{"id":72688,"date":"2026-06-13T10:55:14","date_gmt":"2026-06-13T10:55:14","guid":{"rendered":"https:\/\/www.europesays.com\/ai\/72688\/"},"modified":"2026-06-13T10:55:14","modified_gmt":"2026-06-13T10:55:14","slug":"claude-fable-5-outpaces-gpt-5-5-by-13-points-on-frontiermaths-toughest-problems","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/ai\/72688\/","title":{"rendered":"Claude Fable 5 outpaces GPT-5.5 by 13 points on FrontierMath&#8217;s toughest problems"},"content":{"rendered":"<p>\t\t\t<a href=\"https:\/\/the-decoder.com\/author\/matthias-bastian\/\" class=\"w-6 h-6 relative rounded-full overflow-hidden shrink-0 bg-gray-400 block   exclude-from-pdf\" title=\"View all posts by Matthias Bastian\" rel=\"nofollow noopener\" target=\"_blank\"><br \/>\n\t\t\t\t<img loading=\"lazy\" alt=\"Matthias Bastian\" src=\"https:\/\/www.europesays.com\/ai\/wp-content\/uploads\/2026\/04\/avatar_matthias_bastian.jpg\"  class=\"avatar avatar-24 photo w-6 h-6 left-0 top-0 absolute\" height=\"24\" width=\"24\" decoding=\"async\"\/>\t\t\t<\/a><\/p>\n<p>Anthropic&#8217;s new model, Claude Fable 5, posts top scores on the FrontierMath benchmark.\u00a0According to\u00a0<a href=\"https:\/\/epoch.ai\/\" target=\"_blank\" rel=\"noopener noreferrer nofollow\">Epoch AI<\/a>, Fable 5 hits 87 percent accuracy on tiers 1 through 3 and 88 percent on the hardest tier 4 (v2).<\/p>\n<p><img fetchpriority=\"high\" decoding=\"async\" class=\"wp-image-36579 size-full\" src=\"https:\/\/www.europesays.com\/ai\/wp-content\/uploads\/2026\/06\/frontier_math_fable5.png\" alt=\"\" width=\"1024\" height=\"1280\"\/>Image: EpochAI<\/p>\n<p>Anthropic&#8217;s models are getting dramatically better at math in a short span of time. As recently as early 2026, predecessor model Opus 4.5 scored below 10 percent on tier 4. OpenAI&#8217;s GPT-5.5 reaches about 75 percent on the same tier, well behind Fable 5,\u00a0<a href=\"https:\/\/the-decoder.com\/openais-ipo-slips-as-altman-tells-staff-to-expect-a-public-offering-within-the-next-year\/\" target=\"_blank\" rel=\"noopener noreferrer nofollow\">although GPT-5.6 is already in the making<\/a>.<\/p>\n<p>All models were tested on Epoch AI&#8217;s standard scaffold with maximum reasoning effort. FrontierMath is widely considered one of the toughest benchmarks for AI math reasoning. These\u00a0<a href=\"https:\/\/the-decoder.com\/terence-tao-argues-ai-could-bring-division-of-labor-to-math-for-the-first-time-in-history\/\" target=\"_blank\" rel=\"noopener noreferrer nofollow\">math gains aren&#8217;t just in benchmarks<\/a>, real-world examples keep stacking up. Most recently, <a href=\"https:\/\/the-decoder.com\/openais-gpt-5-4-pro-reportedly-solves-a-longstanding-open-erdos-math-problem-in-under-two-hours\/\" target=\"_blank\" rel=\"noopener noreferrer nofollow\">an OpenAI model solved a longstanding Erd\u0151s problem<\/a>; so did\u00a0<a href=\"https:\/\/the-decoder.com\/claude-mythos-reportedly-solves-openais-landmark-erdos-problem-with-a-cute-simple-proof\/\" target=\"_blank\" rel=\"noopener noreferrer nofollow\">Claude Mythos<\/a>.<\/p>\n<p>\t\t\t\tAI News Without the Hype \u2013 Curated by Humans<\/p>\n<p>\n\t\t\t\t\tSubscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive &#8220;AI Radar&#8221; frontier report six times a year, full archive access, and access to our comment section.\t\t\t\t<\/p>\n<p>\t\t\t\t<a href=\"https:\/\/the-decoder.com\/subscription\/\" class=\"inline-block text-white bg-(--heise-primary) mt-3 hover:bg-blue-800 focus:ring-4 focus:outline-none focus:ring-blue-300 font-medium rounded-sm w-full sm:w-auto  pl-3 pr-3 py-2.5 text-center newsletter-submit-button hover:no-underline\" rel=\"nofollow noopener\" target=\"_blank\"><br \/>\n\t\t\t\t\tSubscribe now\t\t\t\t<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"Anthropic&#8217;s new model, Claude Fable 5, posts top scores on the FrontierMath benchmark.\u00a0According to\u00a0Epoch AI, Fable 5 hits&hellip;\n","protected":false},"author":2,"featured_media":21721,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[8],"tags":[53,3154,182,1785],"class_list":["post-72688","post","type-post","status-publish","format-standard","has-post-thumbnail","category-anthropic","tag-anthropic","tag-anthropic-claude","tag-claude","tag-math"],"_links":{"self":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/72688","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/comments?post=72688"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/72688\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media\/21721"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media?parent=72688"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/categories?post=72688"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/tags?post=72688"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}