[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"api:\u002Fnav:{}":3,"api:\u002Frecords\u002F43:{}":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",{"record":105,"variant":125,"benchmark":144,"rank":133,"ranked_count":72,"samples":152,"other_harnesses":156,"distribution":157,"cases":168},{"id":106,"notes":107,"score":108,"metrics":109,"cost_usd":107,"settings":110,"num_cases":118,"score_std":107,"harness_id":107,"has_bundle":119,"is_primary":119,"output_tps":107,"variant_id":73,"num_samples":54,"benchmark_id":54,"evaluated_at":120,"harness_name":107,"harness_slug":107,"input_tokens":121,"ttft_seconds":107,"output_tokens":122,"parent_run_id":107,"harness_version":107,"avg_case_seconds":123,"reasoning_tokens":107,"cost_per_case_usd":107,"trajectory_bundle_size_bytes":124},43,null,"0.4330",{},{"top_p":111,"recipe":107,"harness":107,"judge_model":112,"num_samples":54,"temperature":113,"extra_settings":114,"scoring_method":107,"harness_version":107,"framework_version":116,"max_output_tokens":117},"1.000","Qwen3-30B-A3B-Instruct-2507","0.60",{"top_k":115},-1,"OPT 1478395",65536,1000,true,"2026-10-20",34675,3013795,"172.65",3291417,{"access":126,"effort":127,"family":36,"is_tier":119,"hardware":107,"model_id":54,"provider":107,"data_date":128,"precision":107,"categories":129,"is_primary":119,"model_name":36,"model_slug":37,"short_name":36,"variant_id":73,"effort_rank":139,"input_price":107,"vendor_name":32,"vendor_slug":33,"architecture":107,"output_price":107,"overall_rank":43,"ranked_count":72,"release_date":140,"variant_name":141,"variant_slug":142,"vendor_order":143,"weights_repo":107,"missing_count":43,"overall_score":38,"context_window":107,"total_cost_usd":107,"total_params_b":107,"weights_source":107,"active_params_b":107,"cache_hit_price":107,"cost_incomplete":119,"is_open_weights":119,"inference_engine":107},"api","max","2026-10-23",[130,132,135,137],{"name":41,"rank":54,"slug":42,"score":131,"expected":43,"available":54,"ranked_count":72},"72.997032640949555000000000",{"name":45,"rank":133,"slug":46,"score":134,"expected":47,"available":72,"ranked_count":72},3,"59.363333333333333750000000",{"name":49,"rank":54,"slug":50,"score":136,"expected":43,"available":43,"ranked_count":72},"54.225000000000000000000000",{"name":52,"rank":54,"slug":53,"score":138,"expected":54,"available":54,"ranked_count":72},"52.500000000000000000000000",6,"2026-08-18","GLM-5.3 官方 API max","glm-5-3-api-max",0,{"id":54,"name":99,"slug":100,"license":145,"metrics":146,"version":107,"is_active":119,"num_cases":118,"parent_id":107,"score_max":147,"score_min":148,"created_at":149,"is_agentic":4,"sort_order":143,"updated_at":149,"description":107,"metric_name":150,"homepage_url":107,"license_note":107,"scoring_method":107,"composite_weight":147,"higher_is_better":119,"bundle_size_bytes":151},"public",[],"1.0000","0.0000","2026-10-28T09:47:38.906402+08:00","Accuracy",110385750,[153],{"total":118,"failed":154,"passed":155,"run_id":106,"ungraded":143,"sample_idx":143,"trajectories":118},567,433,[],[158,161,164,165],{"name":20,"rank":54,"score":159,"run_id":160,"model_slug":21,"vendor_slug":17},"0.5710",16,{"name":28,"rank":43,"score":162,"run_id":163,"model_slug":29,"vendor_slug":25},"0.4460",61,{"name":36,"rank":133,"score