[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"api:\u002Fnav:{}":3,"api:\u002Frecords\u002F60:{}":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":54,"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":117,"score_std":107,"harness_id":107,"has_bundle":118,"is_primary":118,"output_tps":107,"variant_id":119,"num_samples":54,"benchmark_id":120,"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},60,null,"0.8877",{},{"top_p":111,"recipe":107,"harness":107,"judge_model":107,"num_samples":54,"temperature":112,"extra_settings":113,"scoring_method":107,"harness_version":107,"framework_version":115,"max_output_tokens":116},"1.000","0.60",{"top_k":114},-1,"OPT 1478395",65536,12032,true,11,7,"2026-10-23",3433876,14673875,"107.58",21102835,{"access":127,"effort":128,"family":28,"is_tier":118,"hardware":107,"model_id":129,"provider":107,"data_date":130,"precision":107,"categories":131,"is_primary":118,"model_name":28,"model_slug":29,"short_name":28,"variant_id":119,"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":118,"is_open_weights":118,"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":120,"name":96,"slug":97,"license":145,"metrics":146,"version":107,"is_active":118,"num_cases":117,"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":118,"bundle_size_bytes":151},"public",[],"1.0000","0.0000","2026-10-28T09:47:38.906402+08:00","Accuracy",1829320613,[153],{"total":117,"failed":154,"passed":155,"run_id":106,"ungraded":143,"sample_idx":143,"trajectories":117},1351,10681,[],[158,159,162,165],{"name":28,"rank":54,"score":108,"run_id":106,"model_slug":29,"vendor_slug":25},{"name":20,"rank":43,"score":160,"run_id":161,"model_slug":21,"vendor_slug":17},"0.8713",15,{"name":12,"rank":129,"score":163,"run_id":164,"model_slug":13,"vendor_slug":9},"0.8516",117,{"name":36,"rank":72,"score":166,"run_id":167,"model_slug":37,"vendor_slug":33},"0.8507",42,{"restricted":4,"rows":169,"counts":504,"next_after":499},[170,179,186,193,200,207,214,221,228,235,242,249,256,263,269,273,280,286,293,300,307,314,320,327,334,341,347,354,361,368,374,381,388,395,402,409,416,423,430,436,443,450,457,464,469,473,479,485,491,498],{"id":171,"error":107,"extra":172,"score":147,"passed":118,"case_key":175,"cost_usd":107,"sample_idx":143,"input_tokens":176,"output_tokens":177,"has_trajectory":118,"duration_seconds":178},162158,{"status":173,"finish_reason":174},"completed","stop","0",258,566,"99.38",{"id":180,"error":107,"extra":181,"score":147,"passed":118,"case_key":182,"cost_usd":107,"sample_idx":143,"input_tokens":183,"output_tokens":184,"has_trajectory":118,"duration_seconds":185},162159,{"status":173,"finish_reason":174},"1",274,206,"57.62",{"id":187,"error":107,"extra":188,"score":147,"passed":118,"case_key":189,"cost_usd":107,"sample_idx":143,"input_tokens":190,"output_tokens":191,"has_trajectory":118,"duration_seconds":192},162160,{"status":173,"finish_reason":174},"2",294,433,"84.22",{"id":194,"error":107,"extra":195,"score":147,"passed":118,"case_key":196,"cost_usd":107,"sample_idx":143,"input_tokens":197,"output_tokens":198,"has_trajectory":118,"duration_seconds":199},162161,{"status":173,"finish_reason":174},"3",190,172,"53.80",{"id":201,"error":107,"extra":202,"score":147,"passed":118,"case_key":203,"cost_usd":107,"sample_idx":143,"input_tokens":204,"output_tokens":205,"has_trajectory":118,"duration_seconds":206},162162,{"status":173,"finish_reason":174},"4",289,177,"54.22",{"id":208,"error":107,"extra":209,"score":147,"passed":118,"case_key":210,"cost_usd":107,"sample_idx":143,"input_tokens":211,"output_tokens":212,"has_trajectory":118,"duration_seconds":213},162163,{"status":173,"finish_reason":174},"5",236,227,"59.94",{"id":215,"error":107,"