[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"api:\u002Fnav:{}":3,"api:\u002Fbenchmarks:{}":104},{"login_code_required":4,"data_date":5,"vendors":6,"categories":39,"topics":55,"model_count":72,"benchmark_count":73,"models":74,"benchmarks":79},false,"2026-10-27",[7,15,23,31],{"name":8,"slug":9,"models":10},"阿里巴巴","alibaba",[11],{"name":12,"slug":13,"short_name":12,"overall_score":14},"Qwen3.8-27B","qwen3-8-27b","47.576875000000000000000000",{"name":16,"slug":17,"models":18},"深度求索","deepseek",[19],{"name":20,"slug":21,"short_name":20,"overall_score":22},"DeepSeek-V4-Pro","deepseek-v4-pro","65.030000000000000000000000",{"name":24,"slug":25,"models":26},"月之暗面","moonshot",[27],{"name":28,"slug":29,"short_name":28,"overall_score":30},"Kimi-K3","kimi-k3","57.474000000000000000000000",{"name":32,"slug":33,"models":34},"智谱","zhipu",[35],{"name":36,"slug":37,"short_name":36,"overall_score":38},"GLM-5.3","glm-5-3","61.067500000000000000000000",[40,44,48,51],{"name":41,"slug":42,"benchmark_count":43},"体验感","experience",2,{"name":45,"slug":46,"benchmark_count":47},"认知能力","cognition",5,{"name":49,"slug":50,"benchmark_count":43},"Agentic 能力","agentic",{"name":52,"slug":53,"benchmark_count":54},"应用领域","domain",1,[56,60,64,68],{"slug":57,"name":58,"question":59},"quant","量化 vs 原精度","量化之后能力掉多少",{"slug":61,"name":62,"question":63},"selfhost","自部署 vs 官方 API","同一份权重，自己部署和调官方 API，分数一致吗",{"slug":65,"name":66,"question":67},"size","同家族尺寸","同一代模型，小尺寸比旗舰差多少",{"slug":69,"name":70,"question":71},"harness","多 Harness","同一个模型换一个 harness，agentic 分数变多少",4,8,[75,76,77,78],{"name":20,"slug":21},{"name":36,"slug":37},{"name":28,"slug":29},{"name":12,"slug":13},[80,83,86,89,92,95,98,101],{"name":81,"slug":82},"AA-LCR","aa-lcr",{"name":84,"slug":85},"AA-Omniscience","aa-omniscience",{"name":87,"slug":88},"AutomationBench","automationbench",{"name":90,"slug":91},"CL-bench","cl-bench",{"name":93,"slug":94},"HLE","hle",{"name":96,"slug":97},"MMLU-Pro","mmlu-pro",{"name":99,"slug":100},"SimpleQA Verified","simpleqa-verified",{"name":102,"slug":103},"SWE-bench Pro","swe-bench-pro",{"categories":105},[106,141,189,220],{"name":41,"slug":42,"ranking":107,"benchmarks":117,"description":140,"benchmark_count":43},[108,110,112,115],{"name":36,"rank":54,"score":109,"model_slug":37,"vendor_slug":33},"72.997032640949555000000000",{"name":28,"rank":43,"score":111,"model_slug":29,"vendor_slug":25},"65.051903114186850000000000",{"name":12,"rank":113,"score":114,"model_slug":13,"vendor_slug":9},3,"48.453230452674897000000000",{"name":20,"rank":72,"score":116,"model_slug":21,"vendor_slug":17},"2.857142857142860000000000",[118,131],{"id":72,"best":119,"name":84,"slug":85,"license":122,"num_cases":123,"categories":124,"is_agentic":4,"sort_order":127,"updated_at":128,"description":129,"metric_name":130},{"name":28,"score":120,"run_id":121,"model_slug":29,"vendor_slug":25},"0.3500",58,"public",600,[125,126],{"name":41,"slug":42},{"name":45,"slug":46},0,"2026-10-26",null,"Omniscience Index",{"id":47,"best":132,"name":90,"slug":91,"license":122,"num_cases":135,"categories":136,"is_agentic":4,"sort_order":127,"updated_at":138,"description":129,"metric_name":139},{"name":12,"score":133,"run_id":134,"model_slug":13,"vendor_slug":9},"0.2489",115,1899,[137],{"name":41,"slug":42},"2026-09-27","Accuracy","指令遵循、幻觉控制和安全对齐",{"name":45,"slug":46,"ranking":142,"benchmarks":151,"description":188,"benchmark_count":47},[143,145,147,149],{"name":20,"rank":54,"score":144,"model_slug":21,"vendor_slug":17},"69.724166666666667500000000",{"name":28,"rank":43,"score":146,"model_slug":29,"vendor_slug":25},"67.050833333333332500000000",{"name":36,"rank