{"id":544,"date":"2026-07-23T20:02:38","date_gmt":"2026-07-23T11:02:38","guid":{"rendered":"https:\/\/www.wetch.co.jp\/ai\/?p=544"},"modified":"2026-07-23T20:02:38","modified_gmt":"2026-07-23T11:02:38","slug":"%e3%82%82%e3%81%ae%e3%81%95%e3%81%97%e3%81%8c%e6%ba%b6%e3%81%91%e3%81%a6%e3%81%84%e3%81%8f%e2%80%95%e2%80%95%e3%83%99%e3%83%b3%e3%83%81%e3%83%9e%e3%83%bc%e3%82%af%e9%a3%bd%e5%92%8c%e3%81%ae%e6%99%82","status":"publish","type":"post","link":"https:\/\/www.wetch.co.jp\/ai\/2026\/07\/23\/%e3%82%82%e3%81%ae%e3%81%95%e3%81%97%e3%81%8c%e6%ba%b6%e3%81%91%e3%81%a6%e3%81%84%e3%81%8f%e2%80%95%e2%80%95%e3%83%99%e3%83%b3%e3%83%81%e3%83%9e%e3%83%bc%e3%82%af%e9%a3%bd%e5%92%8c%e3%81%ae%e6%99%82\/","title":{"rendered":"\u3082\u306e\u3055\u3057\u304c\u6eb6\u3051\u3066\u3044\u304f\u2015\u2015\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u98fd\u548c\u306e\u6642\u4ee3\u306b\u3001AI\u306e\u5b9f\u529b\u3092\u3069\u3046\u6e2c\u308b\u304b"},"content":{"rendered":"<p><em>\u65b0\u3057\u3044\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u304c\u767a\u8868\u3055\u308c\u308b\u305f\u3073\u306b\u3001\u6570\u304b\u6708\u306e\u3046\u3061\u306b\u4e3b\u8981\u30e2\u30c7\u30eb\u304c\u8ed2\u4e26\u307f\u9ad8\u5f97\u70b9\u3092\u53e9\u304d\u51fa\u3057\u3001\u300c\u3082\u3046\u5dee\u304c\u3064\u304b\u306a\u3044\u300d\u3082\u306e\u3055\u3057\u306b\u306a\u3063\u3066\u3044\u304f\u2015\u2015\u305d\u3093\u306a\u5149\u666f\u304c2026\u5e74\u306b\u306a\u3063\u3066\u3059\u3063\u304b\u308a\u898b\u6163\u308c\u305f\u3082\u306e\u306b\u306a\u3063\u305f\u3002\u6570\u5024\u4e0a\u306f\u300c\u8ce2\u304f\u306a\u3063\u305f\u300d\u306f\u305a\u306eAI\u3092\u3001\u79c1\u305f\u3061\u306f\u4e00\u4f53\u4f55\u3067\u6e2c\u308c\u3070\u3044\u3044\u306e\u304b\u3002\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u98fd\u548c\u3068\u3044\u3046\u73fe\u8c61\u3092\u624b\u304c\u304b\u308a\u306b\u3001\u8a55\u4fa1\u3068\u3044\u3046\u5730\u5473\u3060\u304c\u907f\u3051\u3066\u901a\u308c\u306a\u3044\u30c6\u30fc\u30de\u3092\u8003\u3048\u3066\u307f\u305f\u3044\u3002<\/em><\/p>\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/www.wetch.co.jp\/ai\/wp-content\/uploads\/2026\/06\/ill-benchmark.png\" alt=\"\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3068AI\u8a55\u4fa1\u306e\u30a4\u30e1\u30fc\u30b8\u30a4\u30e9\u30b9\u30c8\"\/><\/figure>\n<h2>\u300c\u6570\u5e74\u3082\u3064\u306f\u305a\u306e\u30c6\u30b9\u30c8\u300d\u304c\u6570\u304b\u6708\u3067\u9665\u843d\u3059\u308b<\/h2>\n<p><a href=\"https:\/\/hai.stanford.edu\/ai-index\/2026-ai-index-report\" target=\"_blank\" rel=\"noopener\">Stanford HAI\u306e2026\u5e74\u7248AI