[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"api:\u002Fnav:{}":3,"api:\u002Frecords\u002F14:{}":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":142,"rank":43,"ranked_count":72,"samples":150,"other_harnesses":154,"distribution":155,"cases":166},{"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":43,"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},14,null,"0.4567",{},{"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},"0.950","1.00",{"top_k":114},-1,"OPT 1478395",32768,600,true,3,"2026-10-26",704064732,12837730,"970.09",32227494,{"access":126,"effort":127,"family":128,"is_tier":118,"hardware":107,"model_id":72,"provider":107,"data_date":5,"precision":107,"categories":129,"is_primary":118,"model_name":20,"model_slug":21,"short_name":20,"variant_id":119,"effort_rank":137,"input_price":107,"vendor_name":16,"vendor_slug":17,"architecture":107,"output_price":107,"overall_rank":54,"ranked_count":72,"release_date":138,"variant_name":139,"variant_slug":140,"vendor_order":141,"weights_repo":107,"missing_count":119,"overall_score":22,"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},"self_hosted","max","DeepSeek-V4",[130,132,134,136],{"name":41,"rank":72,"slug":42,"score":131,"expected":43,"available":54,"ranked_count":72},"2.857142857142860000000000",{"name":45,"rank":54,"slug":46,"score":133,"expected":47,"available":72,"ranked_count":72},"69.724166666666667500000000",{"name":49,"rank":119,"slug":50,"score":135,"expected":43,"available":54,"ranked_count":72},"45.670000000000000000000000",{"name":52,"rank":43,"slug":53,"score":135,"expected":54,"available":54,"ranked_count":72},6,"2026-08-13","DeepSeek-V4-Pro 自部署 max","deepseek-v4-pro-self-hosted-max",0,{"id":43,"name":87,"slug":88,"license":143,"metrics":144,"version":107,"is_active":118,"num_cases":117,"parent_id":107,"score_max":145,"score_min":146,"created_at":147,"is_agentic":118,"sort_order":141,"updated_at":147,"description":107,"metric_name":148,"homepage_url":107,"license_note":107,"scoring_method":107,"composite_weight":145,"higher_is_better":118,"bundle_size_bytes":149},"public",[],"1.0000","0.0000","2026-10-28T09:47:38.906402+08:00","Pass Rate",2028958067,[151],{"total":117,"failed":152,"passed":153,"run_id":106,"ungraded":141,"sample_idx":141,"trajectories":117},326,274,[],[156,159,160,163],{"name":36,"rank":54,"score":157,"run_id":158,"model_slug":37,"vendor_slug":33},"0.5250",41,{"name":20,"rank":43,"score":108,"run_id":106,"model_slug":21,"vendor_slug":17},{"name":12,"rank":119,"score":161,"run_id":162,"model_slug":13,"vendor_slug":9},"0.4150",114,{"name":28,"rank":72,"score":164,"run_id":165,"model_slug":29,"vendor_slug":25},"0.0350",59,{"restricted":4,"rows":167,"counts":537,"next_after":530},[168,178,185,192,199,206,214,222,229,236,243,250,257,264,271,278,285,292,300,307,315,323,330,337,344,351,358,365,373,381,389,396,404,412,419,426,434,441,449,456,463,470,478,485,493,500,507,514,522,529],{"id":169,"error":107,"extra":170,"score":173,"passed":4,"case_key":174,"cost_usd":107,"sample_idx":141,"input_tokens":175,"output_tokens":176,"has_trajectory":118,"duration_seconds":177},32423,{"status":171,"finish_reason":172},"completed","stop","0.6667","0",382380,12029,"763.13",{"id":179,"error":107,"extra":180,"score":145,"passed":118,"case_key":181,"cost_usd":107,"sample_idx":141,"input_tokens":182,"output_tokens":183,"has_trajectory":118,"duration_seconds":184},32424,{"status":171,"finish_reason":172},"1",1107889,15840,"1069.73",{"id":186,"error":107,"extra":187,"score":146,"passed":4,"case_key":188,"cost_usd":107,"sample_idx":141,"input_tokens":189,"output_tokens":190,"has_trajectory":118,"duration_seconds":191},32425,{"status":171,"finish_reason":172},"2",1204584,44032,"2573.71",{"id":193,"error":107,"extra":194,"score":146,"passed":4,"case_key":195,"cost_usd":107,"sample_idx":141,"input_tokens":196,"output_tokens":197,"has_trajectory":118,"duration_seconds":198},32426,{"status":171,"finish_reason":172},"3",2085162,20984,"1365.94",{"id":200,"error":107,"extra":201,"score":145,"passed":118,"case_key":202,"cost_usd":107,"sample_idx":141,"input_tokens":203,"output_tokens":204,"has_trajectory":118,"duration_seconds":205},32427,{"status":171,"finish_reason":172},"4",178913,9452,"607.56",{"id":207,"error":107,"extra":208,"score":209,"passed":4,"case_key":210,"cost_usd":107,"sample_idx":141,"input_tokens":211,"output_tokens":212,"has_trajectory":118,"duration_seconds":213},32428,{"status":171,"finish_reason":172},"0.1429","5",960815,20471,"1270.15",{"id":215,"error":107,"extra":216,"score":217,"passed":4,"case_key":218,"cost_usd":107,"sample_idx":141,"input_tokens":219,"output_tokens":220,"has