[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-evaluation-metrics":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"60f67c20-83e6-462e-b7b7-69ed61f75fad","evaluation metrics","evaluation-metrics",0,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"6e6c4ade-4dae-48c3-9a94-a081e08ab931","aisafetybenchexplorer-ai-safety-benchmarks-en","AISafetyBenchExplorer maps AI safety benchmarks","A catalog of 195 AI safety benchmarks shows how fragmented measurement and weak governance make safety evaluation hard to compare.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778739653161-5vdb.png","en","2026-05-14T06:20:29.016052+00:00"]