[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"api:\u002Fnav:{}":3,"api:\u002Frecords\u002F61:{}":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":126,"benchmark":144,"rank":43,"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":120,"num_samples":54,"benchmark_id":54,"evaluated_at":121,"harness_name":107,"harness_slug":107,"input_tokens":122,"ttft_seconds":107,"output_tokens":123,"parent_run_id":107,"harness_version":107,"avg_case_seconds":124,"reasoning_tokens":107,"cost_per_case_usd":107,"trajectory_bundle_size_bytes":125},61,null,"0.4460",{},{"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,11,"2026-10-22",107860,3168580,"349.41",3690434,{"access":127,"effort":128,"family":28,"is_tier":119,"hardware":107,"model_id":129,"provider":107,"data_date":130,"precision":107,"categories":131,"is_primary":119,"model_name":28,"model_slug":29,"short_name":28,"variant_id":120,"effort_rank":139,"input_price":107,"vendor_name":24,"vendor_slug":25,"architecture":107,"output_price":107,"overall_rank":129,"ranked_count":72,"release_date":140,"variant_name":141,"variant_slug":142,"vendor_order":143,"weights_repo":107,"missing_count":129,"overall_score":30,"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",3,"2026-10-24",[132,134,136,138],{"name":41,"rank":43,"slug":42,"score":133,"expected":43,"available":54,"ranked_count":72},"65.051903114186850000000000",{"name":45,"rank":43,"slug":46,"score":135,"expected":47,"available":72,"ranked_count":72},"67.050833333333332500000000",{"name":49,"rank":72,"slug":50,"score":137,"expected":43,"available":54,"ranked_count":72},"3.500000000000000000000000",{"name":52,"rank":72,"slug":53,"score":137,"expected":54,"available":54,"ranked_count":72},6,"2026-07-16","Kimi-K3 官方 API max","kimi-k3-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},554,446,[],[158,161,162,165],{"name":20,"rank":54,"score":159,"run_id":160,"model_slug":21,"vendor_slug":17},"0.5710",16,{"name":28,"rank":43,"score":108,"run_id":106,"model_slug":29,"vendor_slug":25},{"name":36,"rank":129,"score":163,"run_id":164,"model_slug":37,"vendor_slug":33},"0.4330",43,{"name":12,"rank":72,"score":166,"run_id":167,"model_slug":13,"vendor_slug":9},"0.1110",119,{"restricted":4,"rows":169,"counts":493,"next_after":487},[170,179,186,193,200,207,214,221,228,235,242,249,255,261,268,275,282,289,296,303,309,316,322,329,334,340,346,352,359,365,371,377,384,390,396,402,408,414,420,426,432,438,444,450,456,462,468,474,480,486],{"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},174190,{"status":173,"finish_reason":174},"completed","stop","0",110,2089,"255.84",{"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},174191,{"status":173,"finish_reason":174},"1",108,248,"43.27",{"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},174192,{"status":173,"finish_reason":174},"2",107,2227,"270.67",{"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},174193,{"status":173,"finish_reason":174},"3",113,645,"89.26",{"id":201,"error":107,"extra":202,"score":147,"passed":119,"case_key":203,"cost_usd":107,"sample_idx":143,"input_tokens":204,"output_tokens":205,"has_trajectory":119,"duration_seconds":206},174194,{"status":173,"finish_reason":174},"4",122,10164,"1088.09",{"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},174195,{"status":173,"finish_reason":174},"5",104,752,"101.09",{"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},174196,{"status":173,"finish_reason":174},"6",105,6454