[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-longcot":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"3fc144fc-4b25-4cd7-b9fb-256ae305b25e","LongCoT","longcot",1,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"2468c20a-c3cf-4004-8981-44934691673a","longcot-long-horizon-chain-of-thought-benchmark-zh","LongCoT：測長鏈推理，不只看答案","LongCoT 用 2,500 題測試模型能否在長鏈、互相依賴的推理步驟中保持一致。GPT 5.2 與 Gemini 3 Pro 仍低於 10%。","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776319784084-uldi.png","zh","2026-04-16T06:09:22.856744+00:00"]