{"id":6136,"date":"2026-10-19T16:49:16","date_gmt":"2026-10-19T16:49:16","guid":{"rendered":"https:\/\/i10xnews.kinsta.cloud\/?p=6136"},"modified":"2026-10-19T17:19:47","modified_gmt":"2026-10-19T17:19:47","slug":"vibethinker-3b-small-model-verifiable-reasoning","status":"publish","type":"post","link":"https:\/\/i10x.ai\/news\/vibethinker-3b-small-model-verifiable-reasoning","title":{"rendered":"A 3B Model Hits 94.3 on AIME26 and 80.2 on LiveCodeBench"},"content":{"rendered":"\n<h2 class=\"wp-block-heading\">\u26a1 Quick Take<\/h2>\n\n<ul class=\"wp-block-list\"><li><strong>The finding:<\/strong> The 3B dense VibeThinker-3B scores 94.3 on AIME26 and 80.2 Pass@1 on LiveCodeBench v6, matching or beating much larger flagships on verifiable tasks.<\/li><li><strong>Test-time boost:<\/strong> Claim-level test-time scaling lifts AIME26 to 97.1.<\/li><li><strong>Not just memorization:<\/strong> 96.1% acceptance on unseen LeetCode contests (Apr 25\u2013May 31, 2026); IFEval stays at 93.4.<\/li><\/ul>\n\n\n<p class=\"wp-block-paragraph\">How far can verifiable reasoning go in a strictly small model? Sina Weibo Inc. reports VibeThinker-3B, extending their earlier 1.5B Spectrum-to-Signal work with curriculum SFT, multi-domain RL and offline self-distillation.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1344\" height=\"768\" src=\"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/10\/vibethinker-3b-small-model-verifiable-reasoning-scores.webp\" alt=\"Column chart: AIME26 94.3, with CLR 97.1, LiveCodeBench 80.2, LeetCode 96.1, IFEval 93.4.\" class=\"wp-image-6135\" srcset=\"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/vibethinker-3b-small-model-verifiable-reasoning-scores.webp 1344w, https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/vibethinker-3b-small-model-verifiable-reasoning-scores-300x171.webp 300w, https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/vibethinker-3b-small-model-verifiable-reasoning-scores-1024x585.webp 1024w, https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/vibethinker-3b-small-model-verifiable-reasoning-scores-768x439.webp 768w\" sizes=\"auto, (max-width: 1344px) 100vw, 1344px\" \/><figcaption class=\"wp-element-caption\">i10X chart based on data from Xu et al. (2026), arXiv:2606.16140, Table 2 \/ abstract (CC0 1.0).<\/figcaption><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">\ud83d\udd2c What the study shows<\/h2>\n\n\n<p class=\"wp-block-paragraph\">Results place the model in a first-tier reasoning band versus systems such as DeepSeek V3.2, GLM-5 and Gemini 3 Pro on the reported verifiable suites, while preserving instruction following.<\/p>\n\n\n<ul class=\"wp-block-list\"><li><strong>Parametric Compression-Coverage Hypothesis:<\/strong> Authors argue verifiable reasoning is compressible into small parameter budgets when post-training is carefully staged.<\/li><li><strong>CLR averaging:<\/strong> Claim-level test-time scaling flow run 8 times; averaged Pass@1 reported as +CLR.<\/li><\/ul>\n\n\n<h2 class=\"wp-block-heading\">\u2705 Why it matters: small can be elite on verifiable tasks<\/h2>\n\n\n<p class=\"wp-block-paragraph\">If a 3B model sits with frontier systems on math\/code contests, deployment economics change for offline and edge reasoning.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\ud83e\uddea Method in brief<\/h2>\n\n\n<p class=\"wp-block-paragraph\">Curriculum SFT, multi-domain RL, offline self-distillation; global batch 128, cosine LR from 5e-5 to 8e-8.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\u2753 What remains open<\/h2>\n\n<ul class=\"wp-block-list\"><li><strong>Vendor report:<\/strong> All authors at Weibo; independent replication needed.<\/li><li><strong>Task family:<\/strong> Focused on verifiable reasoning, not open-ended chat.<\/li><\/ul>\n\n\n<h2 class=\"wp-block-heading\">\ud83e\udded Context<\/h2>\n\n\n<p class=\"wp-block-paragraph\">Related small-model reasoning in <a href=\"\/news\/category\/studies\/reasoning\">Reasoning<\/a>.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\ud83d\udee0\ufe0f What it means for builders<\/h2>\n\n<ul class=\"wp-block-list\"><li><strong>Try staged post-training:<\/strong> Curriculum + RL + self-distill.