":108,"run_id":106,"model_slug":37,"vendor_slug":33},{"name":12,"rank":72,"score":166,"run_id":167,"model_slug":13,"vendor_slug":9},"0.1110",119,{"restricted":4,"rows":169,"counts":495,"next_after":489},[170,179,186,193,200,207,214,221,228,235,241,248,254,260,267,274,281,287,294,301,308,315,321,328,334,340,347,353,359,365,371,378,385,392,398,404,410,416,422,428,434,440,446,452,458,464,470,476,482,488],{"id":171,"error":107,"extra":172,"score":147,"passed":119,"case_key":175,"cost_usd":107,"sample_idx":143,"input_tokens":176,"output_tokens":177,"has_trajectory":119,"duration_seconds":178},125247,{"status":173,"finish_reason":174},"completed","stop","0",37,980,"82.90",{"id":180,"error":107,"extra":181,"score":147,"passed":119,"case_key":182,"cost_usd":107,"sample_idx":143,"input_tokens":183,"output_tokens":184,"has_trajectory":119,"duration_seconds":185},125248,{"status":173,"finish_reason":174},"1",36,410,"33.94",{"id":187,"error":107,"extra":188,"score":147,"passed":119,"case_key":189,"cost_usd":107,"sample_idx":143,"input_tokens":190,"output_tokens":191,"has_trajectory":119,"duration_seconds":192},125249,{"status":173,"finish_reason":174},"2",34,821,"71.47",{"id":194,"error":107,"extra":195,"score":147,"passed":119,"case_key":196,"cost_usd":107,"sample_idx":143,"input_tokens":197,"output_tokens":198,"has_trajectory":119,"duration_seconds":199},125250,{"status":173,"finish_reason":174},"3",40,334,"27.21",{"id":201,"error":107,"extra":202,"score":148,"passed":4,"case_key":203,"cost_usd":107,"sample_idx":143,"input_tokens":204,"output_tokens":205,"has_trajectory":119,"duration_seconds":206},125251,{"status":173,"finish_reason":174},"4",49,686,"58.18",{"id":208,"error":107,"extra":209,"score":147,"passed":119,"case_key":210,"cost_usd":107,"sample_idx":143,"input_tokens":211,"output_tokens":212,"has_trajectory":119,"duration_seconds":213},125252,{"status":173,"finish_reason":174},"5",31,472,"39.13",{"id":215,"error":107,"extra":216,"score":148,"passed":4,"case_key":217,"cost_usd":107,"sample_idx":143,"input_tokens":218,"output_tokens":219,"has_trajectory":119,"duration_seconds":220},125253,{"status":173,"finish_reason":174},"6",32,1037,"87.40",{"id":222,"error":107,"extra":223,"score":148,"passed":4,"case_key":224,"cost_usd":107,"sample_idx":143,"input_tokens":225,"output_tokens":226,"has_trajectory":119,"duration_seconds":227},125254,{"status":173,"finish_reason":174},"7",38,11234,"786.79",{"id":229,"error":107,"extra":230,"score":148,"passed":4,"case_key":231,"cost_usd":107,"sample_idx":143,"input_tokens":232,"output_tokens":233,"has_trajectory":119,"duration_seconds":234},125255,{"status":173,"finish_reason":174},"8",44,556,"47.81",{"id":236,"error":107,"extra":237,"score":147,"passed":119,"case_key":238,"cost_usd":107,"sample_idx":143,"input_tokens":225,"output_tokens":239,"has_trajectory":119,"duration_seconds":240},125256,{"status":173,"finish_reason":174},"9",841,"72.90",{"id":242,"error":107,"extra":243,"score":148,"passed":4,"case_key":244,"cost_usd":107,"sample_idx":143,"input_tokens":245,"output_tokens":246,"has_trajectory":119,"duration_seconds":247},125257,{"status":173,"finish_reason":174},"10",70,749,"63.23",{"id":249,"error":107,"extra":250,"score":148,"passed":4,"case_key":251,"cost