{"id":54184,"date":"2026-06-23T15:48:23","date_gmt":"2026-06-23T07:48:23","guid":{"rendered":"https:\/\/www.1ai.net\/?p=54184"},"modified":"2026-06-23T15:48:23","modified_gmt":"2026-06-23T07:48:23","slug":"sakana-ai-%e5%8f%91%e5%b8%83-fugu-ultra%ef%bc%8c%e6%80%a7%e8%83%bd%e5%af%b9%e6%a0%87-fable-5","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/54184.html","title":{"rendered":"Sakana AI release Fugu Ultra, performance against Fable 5"},"content":{"rendered":"<p>June 23rd news, yesterday<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e6%97%a5%e6%9c%ac\" title=\"_Other Organiser\" target=\"_blank\" >Japan<\/a> <a href=\"https:\/\/www.1ai.net\/en\/tag\/ai%e5%85%ac%e5%8f%b8\" title=\"[SEES ARTICLES WITH [AI] LABELS]\" target=\"_blank\" >AI Companies<\/a> <a href=\"https:\/\/www.1ai.net\/en\/tag\/sakana\" title=\"_Other Organiser\" target=\"_blank\" >Sakana<\/a> AI publishes Fugu, encapsulating multiple Agent programming systems as a single model API. Once the task is in place, it will decide which model to call, which steps to complete, whether to validate the results and whether to re-refer to itself\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-54185\" title=\"56c93d85j00th2qyi001d000u8m\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2026\/06\/56c93d85j00th2qyi001dd000u000d8m.jpg\" alt=\"56c93d85j00th2qyi001d000u8m\" width=\"1080\" height=\"476\" \/><\/p>\n<p>Fugu is divided into two versions: Fugu for daily coding, code review and interactive scenes, with emphasis on performance and delay balance; and Fugu Ultra for more in-depth expert Agent pool, for more difficult issues\u3002<\/p>\n<p>The official benchmark data show that Fugu Ultra scored 73.7 points on SWE Bench Pro, 69.2 points above Opus 4.8; 50.0 points on HLE, slightly above 49.8 points on Opus 4.8\u3002<\/p>\n<p>The official claim that Fugu Ultra is on the same level as Fable 5 and Mythos Preview. The news of June 23rd<\/p>","protected":false},"excerpt":{"rendered":"<p>News from June 23, yesterday, Japan ' s AI company Sakana AI published Fugu, encapsulating the multiAgent layout system as a single model API. Once the task is in place, it will decide which model to call, which steps to complete, whether to validate the results and whether to re-refer to itself. Fugu is divided into two versions: Fugu for daily coding, code review and interactive scenes, with emphasis on performance and delay balance; and Fugu Ultra for more in-depth expert Agent pool, for more difficult issues. Official benchmark data shows that Fugu Ultra scored 73.7 points on SWE Bench Pro, higher than Opus 4.8<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[155,3683,226],"collection":[],"class_list":["post-54184","post","type-post","status-publish","format-standard","hentry","category-news","tag-ai","tag-sakana","tag-226"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/54184","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=54184"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/54184\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=54184"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=54184"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=54184"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=54184"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}