<\/li><li><strong>Keep IFEval in the loop:<\/strong> Reasoning need not kill controllability.<\/li><li><strong>Budget test-time compute:<\/strong> CLR still helps a strong 3B.<\/li><\/ul>\n\n\n<h2 class=\"wp-block-heading\">\u270d\ufe0f About the analysis<\/h2>\n\n\n<p class=\"wp-block-paragraph\">This article is based on the full text of the preprint &#8220;VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models&#8221; (arXiv:2606.16140v1, submitted June 15, 2026). All numbers are taken from the paper&#8217;s text, tables and figures; i10X did not rerun the experiments. The chart was redrawn by i10X from Table 2 \/ abstract of the paper, which is published under a CC0 1.0 license.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\ud83d\udd2d i10x Perspective<\/h2>\n\n\n<p class=\"wp-block-paragraph\">VibeThinker-3B is a shot across the bow of &#8220;bigger is the only path&#8221; for contest-style reasoning. Treat it as a strong existence proof pending third-party evals \u2014 and as motivation to measure compression of verifiable skills, not just parameter counts.<\/p>\n\n","protected":false},"excerpt":{"rendered":"<p>VibeThinker-3B from Weibo reaches frontier-band verifiable reasoning: 94.3 AIME26 (97.1 with claim-level TTS), 80.2 LiveCodeBench v6 Pass@1, 96.1% on recent LeetCode contests \u2014 without sacrificing IFEval (93.4).<\/p>\n","protected":false},"author":2,"featured_media":6286,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"paper_title":"VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models","paper_url":"https:\/\/arxiv.org\/abs\/2606.16140","pdf_url":"https:\/\/arxiv.org\/pdf\/2606.16140v1","doi":"","arxiv_id":"2606.16140","authors":"Sen Xu, Shixi Liu, Wei Wang, Jixin Min, Yingwei Dai, Zhibin Yin, Yirong Chen, Xin Zhou, Junlin Zhang","institutions":"Sina Weibo Inc.","paper_date":"2026-06-15","venue":"arXiv (cs.AI), version 1","peer_reviewed":false,"code_url":"","data_url":"","funding_coi":"All authors affiliated with Sina Weibo Inc.","figure_license":"Chart drawn by i10X from Table 2 \/ abstract (CC0 1.0)","paper_license":"CC0 1.0","replication":"no","study_models":"VibeThinker-3B (3B dense); compared to DeepSeek V3.2, GLM-5, Gemini 3 Pro and others","study_sample":"AIME26, LiveCodeBench v6, LeetCode contests, IFEval","footnotes":"","_yoast_wpseo_primary_category":""},"categories":[56,52],"tags":[],"companies":[46,37,38],"products":[49],"class_list":["post-6136","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-reasoning","category-studies","company-deepseek","company-google","company-open-ai","product-gemini"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.7 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>VibeThinker-3B: Frontier Reasoning in a 3B Model - i10X News<\/title>\n<meta name=\"description\" content=\"VibeThinker-3B scores 94.3 AIME26 and 80.2 LiveCodeBench v6. Small-model Spectrum-to-Signal training report from Weibo.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/i10x.ai\/news\/vibethinker-3b-small-model-verifiable-reasoning\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"VibeThinker-3B: Frontier Reasoning in a 3B Model - i10X News\" \/>\n<meta property=\"og:description\" content=\"VibeThinker-3B scores 94.3 AIME26 and 80.2 LiveCodeBench v6. Small-model Spectrum-to-Signal training report from Weibo.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/i10x.ai\/news\/vibethinker-3b-small-model-verifiable-reasoning\" \/>\n<meta property=\"og:site_name\" content=\"i10X News\" \/>\n<meta property=\"article:published_time\" content=\"2026-10-19T16:49:16+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-10-19T17:19:47+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/vibethinker-3b-small-model-verifiable-reasoning-title.webp\" \/>\n\t<meta property=\"og:image:width\" content=\"1344\" \/>\n\t<meta property=\"og:image:height\" content=\"768\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/webp\" \/>\n<meta name=\"author\" content=\"Christopher Ort\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@i10x_ai\" \/>\n<meta