extra":216,"score":147,"passed":118,"case_key":217,"cost_usd":107,"sample_idx":143,"input_tokens":218,"output_tokens":219,"has_trajectory":118,"duration_seconds":220},162164,{"status":173,"finish_reason":174},"6",211,145,"51.05",{"id":222,"error":107,"extra":223,"score":147,"passed":118,"case_key":224,"cost_usd":107,"sample_idx":143,"input_tokens":225,"output_tokens":226,"has_trajectory":118,"duration_seconds":227},162165,{"status":173,"finish_reason":174},"7",176,115,"47.53",{"id":229,"error":107,"extra":230,"score":147,"passed":118,"case_key":231,"cost_usd":107,"sample_idx":143,"input_tokens":232,"output_tokens":233,"has_trajectory":118,"duration_seconds":234},162166,{"status":173,"finish_reason":174},"8",184,349,"74.76",{"id":236,"error":107,"extra":237,"score":147,"passed":118,"case_key":238,"cost_usd":107,"sample_idx":143,"input_tokens":239,"output_tokens":240,"has_trajectory":118,"duration_seconds":241},162167,{"status":173,"finish_reason":174},"9",205,306,"69.25",{"id":243,"error":107,"extra":244,"score":147,"passed":118,"case_key":245,"cost_usd":107,"sample_idx":143,"input_tokens":246,"output_tokens":247,"has_trajectory":118,"duration_seconds":248},162168,{"status":173,"finish_reason":174},"10",189,113,"47.28",{"id":250,"error":107,"extra":251,"score":148,"passed":4,"case_key":252,"cost_usd":107,"sample_idx":143,"input_tokens":253,"output_tokens":254,"has_trajectory":118,"duration_seconds":255},162169,{"status":173,"finish_reason":174},"11",179,259,"63.47",{"id":257,"error":107,"extra":258,"score":147,"passed":118,"case_key":259,"cost_usd":107,"sample_idx":143,"input_tokens":260,"output_tokens":261,"has_trajectory":118,"duration_seconds":262},162170,{"status":173,"finish_reason":174},"12",183,325,"72.21",{"id":264,"error":107,"extra":265,"score":148,"passed":4,"case_key":266,"cost_usd":107,"sample_idx":143,"input_tokens":205,"output_tokens":267,"has_trajectory":118,"duration_seconds":268},162171,{"status":173,"finish_reason":174},"13",200,"57.01",{"id":270,"error":107,"extra":271,"score":147,"passed":118,"case_key":272,"cost_usd":107,"sample_idx":143,"input_tokens":260,"output_tokens":254,"has_trajectory":118,"duration_seconds":255},162172,{"status":173,"finish_reason":174},"14",{"id":274,"error":107,"extra":275,"score":147,"passed":118,"case_key":276,"cost_usd":107,"sample_idx":143,"input_tokens":277,"output_tokens":278,"has_trajectory":118,"duration_seconds":279},162173,{"status":173,"finish_reason":174},"15",210,94,"45.22",{"id":281,"error":107,"extra":282,"score":147,"passed":118,"case_key":283,"cost_usd":107,"sample_idx":143,"input_tokens":183,"output_tokens":284,"has_trajectory":118,"duration_seconds":285},162174,{"status":173,"finish_reason":174},"16",9462,"1031.04",{"id":287,"error":107,"extra":288,"score":147,"passed":118,"case_key":289,"cost_usd":107,"sample_idx":143,"input_tokens":290,"output_tokens":291,"has_trajectory":118,"duration_seconds":292},162175,{"status":173,"finish_reason":174},"17",235,477,"89.69",{"id":294,"error":107,"extra":295,"score":147,"passed":118,"case_key":296,"cost_usd":107,"sample_idx":143,"input_tokens":297,"output_tokens":298,"has_trajectory":118,"duration_seconds":299},162176,{"status":173,"finish_reason":174},"18",442,575,"100.53",{"id":301,"error":107,"extra":302,"score":147,"passed":118,"case_key":303,"cost_usd":107,"sample_idx":143,"input_tokens":304,"output_tokens":305,"has_trajectory":118,"duration_seconds":306},162177,{"status":173,"finish_reason":174},"19",247,198,"56.84",{"id":308,"error":107,"extra":309,"score":147,"passed":118,"case_key":310,"cost_usd":107,"sample_idx":143,"input_tokens":311,"output_tokens":312,"has_trajectory":118,"duration_seconds":313},162178,{"status":173,"finish_