[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-coding-model":3},{"tag":4,"articles":11},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"e08d44c9-7a96-4148-b08f-23b2aa57b23d","coding model","coding-model",4,"coding model 指的是針對程式生成、除錯、重構與終端操作優化的模型，常用 SWE-bench、Terminal Bench 等指標評估。這類模型也逐漸分化出長上下文、代理式工具調用與多模態等能力。","Coding models are tuned for code generation, debugging, refactoring, and terminal workflows, often judged by benchmarks like SWE-bench and Terminal Bench. The category is now splitting into long-context, agent-style tool use, and multimodal variants.",[12,21],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"91fe9555-c2db-4489-babe-df23943ec39b","glm-5-zai-flagship-coding-agents-en","GLM-5: Z.AI's new flagship for coding and agents","GLM-5 posts 77.8 on SWE-bench Verified and 56.2 on Terminal Bench 2.0, putting Z.AI in direct competition with top coding models.","model-release","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775135076803-ig5q.png","en","2026-04-02T13:03:42.827978+00:00",{"id":22,"slug":23,"title":24,"summary":25,"category":17,"image_url":26,"cover_image":27,"language":19,"created_at":28},"a1379e9a-6785-4ff5-9b0a-8cff55f8264f","cursor-composer-2-started-from-kimi-en","Cursor’s Composer 2 started from Kimi","Cursor says Composer 2 began on Moonshot AI’s Kimi base, then added more training. The company says the final model is very different.",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Fcover-1774595866498-425oei.png","2026-03-28T03:11:59.132398+00:00"]