00e3o de contexto mais longa at\u00e9<\/p>","protected":false},"author":2,"featured_media":11548,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[188,481,223],"class_list":["post-11543","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-elon-musk","tag-grok","tag-xai"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>xAI previews Grok-1.5 and creates a new benchmark called RealWorldQA | 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\/pt\/2024\/04\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\/\" \/>\n<meta property=\"og:locale\" content=\"pt_PT\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"xAI previews Grok-1.5 and creates a new benchmark called RealWorldQA | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Elon Musk&#8217;s xAI has revealed Grok-1.5, a multimodal AI model designed to beat competitors in understanding real-world scenarios.\u00a0 Following in the footsteps of others, like GPT-4V, the new Grok-1.5 introduces visual processing to analyze anything from documents and diagrams to charts, screenshots, and photographs. Grok-1.5 also gains ground in text, coding, and math tasks, scoring 50.6% on the MATH benchmark, 90% on the GSM8K benchmark, and 74.1% on the HumanEval benchmark.\u00a0 This throws Grok-1.5 right into the LLM heavyweight tier, averaging slightly lower scores than Gemini Pro 1.5, GPT-4, and Claude 3 Opus. Grok-1.5 also offers longer context understanding up\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/pt\/2024\/04\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-04-14T16:29:00+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-04-15T11:48:24+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-14-17.28.41-Create-an-image-with-the-word-GROK-in-a-clear-legible-bold-sans-serif-font-centered-on-a-high-quality-landscape-canvas.-The-background-should-b.webp\" \/>\n\t<meta property=\"og:image:width\" content=\"1792\" \/>\n\t<meta property=\"og:image:height\" content=\"1024\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/webp\" \/>\n<meta name=\"author\" content=\"Sam Jeans\" \/>\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=\"Escrito por\" \/>\n\t<meta name=\"twitter:data1\" content=\"Sam Jeans\" \/>\n\t<meta name=\"twitter:label2\" content=\"Tempo estimado de leitura\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutos\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\\\/\"},\"author\":{\"name\":\"Sam Jeans\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/711e81f945549438e8bbc579efdeb3c9\"},\"headline\":\"xAI previews Grok-1.5 and creates a new benchmark called RealWorldQA\",\"datePublished\":\"2024-04-14T16:29:00+00:00\",\"dateModified\":\"2024-04-15T11:48:24+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\\\/\"},\"wordCount\":546,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/DALL\u00b7E-2024-04-14-17.28.41-Create-an-image-with-the-word-GROK-in-a-clear-legible-bold-sans-serif-font-centered-on-a-high-quality-landscape-canvas.-The-background-should-b.webp\",\"keywords\":[\"Elon Musk\",\"Grok\",\"xAI\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"pt-PT\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\\\/\",\"name\":\"xAI previews Grok-1.5 and creates a new benchmark called RealWorldQA | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/DALL\u00b7E-2024-04-14-17.28.41-Create-an-image-with-the-word-GROK-in-a-clear-legible-bold-sans-serif-font-centered-on-a-high-quality-landscape-canvas.-The-background-should-b.webp\",\"datePublished\":\"2024-04-14T16:29:00+00:00\",\"dateModified\":\"2024-04-15T11:48:24+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\\\/#breadcrumb\"},\"inLanguage\":\"pt-PT\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"pt-PT\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/DALL\u00b7E-2024-04-14-17.28.41-Create-an-image-with-the-word-GROK-in-a-clear-legible-bold-sans-serif-font-centered-on-a-high-quality-landscape-canvas.-The-background-should-b.webp\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/DALL\u00b7E-2024-04-14-17.28.41-Create-an-image-with-the-word-GROK-in-a-clear-legible-bold-sans-serif-font-centered-on-a-high-quality-landscape-canvas.-The-background-should-b.webp\",\"width\":1792,\"height\":1024},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"xAI previews Grok-1.5 and creates a new benchmark called RealWorldQA\"}]},{\"@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\":\"pt-PT\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"pt-PT\",\"@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\\\/711e81f945549438e8bbc579efdeb3c9\",\"name\":\"Sam Jeans\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"pt-PT\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"caption\":\"Sam Jeans\"},\"description\":\"Sam is a science and technology writer who has worked in various AI startups. When he\u2019s not writing, he can be found reading medical journals or digging through boxes of vinyl records.\",\"sameAs\":[\"https:\\\/\\\/www.linkedin.com\\\/in\\\/sam-jeans-6746b9142\\\/\"],\"url\":\"https:\\\/\\\/dailyai.com\\\/pt\\\/author\\\/samjeans\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"A xAI pr\u00e9-visualiza o Grok-1.5 e cria um novo par\u00e2metro de refer\u00eancia chamado RealWorldQA | 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\/pt\/2024\/04\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\/","og_locale":"pt_PT","og_type":"article","og_title":"xAI previews Grok-1.5 and creates a new benchmark called RealWorldQA | DailyAI","og_description":"Elon Musk&#8217;s xAI has revealed Grok-1.5, a multimodal AI model designed to beat competitors in understanding real-world scenarios.