_usd":107,"sample_idx":143,"input_tokens":183,"output_tokens":252,"has_trajectory":119,"duration_seconds":253},125258,{"status":173,"finish_reason":174},"11",564,"48.26",{"id":255,"error":107,"extra":256,"score":148,"passed":4,"case_key":257,"cost_usd":107,"sample_idx":143,"input_tokens":190,"output_tokens":258,"has_trajectory":119,"duration_seconds":259},125259,{"status":173,"finish_reason":174},"12",695,"58.67",{"id":261,"error":107,"extra":262,"score":147,"passed":119,"case_key":263,"cost_usd":107,"sample_idx":143,"input_tokens":264,"output_tokens":265,"has_trajectory":119,"duration_seconds":266},125260,{"status":173,"finish_reason":174},"13",29,730,"61.74",{"id":268,"error":107,"extra":269,"score":148,"passed":4,"case_key":270,"cost_usd":107,"sample_idx":143,"input_tokens":271,"output_tokens":272,"has_trajectory":119,"duration_seconds":273},125261,{"status":173,"finish_reason":174},"14",27,384,"31.57",{"id":275,"error":107,"extra":276,"score":147,"passed":119,"case_key":277,"cost_usd":107,"sample_idx":143,"input_tokens":278,"output_tokens":279,"has_trajectory":119,"duration_seconds":280},125262,{"status":173,"finish_reason":174},"15",24,534,"45.15",{"id":282,"error":107,"extra":283,"score":147,"passed":119,"case_key":284,"cost_usd":107,"sample_idx":143,"input_tokens":271,"output_tokens":285,"has_trajectory":119,"duration_seconds":286},125263,{"status":173,"finish_reason":174},"16",12563,"872.00",{"id":288,"error":107,"extra":289,"score":147,"passed":119,"case_key":290,"cost_usd":107,"sample_idx":143,"input_tokens":291,"output_tokens":292,"has_trajectory":119,"duration_seconds":293},125264,{"status":173,"finish_reason":174},"17",28,605,"51.66",{"id":295,"error":107,"extra":296,"score":147,"passed":119,"case_key":297,"cost_usd":107,"sample_idx":143,"input_tokens":298,"output_tokens":299,"has_trajectory":119,"duration_seconds":300},125265,{"status":173,"finish_reason":174},"18",59,4137,"263.81",{"id":302,"error":107,"extra":303,"score":147,"passed":119,"case_key":304,"cost_usd":107,"sample_idx":143,"input_tokens":305,"output_tokens":306,"has_trajectory":119,"duration_seconds":307},125266,{"status":173,"finish_reason":174},"19",35,1134,"94.85",{"id":309,"error":107,"extra":310,"score":147,"passed":119,"case_key":311,"cost_usd":107,"sample_idx":143,"input_tokens":312,"output_tokens":313,"has_trajectory":119,"duration_seconds":314},125267,{"status":173,"finish_reason":174},"20",23,675,"57.21",{"id":316,"error":107,"extra":317,"score":148,"passed":4,"case_key":318,"cost_usd":107,"sample_idx":143,"input_tokens":190,"output_tokens":319,"has_trajectory":119,"duration_seconds":320},125268,{"status":173,"finish_reason":174},"21",1112,"93.10",{"id":322,"error":107,"extra":323,"score":148,"passed":4,"case_key":324,"cost_usd":107,"sample_idx":143,"input_tokens":325,"output_tokens":326,"has_trajectory":119,"duration_seconds":327},125269,{"status":173,"finish_reason":174},"22",30,542,"46.06",{"id":329,"error":107,"extra":330,"score":147,"passed":119,"case_key":331,"cost_usd":107,"sample_idx":143,"input_tokens":211,"output_tokens":332,"has_trajectory":119,"duration_seconds":333},125270,{"status":173,"finish_reason":174},"23",1124,"94.26",{"id":335,"error":107,"extra":336,"score":147,"passed":119,"case_key":337,"cost