reason":174},"20",409,509,"93.20",{"id":315,"error":107,"extra":316,"score":147,"passed":118,"case_key":317,"cost_usd":107,"sample_idx":143,"input_tokens":318,"output_tokens":260,"has_trajectory":118,"duration_seconds":319},162179,{"status":173,"finish_reason":174},"21",295,"55.07",{"id":321,"error":107,"extra":322,"score":148,"passed":4,"case_key":323,"cost_usd":107,"sample_idx":143,"input_tokens":324,"output_tokens":325,"has_trajectory":118,"duration_seconds":326},162180,{"status":173,"finish_reason":174},"22",226,233,"60.81",{"id":328,"error":107,"extra":329,"score":147,"passed":118,"case_key":330,"cost_usd":107,"sample_idx":143,"input_tokens":331,"output_tokens":332,"has_trajectory":118,"duration_seconds":333},162181,{"status":173,"finish_reason":174},"23",219,155,"51.88",{"id":335,"error":107,"extra":336,"score":147,"passed":118,"case_key":337,"cost_usd":107,"sample_idx":143,"input_tokens":338,"output_tokens":339,"has_trajectory":118,"duration_seconds":340},162182,{"status":173,"finish_reason":174},"24",246,507,"93.03",{"id":342,"error":107,"extra":343,"score":147,"passed":118,"case_key":344,"cost_usd":107,"sample_idx":143,"input_tokens":345,"output_tokens":164,"has_trajectory":118,"duration_seconds":346},162183,{"status":173,"finish_reason":174},"25",489,"47.69",{"id":348,"error":107,"extra":349,"score":147,"passed":118,"case_key":350,"cost_usd":107,"sample_idx":143,"input_tokens":351,"output_tokens":352,"has_trajectory":118,"duration_seconds":353},162184,{"status":173,"finish_reason":174},"26",308,488,"90.67",{"id":355,"error":107,"extra":356,"score":147,"passed":118,"case_key":357,"cost_usd":107,"sample_idx":143,"input_tokens":358,"output_tokens":359,"has_trajectory":118,"duration_seconds":360},162185,{"status":173,"finish_reason":174},"27",201,108,"46.45",{"id":362,"error":107,"extra":363,"score":147,"passed":118,"case_key":364,"cost_usd":107,"sample_idx":143,"input_tokens":365,"output_tokens":366,"has_trajectory":118,"duration_seconds":367},162186,{"status":173,"finish_reason":174},"28",222,307,"69.33",{"id":369,"error":107,"extra":370,"score":147,"passed":118,"case_key":371,"cost_usd":107,"sample_idx":143,"input_tokens":372,"output_tokens":211,"has_trajectory":118,"duration_seconds":373},162187,{"status":173,"finish_reason":174},"29",217,"61.06",{"id":375,"error":107,"extra":376,"score":147,"passed":118,"case_key":377,"cost_usd":107,"sample_idx":143,"input_tokens":378,"output_tokens":379,"has_trajectory":118,"duration_seconds":380},162188,{"status":173,"finish_reason":174},"30",213,131,"49.45",{"id":382,"error":107,"extra":383,"score":147,"passed":118,"case_key":384,"cost_usd":107,"sample_idx":143,"input_tokens":385,"output_tokens":386,"has_trajectory":118,"duration_seconds":387},162189,{"status":173,"finish_reason":174},"31",283,354,"74.77",{"id":389,"error":107,"extra":390,"score":147,"passed":118,"case_key":391,"cost_usd":107,"sample_idx":143,"input_tokens":392,"output_tokens":393,"has_trajectory":118,"duration_seconds":394},162190,{"status":173,"finish_reason":174},"32",334,991,"148.73",{"id":396,"error":107,"extra":397,"score":147,"passed":118,"case_key":398,"cost_usd":107,"sample_idx":143,"input_tokens":399,"output_tokens":400,"has_trajectory":118,"duration_seconds":401},162191,{"status":173,"finish_reason":174},"33",419,293,"67.73",{"id":403,"error":107,"extra":404,"score":147,"passed":118,"case_key":405,"cost_usd":107,"sample_idx":143,"input_tokens":406,"output_tokens":407,"has_trajectory":118,"duration_seconds":408},162192,{"status":173,"finish_reason":174},"34",230,284,"66.97",{"id":410,"error":107,"extra":411,"score":147,"passed":118,"case_key":412,"cost_usd":107,"sample_idx":143,"input_tokens":413,"output_tokens":414,"