\u00a0 Following in the footsteps of others, like GPT-4V, the new Grok-1.5 introduces visual processing to analyze anything from documents and diagrams to charts, screenshots, and photographs. Grok-1.5 also gains ground in text, coding, and math tasks, scoring 50.6% on the MATH benchmark, 90% on the GSM8K benchmark, and 74.1% on the HumanEval benchmark.\u00a0 This throws Grok-1.5 right into the LLM heavyweight tier, averaging slightly lower scores than Gemini Pro 1.5, GPT-4, and Claude 3 Opus. Grok-1.5 also offers longer context understanding up","og_url":"https:\/\/dailyai.com\/pt\/2024\/04\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\/","og_site_name":"DailyAI","article_published_time":"2024-04-14T16:29:00+00:00","article_modified_time":"2024-04-15T11:48:24+00:00","og_image":[{"width":1792,"height":1024,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-14-17.28.41-Create-an-image-with-the-word-GROK-in-a-clear-legible-bold-sans-serif-font-centered-on-a-high-quality-landscape-canvas.-The-background-should-b.webp","type":"image\/webp"}],"author":"Sam Jeans","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"Escrito por":"Sam Jeans","Tempo estimado de leitura":"4 minutos"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/04\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/04\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\/"},"author":{"name":"Sam Jeans","@id":"https:\/\/dailyai.com\/#\/schema\/person\/711e81f945549438e8bbc579efdeb3c9"},"headline":"xAI previews Grok-1.5 and creates a new benchmark called RealWorldQA","datePublished":"2024-04-14T16:29:00+00:00","dateModified":"2024-04-15T11:48:24+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/04\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\/"},"wordCount":546,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/04\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-14-17.28.41-Create-an-image-with-the-word-GROK-in-a-clear-legible-bold-sans-serif-font-centered-on-a-high-quality-landscape-canvas.-The-background-should-b.webp","keywords":["Elon Musk","Grok","xAI"],"articleSection":["Industry"],"inLanguage":"pt-PT"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/04\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\/","url":"https:\/\/dailyai.com\/2024\/04\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\/","name":"A xAI pr\u00e9-visualiza o Grok-1.5 e cria um novo par\u00e2metro de refer\u00eancia chamado RealWorldQA | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/04\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/04\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-14-17.28.41-Create-an-image-with-the-word-GROK-in-a-clear-legible-bold-sans-serif-font-centered-on-a-high-quality-landscape-canvas.-The-background-should-b.webp","datePublished":"2024-04-14T16:29:00+00:00","dateModified":"2024-04-15T11:48:24+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/04\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\/#breadcrumb"},"inLanguage":"pt-PT","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/04\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\/"]}]},{"@type":"ImageObject","inLanguage":"pt-PT","@id":"https:\/\/dailyai.com\/2024\/04\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-14-17.28.41-Create-an-image-with-the-word-GROK-in-a-clear-legible-bold-sans-serif-font-centered-on-a-high-quality-landscape-canvas.-The-background-should-b.webp","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-14-17.28.41-Create-an-image-with-the-word-GROK-in-a-clear-legible-bold-sans-serif-font-centered-on-a-high-quality-landscape-canvas.-The-background-should-b.webp","width":1792,"height":1024},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/04\/xai-previews-grok-1-5-and-creates-a-new-benchmark-called-realworldqa\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"xAI previews Grok-1.5 and creates a new benchmark called RealWorldQA"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DailyAI","description":"A sua dose di\u00e1ria de not\u00edcias sobre IA","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":"pt-PT"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"pt-PT","@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\/711e81f945549438e8bbc579efdeb3c9","name":"Cal\u00e7as de ganga Sam","image":{"@type":"ImageObject","inLanguage":"pt-PT","@id":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","caption":"Sam Jeans"},"description":"Sam \u00e9 um escritor de ci\u00eancia e tecnologia que trabalhou em v\u00e1rias startups de IA. Quando n\u00e3o est\u00e1 a escrever, pode ser encontrado a ler revistas m\u00e9dicas ou a vasculhar caixas de discos de vinil.","sameAs":["https:\/\/www.linkedin.com\/in\/sam-jeans-6746b9142\/"],"url":"https:\/\/dailyai.com\/pt\/author\/samjeans\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/posts\/11543","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/comments?post=11543"}],"version-history":[{"count":6,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/posts\/11543\/revisions"}],"predecessor-version":[{"id":11553,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/posts\/11543\/revisions\/11553"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/media\/11548"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/media?parent=11543"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/categories?post=11543"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/tags?post=11543"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}