Index\u30ec\u30dd\u30fc\u30c8<\/a>\u306f\u3001\u3053\u306e\u72b6\u6cc1\u3092\u7aef\u7684\u306b\u8a00\u3044\u5f53\u3066\u3066\u3044\u308b\u3002\u4f55\u5e74\u3082\u7814\u7a76\u8005\u3092\u60a9\u307e\u305b\u308b\u306f\u305a\u3060\u3063\u305f\u8a55\u4fa1\u7528\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u304c\u3001\u308f\u305a\u304b\u6570\u304b\u6708\u3067\u300c\u98fd\u548c\u300d\u3057\u3066\u3057\u307e\u3046\u3068\u3044\u3046\u306e\u3060\u3002<a href=\"https:\/\/hai.stanford.edu\/ai-index\/2026-ai-index-report\/technical-performance\" target=\"_blank\" rel=\"noopener\">Technical Performance\u306e\u7ae0<\/a>\u3067\u3082\u3001\u4e3b\u8981\u306a\u80fd\u529b\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u306e\u591a\u304f\u3067\u30c8\u30c3\u30d7\u30e2\u30c7\u30eb\u540c\u58eb\u306e\u30b9\u30b3\u30a2\u5dee\u304c\u307b\u3068\u3093\u3069\u306a\u304f\u306a\u308a\u3001\u9806\u4f4d\u3092\u6c7a\u3081\u3066\u3044\u308b\u306e\u304c\u8aa4\u5dee\u306e\u7bc4\u56f2\u5185\u306e\u5dee\u3060\u3051\u3001\u3068\u3044\u3046\u30b1\u30fc\u30b9\u304c\u76ee\u7acb\u3064\u3068\u6307\u6458\u3055\u308c\u3066\u3044\u308b\u3002<\/p>\n<p>\u3053\u308c\u306f\u4f53\u611f\u306e\u8a71\u3067\u306f\u306a\u304f\u3001\u5b9a\u91cf\u7684\u306b\u3082\u88cf\u4ed8\u3051\u3089\u308c\u3064\u3064\u3042\u308b\u30022026\u5e74\u306b\u516c\u958b\u3055\u308c\u305f\u7814\u7a76<a href=\"https:\/\/arxiv.org\/html\/2602.16763v3\" target=\"_blank\" rel=\"noopener\">\u300cWhen AI Benchmarks Plateau\u300d<\/a>\u306f\u300160\u500b\u306e\u8a00\u8a9e\u30e2\u30c7\u30eb\u5411\u3051\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3092\u5206\u6790\u3057\u3001\u305d\u306e\u7d04\u534a\u6570\u304c\u3059\u3067\u306b\u300c\u98fd\u548c\u300d\u306e\u5146\u5019\u3092\u793a\u3057\u3066\u3044\u308b\u3068\u5831\u544a\u3057\u305f\u3002\u3057\u304b\u3082\u98fd\u548c\u304c\u9032\u307f\u3084\u3059\u3044\u306e\u306f\u516c\u958b\u304b\u3089\u6642\u9593\u304c\u7d4c\u3063\u305f\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u3001\u8208\u5473\u6df1\u3044\u3053\u3068\u306b\u300c\u30c6\u30b9\u30c8\u30c7\u30fc\u30bf\u304c\u975e\u516c\u958b\u304b\u3069\u3046\u304b\u300d\u3088\u308a\u3082\u300c\u5c02\u9580\u5bb6\u304c\u3069\u308c\u3060\u3051\u4e01\u5be7\u306b\u554f\u984c\u3092\u4f5c\u308a\u8fbc\u3093\u3067\u3044\u308b\u304b\u300d\u306e\u65b9\u304c\u3001\u5bff\u547d\u3092\u5de6\u53f3\u3059\u308b\u8981\u56e0\u3060\u3063\u305f\u3068\u3044\u3046\u3002<\/p>\n<h2>\u4f55\u304c\u8d77\u304d\u3066\u3044\u308b\u306e\u304b\u2015\u2015\u5177\u4f53\u4f8b\u3067\u898b\u308b\u300c\u982d\u6253\u3061\u300d<\/h2>\n<p>\u5178\u578b\u4f8b\u3092\u6319\u3052\u308b\u3068\u308f\u304b\u308a\u3084\u3059\u3044\u3002MMLU\u306e\u3088\u3046\u306a\u6c4e\u7528\u77e5\u8b58\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u306f\u3059\u3067\u306b\u6570\u5e74\u524d\u304b\u3089\u4e0a\u4f4d\u30e2\u30c7\u30eb\u304c\u5929\u4e95\u4ed8\u8fd1\u306b\u5f35\u308a\u4ed8\u304d\u3001\u8b58\u5225\u529b\u3092\u5931\u3063\u3066\u3044\u308b\u3002\u56f3\u5f62\u63a8\u8ad6\u306eARC-AGI\u3082\u521d\u4ee3\u304c\u307b\u307c\u89e3\u304b\u308c\u305f\u305f\u3081\u3001\u3088\u308a\u96e3\u3057\u3044\u300cARC-AGI-2\u300d\u3078\u306e\u5207\u308a\u66ff\u3048\u304c\u9032\u3093\u3060\u3002\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u9818\u57df\u306e<a