{"id":50143,"date":"2026-02-12T12:14:13","date_gmt":"2026-02-12T04:14:13","guid":{"rendered":"https:\/\/www.1ai.net\/?p=50143"},"modified":"2026-02-12T12:14:23","modified_gmt":"2026-02-12T04:14:23","slug":"%e6%99%ba%e8%b0%b1%e4%b8%8a%e7%ba%bf%e5%85%a8%e6%96%b0%e6%a8%a1%e5%9e%8b-glm-5","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/50143.html","title":{"rendered":"GLM-5"},"content":{"rendered":"

2 \u6708 12 \u65e5\u6d88\u606f\uff0c\u521a\u521a\uff0c\u667a\u8c31<\/a>\u6b63\u5f0f\u4e0a\u7ebf\u5e76\u5f00\u6e90\u6700\u65b0\u6a21\u578b<\/a> GLM-5\u3002<\/p>\n

\"68c93506j00tabvqa006dd000u000kem\"<\/p>\n

\u636e\u4ecb\u7ecd\uff0cGLM-5 \u662f\u8fc8\u5411 Agentic Engineering \u7684\u4ea7\u7269\uff1a\u5728 Coding \u4e0e Agent \u80fd\u529b\u4e0a\uff0c\u5176\u53d6\u5f97\u5f00\u6e90 SOTA \u8868\u73b0\uff0c\u5728\u771f\u5b9e\u7f16\u7a0b\u573a\u666f\u7684\u4f7f\u7528\u4f53\u611f\u903c\u8fd1 Claude Opus 4.5\uff0c\u64c5\u957f\u590d\u6742\u7cfb\u7edf\u5de5\u7a0b\u4e0e\u957f\u7a0b Agent \u4efb\u52a1\u3002<\/p>\n

GLM-5 \u91c7\u7528\u5168\u65b0\u57fa\u5ea7\uff1a\u53c2\u6570\u89c4\u6a21\u4ece 355B\uff08\u6fc0\u6d3b 32B\uff09\u6269\u5c55\u81f3 744B\uff08\u6fc0\u6d3b 40B\uff09\uff0c\u9884\u8bad\u7ec3\u6570\u636e\u4ece 23T \u63d0\u5347\u81f3 28.5T<\/strong>\uff1b\u6784\u5efa\u5168\u65b0\u7684\u300cSlime\u300d\u6846\u67b6\uff0c\u652f\u6301\u66f4\u5927\u6a21\u578b\u89c4\u6a21\u53ca\u66f4\u590d\u6742\u7684\u5f3a\u5316\u5b66\u4e60\u4efb\u52a1\u3002<\/p>\n

\u540c\u65f6\uff0cGLM-5 \u8fd8\u9996\u6b21\u96c6\u6210 DeepSeek Sparse Attention\uff08\u7a00\u758f\u6ce8\u610f\u529b\uff09<\/strong>\uff0c\u5728\u7ef4\u6301\u957f\u6587\u672c\u6548\u679c\u65e0\u635f\u7684\u540c\u65f6\uff0c\u5927\u5e45\u964d\u4f4e\u6a21\u578b\u90e8\u7f72\u6210\u672c\u3002<\/p>\n

\u5177\u4f53\u8868\u73b0\u4e0a\uff1a<\/p>\n

\u5728\u5168\u7403\u6743\u5a01\u7684 Artificial Analysis \u699c\u5355\u4e2d\uff0cGLM-5 \u4f4d\u5c45\u5168\u7403\u7b2c\u56db\u3001\u5f00\u6e90\u7b2c\u4e00\u3002<\/p>\n

GLM-5 \u5728\u7f16\u7a0b\u80fd\u529b\u4e0a\u5b9e\u73b0\u4e86\u5bf9\u9f50 Claude Opus 4.5\uff0c\u5728\u4e1a\u5185\u516c\u8ba4\u7684\u4e3b\u6d41\u57fa\u51c6\u6d4b\u8bd5\u4e2d\u53d6\u5f97\u5f00\u6e90\u6a21\u578b SOTA\u3002<\/p>\n

