{"id":125385,"date":"2024-09-13T10:44:17","date_gmt":"2024-09-13T01:44:17","guid":{"rendered":"https:\/\/softantenna.com\/blog\/?p=125385"},"modified":"2024-09-13T10:44:17","modified_gmt":"2024-09-13T01:44:17","slug":"openai-o1","status":"publish","type":"post","link":"https:\/\/softantenna.com\/blog\/openai-o1\/","title":{"rendered":"\u7269\u7406\u5b66\u3001\u79d1\u5b66\u3001\u751f\u7269\u5b66\u3001\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u306a\u3069\u3088\u308a\u8907\u96d1\u306a\u30bf\u30b9\u30af\u306b\u5bfe\u5fdc\u3057\u305f\u6700\u65b0\u30e2\u30c7\u30eb\u300cOpenAI o1\u300d\u304c\u7206\u8a95"},"content":{"rendered":"

\"1609914495<\/p>\n

OpenAI\u306f9\u670812\u65e5(\u73fe\u5730\u6642\u9593)\u3001\u6700\u65b0\u306eAI\u30e2\u30c7\u30eb\u300cOpenAI o1\u300d\u3092\u767a\u8868<\/a>\u3057\u307e\u3057\u305f\u3002<\/p>\n

OpenAI\u306f\u30d6\u30ed\u30b0\u306e\u6295\u7a3f\u3067\u3001\u65b0\u3057\u3044\u30e2\u30c7\u30eb\u306e\u6a5f\u80fd\u3092\u8aac\u660e\u3057\u3066\u3044\u307e\u3059\u3002\u4ee5\u524d\u300cStrawberry\u300d\u3068\u3044\u3046\u30b3\u30fc\u30c9\u30cd\u30fc\u30e0\u3067\u5831\u544a\u3055\u308c\u3066\u3044\u305f\u6a5f\u80fd\u304c\u5229\u7528\u3067\u304d\u3001\u540c\u793e\u306f\u65b0\u30e2\u30c7\u30eb\u304c\u300c\u53cd\u5fdc\u3059\u308b\u524d\u306b\u8003\u3048\u308b\u6642\u9593\u3092\u5897\u3084\u3059\u300d\u305f\u3081\u306b\u4f5c\u3089\u308c\u305f\u3068\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n

OpenAI o1\u306f\u3001\u7269\u7406\u5b66\u3001\u5316\u5b66\u3001\u751f\u7269\u5b66\u3084\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u306a\u3069\u3001\u3088\u308a\u8907\u96d1\u306a\u30bf\u30b9\u30af\u3084\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u306b\u53d6\u308a\u7d44\u3080\u3053\u3068\u304c\u76ee\u6a19\u3060\u3068\u3055\u308c\u3066\u3044\u307e\u3059:<\/p>\n

\nIn our tests, the next model update performs similarly to PhD students on challenging benchmark tasks in physics, chemistry, and biology. We also found that it excels in math and coding. In a qualifying exam for the International Mathematics Olympiad (IMO), GPT-4o correctly solved only 13% of problems, while the reasoning model scored 83%. Their coding abilities were evaluated in contests and reached the 89th percentile in Codeforces competitions.<\/p>\n

\u6211\u3005\u306e\u30c6\u30b9\u30c8\u3067\u306f\u3001\u6b21\u671f\u30e2\u30c7\u30eb\u306e\u30a2\u30c3\u30d7\u30c7\u30fc\u30c8\u306f\u3001\u7269\u7406\u5b66\u3001\u5316\u5b66\u3001\u751f\u7269\u5b66\u306e\u96e3\u6613\u5ea6\u306e\u9ad8\u3044\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u30bf\u30b9\u30af\u306b\u304a\u3044\u3066\u3001\u535a\u58eb\u8ab2\u7a0b\u306e\u5b66\u751f\u3068\u540c\u69d8\u306e\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u3092\u793a\u3057\u307e\u3057\u305f\u3002\u307e\u305f\u3001\u6570\u5b66\u3084\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u306b\u3082\u512a\u308c\u3066\u3044\u308b\u3053\u3068\u304c\u308f\u304b\u308a\u307e\u3057\u305f\u3002\u56fd\u969b\u6570\u5b66\u30aa\u30ea\u30f3\u30d4\u30c3\u30af\uff08IMO\uff09\u306e\u4e88\u9078\u8a66\u9a13\u3067\u3001GPT-4o\u306f\u554f\u984c\u306e13\uff05\u3057\u304b\u6b63\u3057\u304f\u89e3\u3051\u306a\u304b\u3063\u305f\u306e\u306b\u5bfe\u3057\u3001\u63a8\u8ad6\u30e2\u30c7\u30eb\u306f83\uff05\u306e\u30b9\u30b3\u30a2\u3092\u51fa\u3057\u305f\u3002\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u80fd\u529b\u306f\u30b3\u30f3\u30c6\u30b9\u30c8\u3067\u8a55\u4fa1\u3055\u308c\u3001Codeforces\u30b3\u30f3\u30c6\u30b9\u30c8\u3067\u306f89\u30d1\u30fc\u30bb\u30f3\u30bf\u30a4\u30eb\u306b\u9054\u3057\u305f\u3002\n<\/p><\/blockquote>\n