href=\"https:\/\/www.swebench.com\/\" target=\"_blank\" rel=\"noopener\">SWE-bench<\/a>\u3082\u540c\u69d8\u3067\u3001\u7d20\u70b9\u3067\u306e\u6bd4\u8f03\u304c\u96e3\u3057\u304f\u306a\u308b\u305f\u3073\u306b\u300cVerified\u300d\u300chardened\u300d\u3068\u3044\u3063\u305f\u5f37\u5316\u7248\u304c\u77e2\u7d99\u304e\u65e9\u306b\u6295\u5165\u3055\u308c\u3066\u3044\u308b\u3002<\/p>\n<table>\n<thead>\n<tr>\n<th>\u30d9\u30f3\u30c1\u30de\u30fc\u30af<\/th>\n<th>\u5bfe\u8c61\u9818\u57df<\/th>\n<th>\u98fd\u548c\u5f8c\u306e\u5bfe\u5fdc<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>MMLU<\/td>\n<td>\u6c4e\u7528\u77e5\u8b58\u30fb\u63a8\u8ad6<\/td>\n<td>\u4e0a\u4f4d\u30e2\u30c7\u30eb\u304c\u5929\u4e95\u4ed8\u8fd1\u306b\u5bc6\u96c6\u3001\u8b58\u5225\u529b\u304c\u4f4e\u4e0b<\/td>\n<\/tr>\n<tr>\n<td>ARC-AGI<\/td>\n<td>\u62bd\u8c61\u7684\u63a8\u8ad6<\/td>\n<td>\u521d\u4ee3\u304c\u5b9f\u8cea\u89e3\u6c7a\u3001\u3088\u308a\u96e3\u3057\u3044\u5f8c\u7d99\u7248\u3078\u79fb\u884c<\/td>\n<\/tr>\n<tr>\n<td>SWE-bench<\/td>\n<td>\u5b9f\u52d9\u7684\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0<\/td>\n<td>Verified\u7248\u306a\u3069\u300c\u6c5a\u67d3\u3055\u308c\u306b\u304f\u3044\u300d\u5f37\u5316\u7248\u3092\u968f\u6642\u8ffd\u52a0<\/td>\n<\/tr>\n<tr>\n<td>GPQA<\/td>\n<td>\u5927\u5b66\u9662\u30ec\u30d9\u30eb\u306e\u5c02\u9580\u77e5\u8b58<\/td>\n<td>\u30c8\u30c3\u30d7\u30e2\u30c7\u30eb\u304c9\u5272\u8d85\u306b\u5230\u9054\u3057\u5dee\u304c\u3064\u304d\u306b\u304f\u3044<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>\u8981\u3059\u308b\u306b\u300c\u9759\u7684\u306a\u554f\u984c\u96c6\u3092\u4f5c\u3063\u3066\u3001\u305d\u308c\u3092\u4f55\u5e74\u3082\u4f7f\u3044\u56de\u3059\u300d\u3068\u3044\u3046\u8a55\u4fa1\u306e\u578b\u305d\u306e\u3082\u306e\u304c\u3001AI\u306e\u9032\u6b69\u901f\u5ea6\u306b\u8ffd\u3044\u3064\u3051\u306a\u304f\u306a\u3063\u3066\u3044\u308b\u3002<\/p>\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/www.wetch.co.jp\/ai\/wp-content\/uploads\/2026\/07\/photo-30.jpg\" alt=\"\u30e1\u30b8\u30e3\u30fc\u3067\u9577\u3055\u3092\u6e2c\u308b\u69d8\u5b50\"\/><figcaption><small>Photo: <a href=\"https:\/\/www.flickr.com\/photos\/73175123@N02\/6900292993\" target=\"_blank\" rel=\"noopener\">\u2665 jules<\/a> \/ CC BY-SA 