":113,"score":148,"model_slug":37,"vendor_slug":33},"59.363333333333333750000000",{"name":12,"rank":72,"score":150,"model_slug":13,"vendor_slug":9},"45.520000000000000000000000",[152,160,167,172,179],{"id":153,"best":154,"name":96,"slug":97,"license":122,"num_cases":157,"categories":158,"is_agentic":4,"sort_order":127,"updated_at":5,"description":129,"metric_name":139},7,{"name":28,"score":155,"run_id":156,"model_slug":29,"vendor_slug":25},"0.8877",60,12032,[159],{"name":45,"slug":46},{"id":113,"best":161,"name":81,"slug":82,"license":122,"num_cases":164,"categories":165,"is_agentic":4,"sort_order":127,"updated_at":128,"description":129,"metric_name":139},{"name":28,"score":162,"run_id":163,"model_slug":29,"vendor_slug":25},"0.8300",57,100,[166],{"name":45,"slug":46},{"id":72,"best":168,"name":84,"slug":85,"license":122,"num_cases":123,"categories":169,"is_agentic":4,"sort_order":127,"updated_at":128,"description":129,"metric_name":130},{"name":28,"score":120,"run_id":121,"model_slug":29,"vendor_slug":25},[170,171],{"name":41,"slug":42},{"name":45,"slug":46},{"id":54,"best":173,"name":99,"slug":100,"license":122,"num_cases":176,"categories":177,"is_agentic":4,"sort_order":127,"updated_at":128,"description":129,"metric_name":139},{"name":20,"score":174,"run_id":175,"model_slug":21,"vendor_slug":17},"0.5710",16,1000,[178],{"name":45,"slug":46},{"id":180,"best":181,"name":93,"slug":94,"license":122,"num_cases":184,"categories":185,"is_agentic":4,"sort_order":127,"updated_at":187,"description":129,"metric_name":139},6,{"name":12,"score":182,"run_id":183,"model_slug":13,"vendor_slug":9},"0.3109",116,2158,[186],{"name":45,"slug":46},"2026-10-20","语言理解与表达、知识储备和推理能力",{"name":49,"slug":50,"ranking":190,"benchmarks":199,"description":219,"benchmark_count":43},[191,193,195,197],{"name":36,"rank":54,"score":192,"model_slug":37,"vendor_slug":33},"54.225000000000000000000000",{"name":12,"rank":43,"score":194,"model_slug":13,"vendor_slug":9},"49.480000000000000000000000",{"name":20,"rank":113,"score":196,"model_slug":21,"vendor_slug":17},"45.670000000000000000000000",{"name":28,"rank":72,"score":198,"model_slug":29,"vendor_slug":25},"3.500000000000000000000000",[200,209],{"id":43,"best":201,"name":87,"slug":88,"license":122,"num_cases":123,"categories":204,"is_agentic":207,"sort_order":127,"updated_at":128,"description":129,"metric_name":208},{"name":36,"score":202,"run_id":203,"model_slug":37,"vendor_slug":33},"0.5250",41,[205,206],{"name":49,"slug":50},{"name":52,"slug":53},true,"Pass Rate",{"id":210,"best":211,"name":102,"slug":103,"license":122,"num_cases":214,"categories":215,"is_agentic":207,"sort_order":127,"updated_at":217,"description":129,"metric_name":218},9,{"name":12,"score":212,"run_id":213,"model_slug":13,"vendor_slug":9},"0.5746",120,731,[216],{"name":49,"slug":50},"2026-10-23","Resolved Rate","任务规划与分解、工具调用和记忆管理",{"name":52,"slug":53,"ranking":221,"benchmarks":228,"description":234,"benchmark_count":54},[222,224,225,227],{"name":36,"rank":54,"score":223,"model_slug":37,"vendor_slug":33},"52.500000000000000000000000",{"name":20,"rank":43,"score":196,"model_slug":21,"vendor_slug":17},{"name":12,"rank":113,"score":226,"model_slug":13,"vendor_slug":9},"41.500000000000000000000000",{"name":28,"rank":72,"score":198,"model_slug":29,"vendor_slug":25},[229],{"id":43,"best":230,"name":87,"slug":88,"license":122,"num_cases":123,"categories":231,"is_agentic":207,"sort_order":127,"updated_at":128,"description":129,"metric_name":208},{"name":36,"score":202,"run_id":203,"model_slug":37,"vendor_slug":33},[232,233],{"name":49,"slug":50},{"name":52,"slug":53},"软件工程、通用办公、金融经济、法律、创意设计和网络安全"]