[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-ai-coding-benchmark":3},{"tag":4,"articles":10,"peer_article_count":8},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"856a45b7-cb2f-4b16-803b-d666cfade83b","AI coding benchmark","ai-coding-benchmark",0,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"deadc4df-9113-4f89-a962-86c8fe04b87a","deepswe-reshuffles-ai-coding-leaderboard-en","DeepSWE reshuffles the AI coding leaderboard","DeepSWE’s 113-task test across 91 repos puts GPT-5.5 at 70% and exposes a loophole in Claude Opus.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780006679356-1rr8.png","en","2026-05-28T22:17:31.831265+00:00"]