2.0\uff08Openverse\u7d4c\u7531\uff09<\/small><\/figcaption><\/figure>\n<h2>\u6b63\u7b54\u7387\u304b\u3089\u300c\u3069\u308c\u3060\u3051\u9577\u304f\u4efb\u305b\u3089\u308c\u308b\u304b\u300d\u3078<\/h2>\n<p>\u9759\u7684\u306a\u30c6\u30b9\u30c8\u306e\u9650\u754c\u306b\u5bfe\u3057\u3001\u3044\u304f\u3064\u304b\u306e\u7814\u7a76\u6a5f\u95a2\u306f\u6e2c\u308b\u8ef8\u305d\u306e\u3082\u306e\u3092\u5909\u3048\u59cb\u3081\u305f\u3002\u4ee3\u8868\u4f8b\u304cAI\u5b89\u5168\u6027\u7814\u7a76\u56e3\u4f53<a href=\"https:\/\/metr.org\/\" target=\"_blank\" rel=\"noopener\">METR<\/a>\u306b\u3088\u308b\u300c\u30bf\u30a4\u30e0\u30db\u30e9\u30a4\u30ba\u30f3\u300d\u3068\u3044\u3046\u6307\u6a19\u3060\u3002<a href=\"https:\/\/metr.org\/blog\/2025-03-19-measuring-ai-ability-to-complete-long-tasks\" target=\"_blank\" rel=\"noopener\">2025\u5e74\u306b\u767a\u8868\u3055\u308c\u305f\u624b\u6cd5<\/a>\u3067\u306f\u3001\u30e2\u30c7\u30eb\u306e\u5b9f\u529b\u3092\u300c\u6b63\u7b54\u7387\u300d\u3067\u306f\u306a\u304f\u300c\u4eba\u9593\u63db\u7b97\u3067\u4f55\u6642\u9593\u304b\u304b\u308b\u4f5c\u696d\u3092\u300150%\u306e\u6210\u529f\u7387\u3067\u81ea\u5f8b\u7684\u306b\u3053\u306a\u305b\u308b\u304b\u300d\u3067\u8868\u3059\u3002\u3053\u306e\u300c\u4f5c\u696d\u6642\u9593\u306e\u9577\u3055\u300d\u306f\u3001\u516c\u958b\u5f53\u521d\u304b\u3089\u304a\u3088\u305d7\u304b\u6708\u3054\u3068\u306b\u500d\u5897\u3059\u308b\u30da\u30fc\u30b9\u3067\u4f38\u3073\u7d9a\u3051\u3066\u304a\u308a\u3001<a href=\"https:\/\/metr.org\/blog\/2026-1-29-time-horizon-1-1\" target=\"_blank\" rel=\"noopener\">2026\u5e741\u6708\u306e\u66f4\u65b0\u7248\uff08TH1.1\uff09<\/a>\u3067\u3082\u307b\u307c\u540c\u69d8\u306e\u50be\u5411\u304c\u78ba\u8a8d\u3055\u308c\u3066\u3044\u308b\u3002\u6b63\u7b54\u7387\u3068\u3044\u3046\u300c\u70b9\u300d\u3067\u306f\u306a\u304f\u3001\u81ea\u5f8b\u7684\u306b\u4efb\u305b\u3089\u308c\u308b\u4f5c\u696d\u306e\u300c\u9577\u3055\u300d\u3068\u3044\u3046\u6642\u9593\u8ef8\u306b\u7f6e\u304d\u63db\u3048\u308b\u3053\u3068\u3067\u3001\u30d5\u30ed\u30f3\u30c6\u30a3\u30a2\u30e2\u30c7\u30eb\u540c\u58eb\u306e\u5b9f\u8cea\u7684\u306a\u5dee\u3092\u53ef\u8996\u5316\u3057\u3088\u3046\u3068\u3044\u3046\u767a\u60f3\u3060\u3002<\/p>\n<p>\u3082\u3046\u4e00\u3064\u306e\u6d41\u308c\u304c\u3001\u4eba\u9593\u306e\u597d\u307f\u8a55\u4fa1\u3092\u30ea\u30a2\u30eb\u30bf\u30a4\u30e0\u306b\u96c6\u3081\u7d9a\u3051\u308b\u30a2\u30ea\u30fc\u30ca\u5f62\u5f0f\u3060\u3002\u3082\u3068\u3082\u3068<a href=\"https:\/\/arena.ai\/\" target=\"_blank\" rel=\"noopener\">Arena<\/a>\u306fUC Berkeley\u306eSky Computing Lab\u304c2023\u5e74\u306b\u59cb\u3081\u305f\u7814\u7a76\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u300cChatbot