[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-llm-benchmark":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"e738f6c2-87ab-4ae7-a7af-272bf8aa1d1e","LLM benchmark","llm-benchmark",2,null,[11,20,27],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"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","zh","2026-05-04T13:10:38.017323+00:00",{"id":21,"slug":22,"title":23,"summary":24,"category":16,"image_url":25,"cover_image":25,"language":18,"created_at":26},"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",{"id":28,"slug":29,"title":30,"summary":31,"category":16,"image_url":32,"cover_image":32,"language":18,"created_at":33},"2478aa0c-2f56-447c-8fff-419d35183405","claude-mythos-vs-opus-46-capability-jump-zh","Claude Mythos 跟 Opus 4.6 差多少","Anthropic 傳出 Mythos 測試分數高於 Claude Opus 4.6。若 SWE-bench、推理與資安數字屬實，開發者會感受到明顯差距。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775125819094-xhdz.png","2026-04-02T09:09:38.488815+00:00"]