\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u80fd\u529b\u306b\u3064\u3044\u3066\u306f\u3001Codeforces\u30b3\u30f3\u30c6\u30b9\u30c8\u3067\u306f89\u30d1\u30fc\u30bb\u30f3\u30bf\u30a4\u30eb\u306b\u9054\u3057\u305f\u3068\u306e\u3053\u3068\u3002<\/p>\n

OpenAI o1\u306f\u3001Web\u4e0a\u306e\u60c5\u5831\u3092\u691c\u7d22\u3057\u305f\u308a\u3001\u30a2\u30c3\u30d7\u30ed\u30fc\u30c9\u3055\u308c\u305f\u753b\u50cf\u3084\u305d\u306e\u4ed6\u306e\u30d5\u30a1\u30a4\u30eb\u3092\u30c1\u30a7\u30c3\u30af\u3059\u308b\u3068\u3044\u3063\u305f\u3001ChatGPT LLM\u304c\u3067\u304d\u308b\u3053\u3068\u306e\u3044\u304f\u3064\u304b\u306f\u3067\u304d\u307e\u305b\u3093\u3002\u3057\u304b\u3057\u3001\u540c\u793e\u306f\u3053\u306e\u65b0\u3057\u3044\u30e2\u30c7\u30eb\u304c\u751f\u6210AI\u306e\u5927\u304d\u306a\u524d\u9032\u3067\u3042\u308b\u3068\u3057\u3001\u30e2\u30c7\u30eb\u3092 \u300c\u30ab\u30a6\u30f3\u30bf\u30fc\u30921\u306b\u623b\u3059 \u300d\u3092\u610f\u5473\u3059\u308bOpenAI o1\u3068\u540d\u4ed8\u3051\u3066\u3044\u307e\u3059\u3002<\/p>\n

\u30e1\u30a4\u30f3\u306eOpenAI o1\u30e2\u30c7\u30eb\u306b\u52a0\u3048\u3066\u3001\u540c\u793e\u306fOpenAI o1-mini\u3082\u767a\u8868\u3057\u3066\u3044\u307e\u3059\u3002\u3053\u3061\u3089\u306f\u3001\u3088\u308a\u901f\u304f\u3001\u3088\u308a\u5b89\u304f\u4f7f\u3048\u308b\u3088\u3046\u306b\u8a2d\u8a08\u3055\u308c\u3066\u304a\u308a\u3001\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u4f5c\u696d\u306e\u652f\u63f4\u306b\u7279\u5316\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n

ChatGPT Plus\u3068ChatGPT Team\u306e\u5951\u7d04\u8005\u306f\u3001\u4eca\u65e5\u304b\u3089\u65b0\u3057\u3044OpenAI o1\u30e2\u30c7\u30eb\u306b\u30a2\u30af\u30bb\u30b9\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002ChatGPT Enterprise\u3068ChatGPT Edu\u306e\u52a0\u5165\u8005\u306f\u6765\u9031\u304b\u3089\u5229\u7528\u53ef\u80fd\u306b\u306a\u308a\u307e\u3059\u3002\u8fd1\u3044\u5c06\u6765\u3001\u7121\u6599\u306eChatGPT\u30e6\u30fc\u30b6\u30fc\u3082OpenAI o1-mini\u30e2\u30c7\u30eb\u306b\u30a2\u30af\u30bb\u30b9\u3067\u304d\u308b\u3088\u3046\u306b\u306a\u308a\u307e\u3059\u3002<\/p>\n

[via Neowin<\/a>]<\/p>\n","protected":false},"excerpt":{"rendered":"

OpenAI\u306f9\u670812\u65e5(\u73fe\u5730\u6642\u9593)\u3001\u6700\u65b0\u306eAI\u30e2\u30c7\u30eb\u300cOpenAI o1\u300d\u3092\u767a\u8868\u3057\u307e\u3057\u305f\u3002 OpenAI\u306f\u30d6\u30ed\u30b0\u306e\u6295\u7a3f\u3067\u3001\u65b0\u3057\u3044\u30e2\u30c7\u30eb\u306e\u6a5f\u80fd\u3092\u8aac\u660e\u3057\u3066\u3044\u307e\u3059\u3002\u4ee5\u524d\u300cStrawberry\u300d\u3068\u3044\u3046\u30b3\u30fc\u30c9\u30cd\u30fc\u30e0\u3067\u5831\u544a\u3055\u308c\u3066\u3044 […]<\/p>\n","protected":false},"author":2,"featured_media":125384,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"aside","meta":{"swell_btn_cv_data":"","footnotes":""},"categories":[66],"tags":[4620],"class_list":["post-125385","post","type-post","status-publish","format-aside","has-post-thumbnail","hentry","category-webservice","tag-openai","post_format-post-format-aside"],"_links":{"self":[{"href":"https:\/\/softantenna.com\/blog\/wp-json\/wp\/v2\/posts\/125385","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/softantenna.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/softantenna.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/softantenna.com\/blog\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/softantenna.com\/blog\/wp-json\/wp\/v2\/comments?post=125385"}],"version-history":[{"count":0,"href":"https:\/\/softantenna.com\/blog\/wp-json\/wp\/v2\/posts\/125385\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/softantenna.com\/blog\/wp-json\/wp\/v2\/media\/125384"}],"wp:attachment":[{"href":"https:\/\/softantenna.com\/blog\/wp-json\/wp\/v2\/media?parent=125385"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/softantenna.com\/blog\/wp-json\/wp\/v2\/categories?post=125385"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/softantenna.com\/blog\/wp-json\/wp\/v2\/tags?post=125385"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}