Arena\u300d\u3067\u3001\u533f\u540d\u306e2\u30e2\u30c7\u30eb\u5bfe\u6226\u3092\u5927\u91cf\u306e\u30e6\u30fc\u30b6\u30fc\u306b\u6295\u7968\u3057\u3066\u3082\u3089\u3044\u3001Elo\u30ec\u30fc\u30c6\u30a3\u30f3\u30b0\u3067\u30e9\u30f3\u30ad\u30f3\u30b0\u3092\u4f5c\u308b\u4ed5\u7d44\u307f\u3060\u3063\u305f\u30022026\u5e741\u6708\u306b\u306f\u793e\u540d\u30fb\u30b5\u30fc\u30d3\u30b9\u540d\u3092\u300cLMArena\u300d\u304b\u3089\u73fe\u5728\u306e\u300cArena\u300d\u3078\u3068\u6539\u79f0\u3057\u3001\u5546\u696d\u5316\u3082\u9032\u3093\u3067\u3044\u308b\u3002\u9759\u7684\u306a\u554f\u984c\u96c6\u3068\u9055\u3063\u3066\u6bcd\u96c6\u56e3\u306e\u6295\u7968\u304c\u7d76\u3048\u305a\u66f4\u65b0\u3055\u308c\u308b\u5206\u3001\u5358\u7d14\u306a\u6697\u8a18\u3084\u904e\u5b66\u7fd2\u306b\u5f37\u3044\u3068\u3055\u308c\u308b\u4e00\u65b9\u3001\u4e07\u80fd\u3067\u306f\u306a\u3044\u3002NeurIPS 2025\u3067\u767a\u8868\u3055\u308c\u305f<a href=\"https:\/\/arxiv.org\/pdf\/2504.20879\" target=\"_blank\" rel=\"noopener\">\u300cThe Leaderboard Illusion\u300d<\/a>\u3068\u3044\u3046\u8ad6\u6587\u306f\u3001\u4e00\u90e8\u306e\u5927\u624b\u30d7\u30ed\u30d0\u30a4\u30c0\u30fc\u304c\u975e\u516c\u958b\u306e\u30d7\u30e9\u30a4\u30d9\u30fc\u30c8\u30c6\u30b9\u30c8\u3067\u8907\u6570\u306e\u30e2\u30c7\u30eb\u4e9c\u7a2e\u3092\u8a66\u3057\u3001\u90fd\u5408\u306e\u826f\u3044\u30b9\u30b3\u30a2\u3060\u3051\u3092\u516c\u958b\u3067\u304d\u308b\u69cb\u9020\u3084\u3001\u5bfe\u6226\u983b\u5ea6\u30fb\u30c7\u30fc\u30bf\u30a2\u30af\u30bb\u30b9\u91cf\u306b\u5927\u304d\u306a\u504f\u308a\u304c\u3042\u308b\u3053\u3068\u3092\u6307\u6458\u3057\u305f\u3002\u4eba\u9593\u306e\u6295\u7968\u306b\u57fa\u3065\u304f\u8a55\u4fa1\u3067\u3042\u3063\u3066\u3082\u3001\u904b\u7528\u306e\u900f\u660e\u6027\u6b21\u7b2c\u3067\u3086\u304c\u307f\u304c\u751f\u3058\u3046\u308b\u3068\u3044\u3046\u6559\u8a13\u3060\u3002<\/p>\n<h2>\u5b9f\u52d9\u3067\u6c17\u3092\u3064\u3051\u305f\u3044\u3053\u3068<\/h2>\n<p>\u3067\u306f\u30e2\u30c7\u30eb\u9078\u5b9a\u3084\u30c4\u30fc\u30eb\u5c0e\u5165\u306e\u73fe\u5834\u3067\u306f\u3001\u3053\u306e\u72b6\u6cc1\u306b\u3069\u3046\u5411\u304d\u5408\u3048\u3070\u3088\u3044\u304b\u3002\u30dd\u30a4\u30f3\u30c8\u306f\u5927\u304d\u304f3\u3064\u3042\u308b\u3002<\/p>\n<ul>\n<li><strong>\u5358\u4e00\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u30b9\u30b3\u30a2\u3092\u9d5c\u5451\u307f\u306b\u3057\u306a\u3044<\/strong>\u3002\u7279\u306b\u767a\u8868\u76f4\u5f8c\u306e\u300c\u6e80\u70b9\u8fd1\u3044\u300d\u7d50\u679c\u306f\u3001\u98fd\u548c\u6e08\u307f\u304b\u3001\u6c5a\u67d3(\u5b66\u7fd2\u30c7\u30fc\u30bf\u3078\u306e\u6df7\u5165)\u306e\u53ef\u80fd\u6027\u3092\u7591\u3046\u4fa1\u5024\u304c\u3042\u308b\u3002<\/li>\n<li><strong>\u8907\u6570\u306e\u7269\u5dee\u3057\u3092\u7d44\u307f\u5408\u308f\u305b\u3066\u898b\u308b<\/strong>\u3002\u9759\u7684\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u30fb\u30bf\u30a4\u30e0\u30db\u30e9\u30a4\u30ba\u30f3\u306e\u3088\u3046\u306a\u81ea\u5f8b\u6027\u306e\u6307\u6a19\u30fbArena\u306e\u3088\u3046\u306a\u4eba\u9593\u8a55\u4fa1\u3092\u6a2a\u65ad\u7684\u306b\u78ba\u8a8d\u3059\u308b\u3068\u3001\u5358\u767a\u306e\u30b9\u30b3\u30a2\u3088\u308a\u5b9f\u614b\u306b\u8fd1\u3065\u3051\u308b\u3002<\/li>\n<li><strong>\u81ea\u5206\u306e\u696d\u52d9\u30c7\u30fc\u30bf\u3067\u5c0f\u3055\u304f\u691c\u8a3c\u3059\u308b<\/strong>\u3002\u3069\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3082\u6240\u8a6e\u306f\u4ee3\u7406\u6307\u6a19\u3067\u3042\u308a\u3001\u5b9f\u969b\u306e\u696d\u52d9\u30bf\u30b9\u30af\u3067\u306e\u691c\u8a3c\u306b\u52dd\u308b\u3082\u306e\u306f\u306a\u3044\u3002<\/li>\n<\/ul>\n<h2>\u304a\u308f\u308a\u306b<\/h2>\n<p>\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u304c\u6570\u304b\u6708\u3067\u7121\u52b9\u5316\u3055\u308c\u308b\u306e\u306f\u3001\u88cf\u3092\u8fd4\u305b\u3070\u30e2\u30c7\u30eb\u306e\u9032\u5316\u304c\u305d\u308c\u3060\u3051\u901f\u3044\u3068\u3044\u3046\u8a3c\u3067\u3082\u3042\u308b\u3002\u305f\u3060\u3057\u300c\u30c6\u30b9\u30c8\u3067\u89e3\u3051\u305f\u300d\u3053\u3068\u3068\u300c\u73fe\u5834\u3067\u4efb\u305b\u3089\u308c\u308b\u300d\u3053\u3068\u306e\u9593\u306b\u306f\u3001\u4f9d\u7136\u3068\u3057\u3066\u5927\u304d\u306a\u8ddd\u96e2\u304c\u3042\u308b\u3002\u8a55\u4fa1\u3068\u3044\u3046\u5730\u5473\u306a\u8db3\u5834\u304c\u58ca\u308c\u3084\u3059\u304f\u306a\u3063\u3066\u3044\u308b\u4eca\u3060\u304b\u3089\u3053\u305d\u3001\u70b9\u6570\u306e\u4e00\u4eba\u6b69\u304d\u306b\u6d41\u3055\u308c\u305a\u3001\u8907\u6570\u306e\u8996\u70b9\u304b\u3089\u5b9f\u529b\u3092\u898b\u6975\u3081\u308b\u59ff\u52e2\u304c\u3001\u3053\u308c\u307e\u3067\u4ee5\u4e0a\u306b\u554f\u308f\u308c\u3066\u3044\u308b\u3002<\/p>\n<hr \/>\n<h2>\u4e3b\u306a\u60c5\u5831\u6e90<\/h2>\n<ul>\n<li><a href=\"https:\/\/hai.stanford.edu\/ai-index\/2026-ai-index-report\" target=\"_blank\" rel=\"noopener\">Stanford HAI\u300cThe 2026 AI Index Report\u300d<\/a><\/li>\n<li><a href=\"https:\/\/hai.stanford.edu\/ai-index\/2026-ai-index-report\/technical-performance\" target=\"_blank\" rel=\"noopener\">Stanford HAI\u300c2026 AI Index Report: Technical Performance\u300d<\/a><\/li>\n<li><a href=\"https:\/\/arxiv.org\/html\/2602.16763v3\" target=\"_blank\" rel=\"noopener\">\u300cWhen AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation\u300d(arXiv)<\/a><\/li>\n<li><a href=\"https:\/\/metr.org\/blog\/2025-03-19-measuring-ai-ability-to-complete-long-tasks\" target=\"_blank\" rel=\"noopener\">METR\u300cMeasuring AI Ability to Complete Long Tasks\u300d<\/a><\/li>\n<li><a href=\"https:\/\/metr.org\/blog\/2026-1-29-time-horizon-1-1\" target=\"_blank\" rel=\"noopener\">METR\u300cTime