,"688.80",{"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},174197,{"status":173,"finish_reason":174},"7",111,4049,"571.97",{"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},174198,{"status":173,"finish_reason":174},"8",116,1218,"156.86",{"id":236,"error":107,"extra":237,"score":148,"passed":4,"case_key":238,"cost_usd":107,"sample_idx":143,"input_tokens":239,"output_tokens":240,"has_trajectory":119,"duration_seconds":241},174199,{"status":173,"finish_reason":174},"9",109,748,"100.75",{"id":243,"error":107,"extra":244,"score":148,"passed":4,"case_key":245,"cost_usd":107,"sample_idx":143,"input_tokens":246,"output_tokens":247,"has_trajectory":119,"duration_seconds":248},174200,{"status":173,"finish_reason":174},"10",144,8088,"863.86",{"id":250,"error":107,"extra":251,"score":148,"passed":4,"case_key":252,"cost_usd":107,"sample_idx":143,"input_tokens":239,"output_tokens":253,"has_trajectory":119,"duration_seconds":254},174201,{"status":173,"finish_reason":174},"11",373,"57.98",{"id":256,"error":107,"extra":257,"score":148,"passed":4,"case_key":258,"cost_usd":107,"sample_idx":143,"input_tokens":259,"output_tokens":260,"has_trajectory":119,"duration_seconds":227},174202,{"status":173,"finish_reason":174},"12",106,4857,{"id":262,"error":107,"extra":263,"score":147,"passed":119,"case_key":264,"cost_usd":107,"sample_idx":143,"input_tokens":265,"output_tokens":266,"has_trajectory":119,"duration_seconds":267},174203,{"status":173,"finish_reason":174},"13",102,225,"40.44",{"id":269,"error":107,"extra":270,"score":148,"passed":4,"case_key":271,"cost_usd":107,"sample_idx":143,"input_tokens":272,"output_tokens":273,"has_trajectory":119,"duration_seconds":274},174204,{"status":173,"finish_reason":174},"14",99,168,"34.18",{"id":276,"error":107,"extra":277,"score":147,"passed":119,"case_key":278,"cost_usd":107,"sample_idx":143,"input_tokens":279,"output_tokens":280,"has_trajectory":119,"duration_seconds":281},174205,{"status":173,"finish_reason":174},"15",97,403,"62.77",{"id":283,"error":107,"extra":284,"score":147,"passed":119,"case_key":285,"cost_usd":107,"sample_idx":143,"input_tokens":286,"output_tokens":287,"has_trajectory":119,"duration_seconds":288},174206,{"status":173,"finish_reason":174},"16",100,4035,"571.78",{"id":290,"error":107,"extra":291,"score":148,"passed":4,"case_key":292,"cost_usd":107,"sample_idx":143,"input_tokens":293,"output_tokens":294,"has_trajectory":119,"duration_seconds":295},174207,{"status":173,"finish_reason":174},"17",101,3454,"407.50",{"id":297,"error":107,"extra":298,"score":147,"passed":119,"case_key":299,"cost_usd":107,"sample_idx":143,"input_tokens":300,"output_tokens":301,"has_trajectory":119,"duration_seconds":302},174208,{"status":173,"finish_reason":174},"18",132,3967,"464.42",{"id":304,"error":107,"extra":305,"score":147,"passed":119,"case_key":306,"cost_usd":107,"sample_idx":143,"input_tokens":225,"output_tokens":307,"has_trajectory":119,"duration_seconds":308},174209,{"status":173,"finish_reason":174},"19",9679,"1037.20",{"id":310,"error":107,"extra":311,"score":147,"passed":119,"case_key":312,"cost_usd":107,"sample_idx":143,"input_tokens":313,"output_tokens":314,"has_trajectory":119,"duration_seconds":315},174210,{"status":173,"finish_reason":174},"20",96,490,"72.97",{"id":317,"error":107,"extra":318,"score":148,"passed":4,"case_key":319,"cost_usd":107,"sample_idx":143,"input_tokens":259,"output_tokens":320,"has_trajectory":119,"duration_seconds":321