name=\"twitter:site\" content=\"@i10x_ai\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Christopher Ort\" \/>\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\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/vibethinker-3b-small-model-verifiable-reasoning#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/vibethinker-3b-small-model-verifiable-reasoning\"},\"author\":{\"name\":\"Christopher Ort\",\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#\\\/schema\\\/person\\\/d410bb7ee72febefca2c9c369939219a\"},\"headline\":\"A 3B Model Hits 94.3 on AIME26 and 80.2 on LiveCodeBench\",\"datePublished\":\"2026-10-19T16:49:16+00:00\",\"dateModified\":\"2026-10-19T17:19:47+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/vibethinker-3b-small-model-verifiable-reasoning\"},\"wordCount\":380,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/vibethinker-3b-small-model-verifiable-reasoning#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/vibethinker-3b-small-model-verifiable-reasoning-title.webp\",\"articleSection\":[\"Reasoning\",\"Studies\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/i10x.ai\\\/news\\\/vibethinker-3b-small-model-verifiable-reasoning#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/vibethinker-3b-small-model-verifiable-reasoning\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/vibethinker-3b-small-model-verifiable-reasoning\",\"name\":\"VibeThinker-3B: Frontier Reasoning in a 3B Model - i10X News\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/vibethinker-3b-small-model-verifiable-reasoning#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/vibethinker-3b-small-model-verifiable-reasoning#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/vibethinker-3b-small-model-verifiable-reasoning-title.webp\",\"datePublished\":\"2026-10-19T16:49:16+00:00\",\"dateModified\":\"2026-10-19T17:19:47+00:00\",\"description\":\"VibeThinker-3B scores 94.3 AIME26 and 80.2 LiveCodeBench v6. Small-model Spectrum-to-Signal training report from Weibo.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/vibethinker-3b-small-model-verifiable-reasoning#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/i10x.ai\\\/news\\\/vibethinker-3b-small-model-verifiable-reasoning\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/vibethinker-3b-small-model-verifiable-reasoning#primaryimage\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/vibethinker-3b-small-model-verifiable-reasoning-title.webp\",\"contentUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/vibethinker-3b-small-model-verifiable-reasoning-title.webp\",\"width\":1344,\"height\":768,\"caption\":\"Illustration: i10X\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/vibethinker-3b-small-model-verifiable-reasoning#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/news.i10x.ai\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"A 3B Model Hits 94.3 on AIME26 and 80.2 on LiveCodeBench\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#website\",\"url\":\"https:\\\/\\\/news.i10x.ai\\\/\",\"name\":\"i10X News\",\"description\":\"Stay updated with the latest news and announcements from i10X.\",\"publisher\":{\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/news.i10x.ai\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#organization\",\"name\":\"i10X\",\"url\":\"https:\\\/\\\/news.i10x.ai\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/i10x-logo-180.png\",\"contentUrl\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/i10x-logo-180.png\",\"width\":180,\"height\":180,\"caption\":\"i10X\"},\"image\":{\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/i10x_ai\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/i10x-ai\",\"https:\\\/\\\/instagram.com\\\/i10x.ai\",\"https:\\\/\\\/www.youtube.com\\\/@i10X_ai_official\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#\\\/schema\\\/person\\\/d410bb7ee72febefca2c9c369939219a\",\"name\":\"Christopher Ort\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/christopher-ort-192.webp\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/christopher-ort-192.webp\",\"contentUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/christopher-ort-192.webp\",\"caption\":\"Christopher