{"id":7973,"date":"2025-12-29T06:28:00","date_gmt":"2025-12-28T21:28:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=7973"},"modified":"2025-12-27T14:02:59","modified_gmt":"2025-12-27T05:02:59","slug":"glm-4-7-minimax-m2-1-ernie-5-0-preview-1203","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=7973","title":{"rendered":"GLM 4.7, MiniMax M2.1 , ERNIE-5.0-Preview-1203"},"content":{"rendered":"\n<p>\u5148\u9031\u306f\u4e2d\u56fd\u306e\u30d5\u30ed\u30f3\u30c6\u30a3\u30a2\u30e2\u30c7\u30eb\u306b\u95a2\u3059\u308b\u767a\u8868\u304c\u76ee\u7acb\u3063\u305f\u3002\u30de\u30a4\u30ca\u30fc\u30a2\u30c3\u30d7\u30c7\u30fc\u30c8\u304c\u591a\u3044\u3082\u306e\u306e\u7740\u5b9f\u306a\u6027\u80fd\u30a2\u30c3\u30d7\u3092\u5b9f\u73fe\u3057\u3066\u3044\u308b\u3002GLM-4.7\uff08<a href=\"https:\/\/x.com\/zai_org\/status\/2003156119087382683\">X\u30e6\u30fc\u30b6\u30fc\u306eZ.ai\u3055\u3093: \u300cGLM-4.7 is here! GLM-4.7 surpasses GLM-4.6 with substantial improvements in coding, complex reasoning, and tool usage, setting new open-source SOTA standards. It also boosts performance in chat, creative writing, and role-play scenarios. Default Model for Coding Plan: https:\/\/t.co\/3vDzwof7A8\u300d \/ X<\/a>\u3001\u30ea\u30dd\u30b8\u30c8\u30ea\uff1a<a href=\"https:\/\/huggingface.co\/zai-org\/GLM-4.7\">zai-org\/GLM-4.7 \u00b7 Hugging Face<\/a>\uff09\u3001MiniMax M2.1\uff08<a href=\"https:\/\/x.com\/MiniMax__AI\/status\/2004524661359407129\">X\u30e6\u30fc\u30b6\u30fc\u306eMiniMax (official)\u3055\u3093: \u300cMiniMax M2.1 is OPEN SOURCE: SOTA for real-world dev &amp; agents \u2022 SOTA on coding benchmarks (SWE \/ VIBE \/ Multi-SWE) \u2022 Beats Gemini 3 Pro &amp; Claude Sonnet 4.5 \u2022 10B active \/ 230B total (MoE) Not just SOTA, faster to infer, easier to deploy, and yes, you can even run it locally https:\/\/t.co\/atCML3vq8C\u300d \/ X<\/a>\u3001\u30ea\u30dd\u30b8\u30c8\u30ea\uff1a<a href=\"https:\/\/huggingface.co\/MiniMaxAI\/MiniMax-M2.1\">MiniMaxAI\/MiniMax-M2.1 \u00b7 Hugging Face<\/a>\uff09\u3068\u3082\u30e2\u30c7\u30eb\u304c\u516c\u958b\u3055\u308c\u3066\u3044\u308b\u306e\u304c\u3059\u3070\u3089\u3057\u3044\u3002ERNIE 5.0\uff08<a href=\"https:\/\/ernie.baidu.com\/blog\/posts\/ernie-5.0-preview-1203-release-on-lmarena\/\">Best Text model from China in LMArena is now ERNIE-5.0-Preview-1203! | ERNIE Blog<\/a>\uff09\u3082\u5f37\u529b\u305d\u3046\u3002<\/p>\n\n\n\n<p>Nemotron3\u306b\u3064\u3044\u3066\u306f\u8ad6\u6587\u304c\u51fa\u3066\u3044\u305f\u3002\u5f37\u529b\u306a\u516c\u958b\u30e2\u30c7\u30eb\u304c\u5897\u3048\u3066\u304a\u308a\u3001\u307e\u305f\u3001\u30a2\u30c3\u30d7\u30c7\u30fc\u30c8\u3082\u3055\u308c\u3066\u304a\u308a\u826f\u3044\u6642\u4ee3\u3067\u3042\u308b\uff08\uff1f\uff09<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>NVIDIA Nemotron 3: Efficient and Open Intelligence\u00a0<\/strong>[227.5]<br>\u30cd\u30e2\u30c8\u30ed\u30f33\u30b7\u30ea\u30fc\u30ba\u306f\u5f37\u529b\u306a\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u3001\u63a8\u8ad6\u3001\u4f1a\u8a71\u80fd\u529b\u3092\u63d0\u4f9b\u3059\u308b\u3002 \u30cd\u30e2\u30c8\u30ed\u30f33\u30e2\u30c7\u30eb\u306f\u3001\u63a8\u8ad6\u3092\u53ef\u80fd\u306b\u3059\u308b\u30de\u30eb\u30c1\u74b0\u5883\u5f37\u5316\u5b66\u7fd2\u3001\u591a\u6bb5\u968e\u30c4\u30fc\u30eb\u306e\u4f7f\u7528\u3001\u304d\u3081\u7d30\u304b\u3044\u63a8\u8ad6\u4e88\u7b97\u5236\u5fa1\u306e\u30b5\u30dd\u30fc\u30c8\u3092\u7528\u3044\u3066\u3001\u5f8c\u304b\u3089\u8a13\u7df4\u3055\u308c\u308b\u3002 