},174211,{"status":173,"finish_reason":174},"21",832,"112.76",{"id":323,"error":107,"extra":324,"score":147,"passed":119,"case_key":325,"cost_usd":107,"sample_idx":143,"input_tokens":326,"output_tokens":327,"has_trajectory":119,"duration_seconds":328},174212,{"status":173,"finish_reason":174},"22",103,4067,"571.96",{"id":330,"error":107,"extra":331,"score":147,"passed":119,"case_key":332,"cost_usd":107,"sample_idx":143,"input_tokens":211,"output_tokens":333,"has_trajectory":119,"duration_seconds":328},174213,{"status":173,"finish_reason":174},"23",4573,{"id":335,"error":107,"extra":336,"score":148,"passed":4,"case_key":337,"cost_usd":107,"sample_idx":143,"input_tokens":326,"output_tokens":338,"has_trajectory":119,"duration_seconds":339},174214,{"status":173,"finish_reason":174},"24",2112,"243.74",{"id":341,"error":107,"extra":342,"score":147,"passed":119,"case_key":343,"cost_usd":107,"sample_idx":143,"input_tokens":286,"output_tokens":344,"has_trajectory":119,"duration_seconds":345},174215,{"status":173,"finish_reason":174},"25",10264,"1083.25",{"id":347,"error":107,"extra":348,"score":148,"passed":4,"case_key":349,"cost_usd":107,"sample_idx":143,"input_tokens":176,"output_tokens":350,"has_trajectory":119,"duration_seconds":351},174216,{"status":173,"finish_reason":174},"26",804,"94.84",{"id":353,"error":107,"extra":354,"score":148,"passed":4,"case_key":355,"cost_usd":107,"sample_idx":143,"input_tokens":356,"output_tokens":357,"has_trajectory":119,"duration_seconds":358},174217,{"status":173,"finish_reason":174},"27",112,2966,"336.64",{"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},174218,{"status":173,"finish_reason":174},"28",967,"113.64",{"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},174219,{"status":173,"finish_reason":174},"29",3882,"498.96",{"id":372,"error":107,"extra":373,"score":148,"passed":4,"case_key":374,"cost_usd":107,"sample_idx":143,"input_tokens":356,"output_tokens":375,"has_trajectory":119,"duration_seconds":376},174220,{"status":173,"finish_reason":174},"30",639,"76.97",{"id":378,"error":107,"extra":379,"score":147,"passed":119,"case_key":380,"cost_usd":107,"sample_idx":143,"input_tokens":381,"output_tokens":382,"has_trajectory":119,"duration_seconds":383},174221,{"status":173,"finish_reason":174},"31",98,1565,"180.18",{"id":385,"error":107,"extra":386,"score":147,"passed":119,"case_key":387,"cost_usd":107,"sample_idx":143,"input_tokens":259,"output_tokens":388,"has_trajectory":119,"duration_seconds":389},174222,{"status":173,"finish_reason":174},"32",654,"77.56",{"id":391,"error":107,"extra":392,"score":148,"passed":4,"case_key":393,"cost_usd":107,"sample_idx":143,"input_tokens":286,"output_tokens":394,"has_trajectory":119,"duration_seconds":395},174223,{"status":173,"finish_reason":174},"33",1026,"120.75",{"id":397,"error":107,"extra":398,"score":147,"passed":119,"case_key":399,"cost_usd":107,"sample_idx":143,"input_tokens":218,"output_tokens":400,"has_trajectory":119,"duration_seconds":401},174224,{"status":173,"finish_reason":174},"34",3522,"433.77",{"id":403,"error":107,"extra":404,"score":147,"passed":119,"case_key":405,"cost_usd":107,"sample_idx":143,"input_tokens":356,"output_tokens":406,"has_trajectory":119,"duration_seconds":407},174225,{"status":173,"finish_reason":174},"35",4454,"459.55",{"id":409,"error":107,"extra":410,"score":147,"passed":119,"case_key":411,"cost_usd":107,"sample_idx":143,"input_tokens":183,"output_tokens":412,"has_trajectory":119,"duration_seconds":413},174226,{"status":173,"finish_reason":174},"36",11279,"1196.75",{"id":415,"error":107,"extra":416,"score":147,"passed":119,"case_key":417,"cost_usd":107,"sample_idx":143,"input_tokens":259,"output_tokens":418,"has_trajectory":119,"duration_seconds":419},174227,{"status":173,"finish_reason":174},"37",904,"114.37",{"id":421,"error":107,"extra":422,"score":147,"passed":119,"case_key":423,"cost_usd":107,"sample_idx":143,"input_tokens":286,"output_tokens":424,"has_trajectory":119,"duration_seconds":425},174228,{"status":173,"finish_reason":174},"38",14398,"1510.52",{"id":427,"error":107,"extra":428,"score":147,"passed":119,"case_key":429,"cost_usd":107,"sample_idx":143,"input_tokens":293,"output_tokens":430,"has_trajectory":119,"duration_seconds":431},174229,{"status":173,"finish_reason":174},"39",7529,"784.93",{"id":433,"error":107,"extra":434,"score":148,"passed":4,"case_key":435,"cost_usd":107,"sample_idx":143,"input_tokens":286,"output_tokens":436,"has_trajectory":119,"duration_seconds":437},174230,{"status":173,"finish_reason":174},"40",2844,"315.99",{"id":439,"error":107,"extra":440,"score":147,"passed":119,"case_key":441,"cost_usd":107,"sample_idx":143,"input_tokens":259,"output_tokens":442,"has_trajectory":119,"duration_seconds":443},174231,{"status":173,"finish_reason":174},"41",721,"91.30",{"id":445,"error":107,"extra":446,"score":147,"passed":119,"case_key":447,"cost_usd":107,"sample_idx":143,"input_tokens":265,"output_tokens":448,"has_trajectory":119,"duration_seconds":449},174232,{"status":173,"finish_reason":174},"42",3640,"363.92",{"id":451,"error":107,"extra":452,"score":148,"passed":4,"case_key":453,"cost_usd":107,"sample_idx":143,"input_tokens":239,"output_tokens":454,"has_trajectory":119,"duration_seconds":455},174233,{"status":173,"finish_reason":174},"43",349,"48.93",{"id":457,"error":107,"extra":458,"score":147,"passed":119,"case_key":459,"cost_usd":107,"sample_idx":143,"input_tokens":232,"output_tokens":460,"has_trajectory":119,"duration_seconds":461},174234,{"status":173,"finish_reason":174},"44",887,"103.70",{"id":463,"error":107,"extra":464,"score":147,"passed":119,"case_key":465,"cost_usd":107,"sample_idx":143,"input_tokens":286,"output_tokens":466,"has_trajectory":119,"duration_seconds":467},174235,{"status":173,"finish_reason":174},"45",5435,"549.89",{"id":469,"error":107,"extra":470,"score":148,"passed":4,"case_key":471,"cost_usd":107,"sample_idx":143,"input_tokens":259,"output_tokens":472,"has_trajectory":119,"duration_seconds":473},174236,{"status":173,"finish_reason":174},"46",1825,"209.86",{"id":475,"error":107,"extra":476,"score":147,"passed":119,"case_key":477,"cost_usd":107,"sample_idx":143,"input_tokens":279,"output_tokens":478,"has_trajectory":119,"duration_seconds":479},174237,{"status":173,"finish_reason":174},"47",7598,"779.39",{"id":481,"error":107,"extra":482,"score":148,"passed":4,"case_key":483,"cost_usd":107,"sample_idx":143,"input_tokens":279,"output_tokens":484,"has_trajectory":119,"duration_seconds":485},174238,{"status":173,"finish_reason":174},"48",1668,"177.00",{"id":487,"error":107,"extra":488,"score":148,"passed":4,"case_key":489,"cost_usd":107,"sample_idx":143,"input_tokens":490,"output_tokens":491,"has_trajectory":119,"duration_seconds":492},174239,{"status":173,"finish_reason":174},"49",127,13746,"1426.78",{"total":118,"failed":154,"passed":155,"run_id":106,"ungraded":143,"sample_idx":143,"trajectories":118}]