_usd":107,"sample_idx":143,"input_tokens":325,"output_tokens":338,"has_trajectory":119,"duration_seconds":339},125271,{"status":173,"finish_reason":174},"24",428,"35.46",{"id":341,"error":107,"extra":342,"score":148,"passed":4,"case_key":343,"cost_usd":107,"sample_idx":143,"input_tokens":344,"output_tokens":345,"has_trajectory":119,"duration_seconds":346},125272,{"status":173,"finish_reason":174},"25",26,3092,"244.82",{"id":348,"error":107,"extra":349,"score":148,"passed":4,"case_key":350,"cost_usd":107,"sample_idx":143,"input_tokens":183,"output_tokens":351,"has_trajectory":119,"duration_seconds":352},125273,{"status":173,"finish_reason":174},"26",4424,"339.88",{"id":354,"error":107,"extra":355,"score":147,"passed":119,"case_key":356,"cost_usd":107,"sample_idx":143,"input_tokens":225,"output_tokens":357,"has_trajectory":119,"duration_seconds":358},125274,{"status":173,"finish_reason":174},"27",8229,"595.60",{"id":360,"error":107,"extra":361,"score":147,"passed":119,"case_key":362,"cost_usd":107,"sample_idx":143,"input_tokens":197,"output_tokens":363,"has_trajectory":119,"duration_seconds":364},125275,{"status":173,"finish_reason":174},"28",11972,"834.53",{"id":366,"error":107,"extra":367,"score":148,"passed":4,"case_key":368,"cost_usd":107,"sample_idx":143,"input_tokens":218,"output_tokens":369,"has_trajectory":119,"duration_seconds":370},125276,{"status":173,"finish_reason":174},"29",769,"67.47",{"id":372,"error":107,"extra":373,"score":148,"passed":4,"case_key":374,"cost_usd":107,"sample_idx":143,"input_tokens":375,"output_tokens":376,"has_trajectory":119,"duration_seconds":377},125277,{"status":173,"finish_reason":174},"30",39,512,"43.20",{"id":379,"error":107,"extra":380,"score":147,"passed":119,"case_key":381,"cost_usd":107,"sample_idx":143,"input_tokens":382,"output_tokens":383,"has_trajectory":119,"duration_seconds":384},125278,{"status":173,"finish_reason":174},"31",25,1027,"86.44",{"id":386,"error":107,"extra":387,"score":148,"passed":4,"case_key":388,"cost_usd":107,"sample_idx":143,"input_tokens":389,"output_tokens":390,"has_trajectory":119,"duration_seconds":391},125279,{"status":173,"finish_reason":174},"32",33,1130,"94.57",{"id":393,"error":107,"extra":394,"score":147,"passed":119,"case_key":395,"cost_usd":107,"sample_idx":143,"input_tokens":271,"output_tokens":396,"has_trajectory":119,"duration_seconds":397},125280,{"status":173,"finish_reason":174},"33",858,"74.16",{"id":399,"error":107,"extra":400,"score":147,"passed":119,"case_key":401,"cost_usd":107,"sample_idx":143,"input_tokens":211,"output_tokens":402,"has_trajectory":119,"duration_seconds":403},125281,{"status":173,"finish_reason":174},"34",305,"24.30",{"id":405,"error":107,"extra":406,"score":148,"passed":4,"case_key":407,"cost_usd":107,"sample_idx":143,"input_tokens":375,"output_tokens":408,"has_trajectory":119,"duration_seconds":409},125282,{"status":173,"finish_reason":174},"35",1572,"128.65",{"id":411,"error":107,"extra":412,"score":147,"passed":119,"case_key":413,"cost_usd":107,"sample_idx":143,"input_tokens":305,"output_tokens":414,"has_trajectory":119,"duration_seconds":415},125283,{"status":173,"finish_reason":174},"36",1636,"133.42",{"id":417,"error":107,"extra":418,"score":147,"passed":119,"case_key":419,"cost_usd