GLM-5 \u5728 SWE-bench-Verified \u548c Terminal Bench 2.0 \u4e2d\u5206\u522b\u83b7\u5f97 77.8 \u548c 56.2 \u7684\u5f00\u6e90\u6a21\u578b\u6700\u9ad8\u5206\u6570\uff0c\u6027\u80fd\u8d85\u8fc7 Gemini 3 Pro\u3002<\/p>\n

GLM-5 \u5728 BrowseComp\uff08\u8054\u7f51\u68c0\u7d22\u4e0e\u4fe1\u606f\u7406\u89e3\uff09\u3001MCP-Atlas\uff08\u5927\u89c4\u6a21\u7aef\u5230\u7aef\u5de5\u5177\u8c03\u7528\uff09\u548c \u03c4\u00b2-Bench\uff08\u590d\u6742\u573a\u666f\u4e0b\u81ea\u52a8\u4ee3\u7406\u7684\u5de5\u5177\u89c4\u5212\u548c\u6267\u884c\uff09\u5747\u53d6\u5f97\u6700\u9ad8\u8868\u73b0\u3002<\/p>\n

\u503c\u5f97\u4e00\u63d0\u7684\u662f\uff0c\u76ee\u524d GLM-5 \u5df2\u5b8c\u6210\u4e0e\u534e\u4e3a\u6607\u817e\u3001\u6469\u5c14\u7ebf\u7a0b\u3001\u5bd2\u6b66\u7eaa\u3001\u6606\u4ed1\u82af\u3001\u6c90\u66e6\u3001\u71e7\u539f\u3001\u6d77\u5149\u7b49\u56fd\u4ea7\u7b97\u529b\u5e73\u53f0\u7684\u6df1\u5ea6\u63a8\u7406\u9002\u914d\u3002\u901a\u8fc7\u5e95\u5c42\u7b97\u5b50\u4f18\u5316\u4e0e\u786c\u4ef6\u52a0\u901f\uff0cGLM-5 \u5728\u56fd\u4ea7\u82af\u7247\u96c6\u7fa4\u4e0a\u5df2\u7ecf\u5b9e\u73b0\u9ad8\u541e\u5410\u3001\u4f4e\u5ef6\u8fdf\u7684\u7a33\u5b9a\u8fd0\u884c\u3002<\/p>\n

\u5373\u65e5\u8d77\uff0cGLM-5 \u5728 Hugging Face \u4e0e ModelScope \u5e73\u53f0\u540c\u6b65\u5f00\u6e90\uff0c\u6a21\u578b\u6743\u91cd\u9075\u5faa MIT License\u3002\u540c\u65f6 GLM-5 \u5df2\u7eb3\u5165 GLM Coding Plan Max \u5957\u9910\u3002<\/p>\n

\u5728\u7ebf\u4f53\u9a8c<\/p>\n

Z.ai\uff1ahttps:\/\/chat.z.ai<\/p>\n

\u667a\u8c31\u6e05\u8a00APP\/\u7f51\u9875\u7248\uff1ahttps:\/\/chatglm.cn<\/p>\n

\u5f00\u6e90\u94fe\u63a5<\/p>\n

GitHub\uff1ahttps:\/\/github.com\/zai-org\/GLM-5<\/p>\n

Hugging Face\uff1ahttps:\/\/huggingface.co\/zai-org\/GLM-5<\/p>\n","protected":false},"excerpt":{"rendered":"

12 February, just now, the latest model GLM-5 is officially online and open. GLM-5 is described as a product of the move towards Agentic Engineering: in the Coding and Agent capabilities, its access to open source SOTA shows that it is approaching Claude Opus 4.5 in the use of a real programming landscape, with a special focus on complex system engineering and long-range Agent missions. GLM-5 Introduction of an entirely new base: parameter scale from 355B (activation 32B) to 744B (activation 40B), pre-training data from 23T to 28.5T; development of an entirely new \"Slime\" framework to support larger model size and more complex enhancements<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[146],"tags":[2680,1489],"collection":[],"class_list":["post-50143","post","type-post","status-publish","format-standard","hentry","category-news","tag-2680","tag-1489"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/50143","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=50143"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/50143\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=50143"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=50143"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=50143"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=50143"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}