[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-benchlm":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"b13bfc1e-0547-40df-bc95-1126506a1298","BenchLM","benchlm",2,null,[11,20,28],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"5b168b94-465a-4d72-bbb1-e6577625cb1a","why-coding-benchmarks-are-finally-telling-the-truth-zh","為什麼程式碼基準測試終於開始說實話","BenchLM 的程式碼排行榜顯示，真正有用的訊號只剩 LiveCodeBench 與 SWE-bench Pro；HumanEval 已經不適合拿來選模型。","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778670697069-56o7.png","zh","2026-05-13T11:10:25.586869+00:00",{"id":21,"slug":22,"title":23,"summary":24,"category":25,"image_url":26,"cover_image":26,"language":18,"created_at":27},"7643f90c-21d3-42f9-80d2-c022f74cbe76","kimi-k2-6-benchlm-2026-scores-zh","Kimi K2.6：BenchLM 2026 成績解析","Kimi K2.6 在 BenchLM 2026 排第 12，Coding 和 Agentic 表現強，還有 256K context 與 open weights。","model-release","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777900262750-nehv.png","2026-05-04T13:10:38.017323+00:00",{"id":29,"slug":30,"title":31,"summary":32,"category":25,"image_url":33,"cover_image":33,"language":18,"created_at":34},"b875d3ed-f892-43a8-a51e-920729e85b1e","gpt-5-4-benchmarks-2026-scores-rankings-zh","GPT-5.4 知識測驗拿 97.6 分","GPT-5.4 在 BenchLM 知識與理解拿到 97.6 分，總榜暫列第 2，還有 1.05M token 長上下文。這篇拆解它適合哪些工作、和其他模型怎麼比。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776082194973-cyii.png","2026-04-13T12:09:40.301446+00:00"]