Horizon 1.1\u300d<\/a><\/li>\n<li><a href=\"https:\/\/arxiv.org\/pdf\/2504.20879\" target=\"_blank\" rel=\"noopener\">\u300cThe Leaderboard Illusion\u300d(arXiv)<\/a><\/li>\n<li><a href=\"https:\/\/www.maginative.com\/article\/chatbot-arena-rebrands-as-lmarena-becomes-a-company\/\" target=\"_blank\" rel=\"noopener\">Maginative\u300cChatbot Arena Rebrands as LMArena, Becomes a Company\u300d<\/a><\/li>\n<\/ul>\n<p><small>\u5404\u30c4\u30fc\u30eb\u306f\u63d0\u4f9b\u5143\u306e\u898f\u7d04\u306b\u5f93\u3063\u3066\u3054\u5229\u7528\u304f\u3060\u3055\u3044\u3002\u60c5\u5831\u306f\u5404\u60c5\u5831\u6e90\u306e\u516c\u958b\u6642\u70b9\u306e\u3082\u306e\u3067\u3059\u3002\u53ce\u96c6\u30fb\u8981\u7d04\u306fAI\u3001\u516c\u958b\u5224\u65ad\u306f\u4eba\u3002<\/small><\/p>\n","protected":false},"excerpt":{"rendered":"<p>AI\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u304c\u767a\u8868\u304b\u3089\u6570\u304b\u6708\u3067\u300c\u982d\u6253\u3061\u300d\u306b\u306a\u308b\u73fe\u8c61\u304c\u5e38\u614b\u5316\u3057\u3066\u3044\u308b\u3002Stanford HAI\u306e\u6700\u65b0\u5831\u544a\u3084\u7814\u7a76\u304c\u793a\u3059\u5b9f\u614b\u3068\u3001METR\u306e\u300c\u4f5c\u696d\u6642\u9593\u306e\u9577\u3055\u300d\u3084Arena(\u65e7LMArena)\u306e\u4eba\u9593\u8a55\u4fa1\u306a\u3069\u3001\u6b21\u306e\u3082\u306e\u3055\u3057\u3092\u63a2\u308b\u52d5\u304d\u3092\u8aad\u307f\u89e3\u304f\u30b3\u30e9\u30e0\u3002<\/p>\n","protected":false},"author":1,"featured_media":46,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"page_builder":"","footnotes":""},"categories":[15],"tags":[],"class_list":["post-544","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-15"],"_links":{"self":[{"href":"https:\/\/www.wetch.co.jp\/ai\/wp-json\/wp\/v2\/posts\/544","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.wetch.co.jp\/ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.wetch.co.jp\/ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.wetch.co.jp\/ai\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.wetch.co.jp\/ai\/wp-json\/wp\/v2\/comments?post=544"}],"version-history":[{"count":1,"href":"https:\/\/www.wetch.co.jp\/ai\/wp-json\/wp\/v2\/posts\/544\/revisions"}],"predecessor-version":[{"id":588,"href":"https:\/\/www.wetch.co.jp\/ai\/wp-json\/wp\/v2\/posts\/544\/revisions\/588"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.wetch.co.jp\/ai\/wp-json\/wp\/v2\/media\/46"}],"wp:attachment":[{"href":"https:\/\/www.wetch.co.jp\/ai\/wp-json\/wp\/v2\/media?parent=544"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wetch.co.jp\/ai\/wp-json\/wp\/v2\/categories?post=544"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wetch.co.jp\/ai\/wp-json\/wp\/v2\/tags?post=544"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}