[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-terminal-bench-20":3},{"tag":4,"articles":11},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"94531867-5fcd-4032-ab55-b86b39b21364","Terminal Bench 2.0","terminal-bench-20",4,"Terminal Bench 2.0 是用來衡量 AI 在終端機環境中完成指令、排錯與工具操作的基準，常見於代理式寫碼與自動化工作流評估。它能反映模型是否真的能在 shell、檔案系統與多步驟任務中穩定執行。","Terminal Bench 2.0 measures how well AI systems handle real terminal work: running commands, fixing errors, navigating files, and chaining multi-step shell tasks. It is a useful signal for agentic coding, automation, and models that must operate reliably in CLI-driven workflows.",[12,21],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"57576af6-0bf2-4616-ac89-8435e39a8aa7","glm-5-zai-flagship-coding-agents-zh","GLM-5 登場：Z.AI 的寫程式旗艦","GLM-5 是 Z.AI 的新旗艦模型。744B 總參數、200K context、SWE-bench Verified 77.8、Terminal Bench 2.0 56.2，直接挑戰頂級 coding 模型。","model-release","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775135063109-o1yh.png","zh","2026-04-02T13:03:42.135022+00:00",{"id":22,"slug":23,"title":24,"summary":25,"category":17,"image_url":26,"cover_image":27,"language":19,"created_at":28},"c4b6186f-bd84-4598-997e-c6e31d543c0d","cursor-composer-2-agentic-coding-model-zh","Cursor Composer 2 走向代理式寫碼","Cursor 推出 Composer 2，CursorBench 61.3、Terminal-Bench 2.0 61.7，主打代理式寫碼與高量產團隊的成本效率。",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1774497597106-o12v.png","2026-03-28T03:13:06.422716+00:00"]