[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-swe-bench-pro":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"ad568dc4-80b0-4a22-b74a-e4bfb4a9f25f","SWE-Bench Pro","swe-bench-pro",2,null,[11,20,27,35],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"435fc551-a461-444a-bf95-dbf5685cfac0","minimax-m3-open-weight-coding-win-en","MiniMax M3 Proves Open-Weight Can Still Win on Coding","MiniMax M3 makes a strong case that open-weight models can still lead on coding, context, and price.","model-release","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780968781159-odhi.png","en","2026-06-09T01:32:31.256895+00:00",{"id":21,"slug":22,"title":23,"summary":24,"category":16,"image_url":25,"cover_image":25,"language":18,"created_at":26},"792ebbf9-6c9b-4651-9a00-c45ad71248fd","why-kimi-k26-changes-coding-model-race-en","Why Kimi K2.6 Changes the Coding Model Race","Kimi K2.6 is the open-weight coding model that matches GPT-5.5 on SWE-Bench Pro at far lower cost.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778980422986-oc3c.png","2026-05-17T01:13:22.633467+00:00",{"id":28,"slug":29,"title":30,"summary":31,"category":32,"image_url":33,"cover_image":33,"language":18,"created_at":34},"a5281bf5-661d-4288-b00e-0aa245e1fb03","why-coding-benchmarks-are-finally-telling-the-truth-en","Why coding benchmarks are finally telling the truth","BenchLM’s coding leaderboard says LiveCodeBench and SWE-bench Pro are the only signals that still matter.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778670666742-3yxf.png","2026-05-13T11:10:26.190997+00:00",{"id":36,"slug":37,"title":38,"summary":39,"category":40,"image_url":41,"cover_image":41,"language":18,"created_at":42},"1e86831a-5448-4953-b598-edd58f6f58d6","marginlab-claude-code-opus-46-tracker-en","Marginlab Tracks Claude Code Opus 4.6 Drift","Marginlab’s daily tracker watches Claude Code Opus 4.6 on 50 SWE-Bench-Pro tasks and flags statistically significant drops.","ai-agent","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775147267640-s3yy.png","2026-04-02T16:27:31.350256+00:00"]