Ort\"},\"description\":\"Christopher Ort handles SEO, AI agent workflows and PR & partnerships at i10x.ai, the all-in-one AI workspace built by i10X Global Pte. Ltd. in Singapore. He is a graduate of Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU). He is the author of \u201cThe Style Penalty\u201d, a study published on SSRN that analyses 1,576 evaluation decisions by four frontier AI models to show how AI-written CVs fare in automated hiring screens; the research has been covered by heise online and t3n.\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/author\\\/christopher-ort\",\"sameAs\":[\"https:\\\/\\\/i10x.ai\\\/blog\\\/author\\\/christopher-ort\"],\"worksFor\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#organization\"},\"alumniOf\":{\"@type\":\"EducationalOrganization\",\"name\":\"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU)\",\"url\":\"https:\\\/\\\/www.fau.eu\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"VibeThinker-3B: Frontier Reasoning in a 3B Model - i10X News","description":"VibeThinker-3B scores 94.3 AIME26 and 80.2 LiveCodeBench v6. Small-model Spectrum-to-Signal training report from Weibo.","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:\/\/i10x.ai\/news\/vibethinker-3b-small-model-verifiable-reasoning","og_locale":"en_US","og_type":"article","og_title":"VibeThinker-3B: Frontier Reasoning in a 3B Model - i10X News","og_description":"VibeThinker-3B scores 94.3 AIME26 and 80.2 LiveCodeBench v6. Small-model Spectrum-to-Signal training report from Weibo.","og_url":"https:\/\/i10x.ai\/news\/vibethinker-3b-small-model-verifiable-reasoning","og_site_name":"i10X News","article_published_time":"2026-10-19T16:49:16+00:00","article_modified_time":"2026-10-19T17:19:47+00:00","og_image":[{"width":1344,"height":768,"url":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/vibethinker-3b-small-model-verifiable-reasoning-title.webp","type":"image\/webp"}],"author":"Christopher Ort","twitter_card":"summary_large_image","twitter_creator":"@i10x_ai","twitter_site":"@i10x_ai","twitter_misc":{"Written by":"Christopher Ort","Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/i10x.ai\/news\/vibethinker-3b-small-model-verifiable-reasoning#article","isPartOf":{"@id":"https:\/\/i10x.ai\/news\/vibethinker-3b-small-model-verifiable-reasoning"},"author":{"name":"Christopher Ort","@id":"https:\/\/news.i10x.ai\/#\/schema\/person\/d410bb7ee72febefca2c9c369939219a"},"headline":"A 3B Model Hits 94.3 on AIME26 and 80.2 on LiveCodeBench","datePublished":"2026-10-19T16:49:16+00:00","dateModified":"2026-10-19T17:19:47+00:00","mainEntityOfPage":{"@id":"https:\/\/i10x.ai\/news\/vibethinker-3b-small-model-verifiable-reasoning"},"wordCount":380,"commentCount":0,"publisher":{"@id":"https:\/\/news.i10x.ai\/#organization"},"image":{"@id":"https:\/\/i10x.ai\/news\/vibethinker-3b-small-model-verifiable-reasoning#primaryimage"},"thumbnailUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/vibethinker-3b-small-model-verifiable-reasoning-title.webp","articleSection":["Reasoning","Studies"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/i10x.ai\/news\/vibethinker-3b-small-model-verifiable-reasoning#respond"]}]},{"@type":"WebPage","@id":"https:\/\/i10x.ai\/news\/vibethinker-3b-small-model-verifiable-reasoning","url":"https:\/\/i10x.ai\/news\/vibethinker-3b-small-model-verifiable-reasoning","name":"VibeThinker-3B: Frontier Reasoning in a 3B Model - i10X News","isPartOf":{"@id":"https:\/\/news.i10x.ai\/#website"},"primaryImageOfPage":{"@id":"https:\/\/i10x.ai\/news\/vibethinker-3b-small-model-verifiable-reasoning#primaryimage"},"image":{"@id":"https:\/\/i10x.ai\/news\/vibethinker-3b-small-model-verifiable-reasoning#primaryimage"},"thumbnailUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/vibethinker-3b-small-model-verifiable-reasoning-title.webp","datePublished":"2026-10-19T16:49:16+00:00","dateModified":"2026-10-19T17:19:47+00:00","description":"VibeThinker-3B scores 94.3 AIME26 and 80.2 LiveCodeBench