has_trajectory":118,"duration_seconds":415},162193,{"status":173,"finish_reason":174},"35",279,504,"92.65",{"id":417,"error":107,"extra":418,"score":147,"passed":118,"case_key":419,"cost_usd":107,"sample_idx":143,"input_tokens":420,"output_tokens":421,"has_trajectory":118,"duration_seconds":422},162194,{"status":173,"finish_reason":174},"36",209,561,"98.49",{"id":424,"error":107,"extra":425,"score":147,"passed":118,"case_key":426,"cost_usd":107,"sample_idx":143,"input_tokens":427,"output_tokens":428,"has_trajectory":118,"duration_seconds":429},162195,{"status":173,"finish_reason":174},"37",215,134,"49.57",{"id":431,"error":107,"extra":432,"score":147,"passed":118,"case_key":433,"cost_usd":107,"sample_idx":143,"input_tokens":434,"output_tokens":254,"has_trajectory":118,"duration_seconds":435},162196,{"status":173,"finish_reason":174},"38",353,"63.46",{"id":437,"error":107,"extra":438,"score":147,"passed":118,"case_key":439,"cost_usd":107,"sample_idx":143,"input_tokens":440,"output_tokens":441,"has_trajectory":118,"duration_seconds":442},162197,{"status":173,"finish_reason":174},"39",297,5287,"591.25",{"id":444,"error":107,"extra":445,"score":147,"passed":118,"case_key":446,"cost_usd":107,"sample_idx":143,"input_tokens":447,"output_tokens":448,"has_trajectory":118,"duration_seconds":449},162198,{"status":173,"finish_reason":174},"40",192,361,"76.21",{"id":451,"error":107,"extra":452,"score":147,"passed":118,"case_key":453,"cost_usd":107,"sample_idx":143,"input_tokens":454,"output_tokens":455,"has_trajectory":118,"duration_seconds":456},162199,{"status":173,"finish_reason":174},"41",245,174,"53.92",{"id":458,"error":107,"extra":459,"score":147,"passed":118,"case_key":460,"cost_usd":107,"sample_idx":143,"input_tokens":461,"output_tokens":462,"has_trajectory":118,"duration_seconds":463},162200,{"status":173,"finish_reason":174},"42",218,541,"96.84",{"id":465,"error":107,"extra":466,"score":148,"passed":4,"case_key":468,"cost_usd":107,"sample_idx":143,"input_tokens":107,"output_tokens":107,"has_trajectory":118,"duration_seconds":107},162201,{"status":467,"finish_reason":107},"failed","43",{"id":470,"error":107,"extra":471,"score":147,"passed":118,"case_key":472,"cost_usd":107,"sample_idx":143,"input_tokens":183,"output_tokens":212,"has_trajectory":118,"duration_seconds":213},162202,{"status":173,"finish_reason":174},"44",{"id":474,"error":107,"extra":475,"score":147,"passed":118,"case_key":476,"cost_usd":107,"sample_idx":143,"input_tokens":184,"output_tokens":477,"has_trajectory":118,"duration_seconds":478},162203,{"status":173,"finish_reason":174},"45",412,"81.75",{"id":480,"error":107,"extra":481,"score":147,"passed":118,"case_key":482,"cost_usd":107,"sample_idx":143,"input_tokens":407,"output_tokens":483,"has_trajectory":118,"duration_seconds":484},162204,{"status":173,"finish_reason":174},"46",457,"86.51",{"id":486,"error":107,"extra":487,"score":147,"passed":118,"case_key":488,"cost_usd":107,"sample_idx":143,"input_tokens":277,"output_tokens":489,"has_trajectory":118,"duration_seconds":490},162205,{"status":173,"finish_reason":174},"47",96,"45.50",{"id":492,"error":107,"extra":493,"score":147,"passed":118,"case_key":494,"cost_usd":107,"sample_idx":143,"input_tokens":495,"output_tokens":496,"has_trajectory":118,"duration_seconds":497},162206,{"status":173,"finish_reason":174},"48",387,391,"46.94",{"id":499,"error":107,"extra":500,"score":147,"passed":118,"case_key":501,"cost_usd":107,"sample_idx":143,"input_tokens":406,"output_tokens":502,"has_trajectory":118,"duration_seconds":503},162207,{"status":173,"finish_reason":174},"49",484,"58.02",{"total":117,"failed":154,"passed":155,"run_id":106,"ungraded":143,"sample_idx":143,"trajectories":117}]