Nemotron 3\u30d5\u30a1\u30df\u30ea\u306f\u3001Mixture-of-Experts\u30cf\u30a4\u30d6\u30ea\u30c3\u30c9\u306eMamba-Transformer\u30a2\u30fc\u30ad\u30c6\u30af\u30c1\u30e3\u3092\u4f7f\u7528\u3057\u3066\u3001\u6700\u9ad8\u30ec\u30d9\u30eb\u306e\u30b9\u30eb\u30fc\u30d7\u30c3\u30c8\u3068\u6700\u5927100\u4e07\u30c8\u30fc\u30af\u30f3\u306e\u30b3\u30f3\u30c6\u30ad\u30b9\u30c8\u9577\u3092\u63d0\u4f9b\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2512.20856v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2512.20856v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Wed, 24 Dec 2025 00:24:05 GMT)<\/li>\n\n\n\n<li>\u300cThe Nemotron 3 family uses a Mixture-of-Experts hybrid Mamba\u2013Transformer architecture to provide best-in-class throughput and context lengths of up to 1M tokens.\u00a0\u300d\u3068Mamba\u30cf\u30a4\u30d6\u30ea\u30c3\u30c9\u3001\u9577\u6587\u5bfe\u5fdc\u306a\u30e2\u30c7\u30eb\u3002<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning\u00a0<\/strong>[223.9]<br>Nemotron 3 Nano 30B-A3B\u306fMixture-of-Experts\u30cf\u30a4\u30d6\u30ea\u30c3\u30c9Mamba-Transformer\u8a00\u8a9e\u30e2\u30c7\u30eb\u3067\u3042\u308b\u3002 \u30cd\u30e2\u30c8\u30ed\u30f33\u30ca\u30ce\u306f25\u5146\u500b\u306e\u30c6\u30ad\u30b9\u30c8\u30c8\u30fc\u30af\u30f3\u3067\u4e8b\u524d\u8a13\u7df4\u3055\u308c\u3001\u305d\u306e\u4e2d\u306b\u306f\u30cd\u30e2\u30c8\u30ed\u30f32\u306b3\u5146\u4ee5\u4e0a\u306e\u65b0\u3057\u3044\u30e6\u30cb\u30fc\u30af\u306a\u30c8\u30fc\u30af\u30f3\u304c\u542b\u307e\u308c\u3066\u3044\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2512.20848v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2512.20848v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Tue, 23 Dec 2025 23:54:32 GMT)<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/huggingface.co\/nvidia\/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8\">nvidia\/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 \u00b7 Hugging Face<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>\u5148\u9031\u306f\u4e2d\u56fd\u306e\u30d5\u30ed\u30f3\u30c6\u30a3\u30a2\u30e2\u30c7\u30eb\u306b\u95a2\u3059\u308b\u767a\u8868\u304c\u76ee\u7acb\u3063\u305f\u3002\u30de\u30a4\u30ca\u30fc\u30a2\u30c3\u30d7\u30c7\u30fc\u30c8\u304c\u591a\u3044\u3082\u306e\u306e\u7740\u5b9f\u306a\u6027\u80fd\u30a2\u30c3\u30d7\u3092\u5b9f\u73fe\u3057\u3066\u3044\u308b\u3002GLM-4.7\uff08X\u30e6\u30fc\u30b6\u30fc\u306eZ.ai\u3055\u3093: \u300cGLM-4.7 is here! GLM-4.7 sur &hellip; <a href=\"https:\/\/devneko.jp\/wordpress\/?p=7973\" class=\"more-link\"><span class=\"screen-reader-text\">&#8220;GLM 4.7, MiniMax M2.1 , ERNIE-5.0-Preview-1203&#8221; \u306e<\/span>\u7d9a\u304d\u3092\u8aad\u3080<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[223],"class_list":["post-7973","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7973","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=7973"}],"version-history":[{"count":1,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7973\/revisions"}],"predecessor-version":[{"id":7974,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7973\/revisions\/7974"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=7973"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=7973"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=7973"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}