v6. Small-model Spectrum-to-Signal training report from Weibo.","breadcrumb":{"@id":"https:\/\/i10x.ai\/news\/vibethinker-3b-small-model-verifiable-reasoning#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/i10x.ai\/news\/vibethinker-3b-small-model-verifiable-reasoning"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/i10x.ai\/news\/vibethinker-3b-small-model-verifiable-reasoning#primaryimage","url":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/vibethinker-3b-small-model-verifiable-reasoning-title.webp","contentUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/vibethinker-3b-small-model-verifiable-reasoning-title.webp","width":1344,"height":768,"caption":"Illustration: i10X"},{"@type":"BreadcrumbList","@id":"https:\/\/i10x.ai\/news\/vibethinker-3b-small-model-verifiable-reasoning#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/news.i10x.ai\/"},{"@type":"ListItem","position":2,"name":"A 3B Model Hits 94.3 on AIME26 and 80.2 on LiveCodeBench"}]},{"@type":"WebSite","@id":"https:\/\/news.i10x.ai\/#website","url":"https:\/\/news.i10x.ai\/","name":"i10X News","description":"Stay updated with the latest news and announcements from i10X.","publisher":{"@id":"https:\/\/news.i10x.ai\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/news.i10x.ai\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/news.i10x.ai\/#organization","name":"i10X","url":"https:\/\/news.i10x.ai\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/news.i10x.ai\/#\/schema\/logo\/image\/","url":"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/10\/i10x-logo-180.png","contentUrl":"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/10\/i10x-logo-180.png","width":180,"height":180,"caption":"i10X"},"image":{"@id":"https:\/\/news.i10x.ai\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/i10x_ai","https:\/\/www.linkedin.com\/company\/i10x-ai","https:\/\/instagram.com\/i10x.ai","https:\/\/www.youtube.com\/@i10X_ai_official"]},{"@type":"Person","@id":"https:\/\/news.i10x.ai\/#\/schema\/person\/d410bb7ee72febefca2c9c369939219a","name":"Christopher Ort","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/christopher-ort-192.webp","url":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/christopher-ort-192.webp","contentUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/christopher-ort-192.webp","caption":"Christopher Ort"},"description":"Christopher Ort handles SEO, AI agent workflows and PR & partnerships at i10x.ai, the all-in-one AI workspace built by i10X Global Pte. Ltd. in Singapore. He is a graduate of Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU). He is the author of \u201cThe Style Penalty\u201d, a study published on SSRN that analyses 1,576 evaluation decisions by four frontier AI models to show how AI-written CVs fare in automated hiring screens; the research has been covered by heise online and t3n.","url":"https:\/\/i10x.ai\/news\/author\/christopher-ort","sameAs":["https:\/\/i10x.ai\/blog\/author\/christopher-ort"],"worksFor":{"@id":"https:\/\/i10x.ai\/news\/#organization"},"alumniOf":{"@type":"EducationalOrganization","name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU)","url":"https:\/\/www.fau.eu"}}]}},"_links":{"self":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts\/6136","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/comments?post=6136"}],"version-history":[{"count":2,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts\/6136\/revisions"}],"predecessor-version":[{"id":6287,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts\/6136\/revisions\/6287"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/media\/6286"}],"wp:attachment":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/media?parent=6136"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/categories?post=6136"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/tags?post=6136"},{"taxonomy":"company","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/companies?post=6136"},{"taxonomy":"product","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/products?post=6136"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}