":107,"sample_idx":143,"input_tokens":305,"output_tokens":420,"has_trajectory":119,"duration_seconds":421},125284,{"status":173,"finish_reason":174},"37",439,"36.58",{"id":423,"error":107,"extra":424,"score":147,"passed":119,"case_key":425,"cost_usd":107,"sample_idx":143,"input_tokens":271,"output_tokens":426,"has_trajectory":119,"duration_seconds":427},125285,{"status":173,"finish_reason":174},"38",664,"55.93",{"id":429,"error":107,"extra":430,"score":147,"passed":119,"case_key":431,"cost_usd":107,"sample_idx":143,"input_tokens":291,"output_tokens":432,"has_trajectory":119,"duration_seconds":433},125286,{"status":173,"finish_reason":174},"39",2578,"204.60",{"id":435,"error":107,"extra":436,"score":148,"passed":4,"case_key":437,"cost_usd":107,"sample_idx":143,"input_tokens":271,"output_tokens":438,"has_trajectory":119,"duration_seconds":439},125287,{"status":173,"finish_reason":174},"40",700,"59.29",{"id":441,"error":107,"extra":442,"score":148,"passed":4,"case_key":443,"cost_usd":107,"sample_idx":143,"input_tokens":389,"output_tokens":444,"has_trajectory":119,"duration_seconds":445},125288,{"status":173,"finish_reason":174},"41",16126,"1089.71",{"id":447,"error":107,"extra":448,"score":147,"passed":119,"case_key":449,"cost_usd":107,"sample_idx":143,"input_tokens":325,"output_tokens":450,"has_trajectory":119,"duration_seconds":451},125289,{"status":173,"finish_reason":174},"42",503,"42.31",{"id":453,"error":107,"extra":454,"score":148,"passed":4,"case_key":455,"cost_usd":107,"sample_idx":143,"input_tokens":305,"output_tokens":456,"has_trajectory":119,"duration_seconds":457},125290,{"status":173,"finish_reason":174},"43",1313,"110.14",{"id":459,"error":107,"extra":460,"score":147,"passed":119,"case_key":461,"cost_usd":107,"sample_idx":143,"input_tokens":106,"output_tokens":462,"has_trajectory":119,"duration_seconds":463},125291,{"status":173,"finish_reason":174},"44",381,"31.38",{"id":465,"error":107,"extra":466,"score":148,"passed":4,"case_key":467,"cost_usd":107,"sample_idx":143,"input_tokens":271,"output_tokens":468,"has_trajectory":119,"duration_seconds":469},125292,{"status":173,"finish_reason":174},"45",489,"41.12",{"id":471,"error":107,"extra":472,"score":148,"passed":4,"case_key":473,"cost_usd":107,"sample_idx":143,"input_tokens":190,"output_tokens":474,"has_trajectory":119,"duration_seconds":475},125293,{"status":173,"finish_reason":174},"46",693,"58.55",{"id":477,"error":107,"extra":478,"score":147,"passed":119,"case_key":479,"cost_usd":107,"sample_idx":143,"input_tokens":312,"output_tokens":480,"has_trajectory":119,"duration_seconds":481},125294,{"status":173,"finish_reason":174},"47",2488,"197.62",{"id":483,"error":107,"extra":484,"score":147,"passed":119,"case_key":485,"cost_usd":107,"sample_idx":143,"input_tokens":278,"output_tokens":486,"has_trajectory":119,"duration_seconds":487},125295,{"status":173,"finish_reason":174},"48",579,"52.57",{"id":489,"error":107,"extra":490,"score":148,"passed":4,"case_key":491,"cost_usd":107,"sample_idx":143,"input_tokens":492,"output_tokens":493,"has_trajectory":119,"duration_seconds":494},125296,{"status":173,"finish_reason":174},"49",53,818,"71.25",{"total":118,"failed":154,"passed":155,"run_id":106,"ungraded":143,"sample_idx":143,"trajectories":118}]