{"id":36916,"date":"2025-06-07T12:52:18","date_gmt":"2025-06-07T04:52:18","guid":{"rendered":"https:\/\/www.1ai.net\/?p=36916"},"modified":"2025-06-07T12:52:18","modified_gmt":"2025-06-07T04:52:18","slug":"google-gemini-%e6%96%b0%e7%89%88%e7%99%bb%e9%a1%b6%e5%a4%a7%e6%a8%a1%e5%9e%8b%e7%ab%9e%e6%8a%80%e5%9c%ba","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/36916.html","title":{"rendered":"Google Gemini New Edition Tops Big Model Arena"},"content":{"rendered":"<p>A few days ago,<a href=\"https:\/\/www.1ai.net\/en\/tag\/google\" title=\"[View articles tagged with [Google]]\" target=\"_blank\" >Google<\/a> <a href=\"https:\/\/www.1ai.net\/en\/tag\/gemini\" title=\"[View articles tagged with [Gemini]]\" target=\"_blank\" >Gemini<\/a> 2.5 Pro announces the release of a new version \"Gemini 2.5 Pro(0605)\".<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-36917\" title=\"97143facj00sxgyu10012d000u000gwm\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2025\/06\/97143facj00sxgyu10012d000u000gwm.jpg\" alt=\"97143facj00sxgyu10012d000u000gwm\" width=\"1080\" height=\"608\" \/><\/p>\n<p>In terms of performance, the new version of Gemini 2.5 Pro performs better in tasks such as coding and reasoning:<\/p>\n<p>Surpassed OpenAI o3 with 21.6% in Humanity's Last Exam and topped the GPQA test with 86.4%.<\/p>\n<p>In the big model arena, the new version of Gemini 2.5 Pro maintains its lead in the Elo score, with a 24-point improvement over the (0506) version (to 1470 points).<\/p>\n<p>According to Google, the (0605) release is based on the (0506) release announced at this year's I\/O conference, and the new version is expected to be the official stable \"debut\" of Gemini 2.5 Pro.<\/p>\n<p>In addition, Google has improved the answers to the new version 2.5 Pro, which now provides more creative and better formatted responses.<\/p>","protected":false},"excerpt":{"rendered":"<p>Recently, Google Gemini 2.5 Pro announced the release of a new version \"Gemini 2.5 Pro(0605)\". In terms of performance, the new version of Gemini 2.5 Pro has stronger performance in code, reasoning and other tasks: in Humanity's Last Exam, it outperforms OpenAI o3 with a score of 21.6%; in GPQA test, it tops the list with a score of 86.4%. In the big model arena, the new version of Gemini 2.5 Pro maintains the lead with a 24-point increase in the Elo score compared to the (0506) version (1,470 points). According to Goo<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[436,308],"collection":[],"class_list":["post-36916","post","type-post","status-publish","format-standard","hentry","category-news","tag-gemini","tag-google"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/36916","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=36916"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/36916\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=36916"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=36916"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=36916"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=36916"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}