_trajectory":118,"duration_seconds":221},32429,{"status":171,"finish_reason":172},"0.2000","6",388837,11940,"749.81",{"id":223,"error":107,"extra":224,"score":145,"passed":118,"case_key":225,"cost_usd":107,"sample_idx":141,"input_tokens":226,"output_tokens":227,"has_trajectory":118,"duration_seconds":228},32430,{"status":171,"finish_reason":172},"7",277084,14006,"870.87",{"id":230,"error":107,"extra":231,"score":145,"passed":118,"case_key":232,"cost_usd":107,"sample_idx":141,"input_tokens":233,"output_tokens":234,"has_trajectory":118,"duration_seconds":235},32431,{"status":171,"finish_reason":172},"8",596360,10522,"647.72",{"id":237,"error":107,"extra":238,"score":145,"passed":118,"case_key":239,"cost_usd":107,"sample_idx":141,"input_tokens":240,"output_tokens":241,"has_trajectory":118,"duration_seconds":242},32432,{"status":171,"finish_reason":172},"9",472728,12451,"788.01",{"id":244,"error":107,"extra":245,"score":145,"passed":118,"case_key":246,"cost_usd":107,"sample_idx":141,"input_tokens":247,"output_tokens":248,"has_trajectory":118,"duration_seconds":249},32433,{"status":171,"finish_reason":172},"10",74552,4197,"295.26",{"id":251,"error":107,"extra":252,"score":145,"passed":118,"case_key":253,"cost_usd":107,"sample_idx":141,"input_tokens":254,"output_tokens":255,"has_trajectory":118,"duration_seconds":256},32434,{"status":171,"finish_reason":172},"11",459847,16735,"1060.48",{"id":258,"error":107,"extra":259,"score":145,"passed":118,"case_key":260,"cost_usd":107,"sample_idx":141,"input_tokens":261,"output_tokens":262,"has_trajectory":118,"duration_seconds":263},32435,{"status":171,"finish_reason":172},"12",800096,10844,"687.39",{"id":265,"error":107,"extra":266,"score":145,"passed":118,"case_key":267,"cost_usd":107,"sample_idx":141,"input_tokens":268,"output_tokens":269,"has_trajectory":118,"duration_seconds":270},32436,{"status":171,"finish_reason":172},"13",148488,5100,"333.04",{"id":272,"error":107,"extra":273,"score":145,"passed":118,"case_key":274,"cost_usd":107,"sample_idx":141,"input_tokens":275,"output_tokens":276,"has_trajectory":118,"duration_seconds":277},32437,{"status":171,"finish_reason":172},"14",278196,10800,"655.22",{"id":279,"error":107,"extra":280,"score":173,"passed":4,"case_key":281,"cost_usd":107,"sample_idx":141,"input_tokens":282,"output_tokens":283,"has_trajectory":118,"duration_seconds":284},32438,{"status":171,"finish_reason":172},"15",11950918,55928,"3411.13",{"id":286,"error":107,"extra":287,"score":145,"passed":118,"case_key":288,"cost_usd":107,"sample_idx":141,"input_tokens":289,"output_tokens":290,"has_trajectory":118,"duration_seconds":291},32439,{"status":171,"finish_reason":172},"16",682770,20855,"1246.18",{"id":293,"error":107,"extra":294,"score":295,"passed":4,"case_key":296,"cost_usd":107,"sample_idx":141,"input_tokens":297,"output_tokens":298,"has_trajectory":118,"duration_seconds":299},32440,{"status":171,"finish_reason":172},"0.8333","17",784673,24029,"1409.11",{"id":301,"error":107,"extra":302,"score":173,"passed":4,"case_key":303,"cost_usd":107,"sample_idx":141,"input_tokens":304,"output_tokens":305,"has_trajectory":118,"duration_seconds":306},32441,{"status":171,"finish_reason":172},"18",645448,20778,"1261.12",{"id":308,"error":107,"extra":309,"score":310,"passed":4,"case_key":311,"cost_usd":107,"sample_idx":141,"input_tokens":312,"output_tokens":313,"has_trajectory":118,"duration_seconds":314},32442,{"status":171,"finish_reason":172},"0.8000","19",353452,11586,"751.51",{"id":316,"error":107,"extra":317,"score":318,"passed":4,"case_key":319,"cost_usd":107,"sample_idx":141,"input_tokens":320,"output_tokens":321,"has_trajectory":118,"duration_seconds":322},32443,{"status":171,"finish_reason":172},"0.5000","20",737085,28374,"1638.60",{"id":324,"error":107,"extra":325,"score":217,"passed":4,"case_key":326,"cost_usd":107,"sample_idx":141,"input_tokens":327,"output_tokens":328,"has_trajectory":118,"duration_seconds":329},32444,{"status":171,"finish_reason":172},"21",1883266,40293,"2286.04",{"id":331,"error":107,"extra":332,"score":173,"passed":4,"case_key":333,"cost_usd":107,"sample_idx":141,"input_tokens":334,"output_tokens":335,"has_trajectory":118,"duration_seconds":336},32445,{"status":171,"finish_reason":172},"22",391920,11026,"705.65",{"id":338,"error":107,"extra":339,"score":310,"passed":4,"case_key":340,"cost_usd":107,"sample_idx":141,"input_tokens":341,"output_tokens":342,"has_trajectory":118,"duration_seconds":343},32446,{"status":171,"finish_reason":172},"23",573252,10998,"714.95",{"id":345,"error":107,"extra":346,"score":145,"passed":118,"case_key":347,"cost_usd":107,"sample_idx":141,"input_tokens":348,"output_tokens":349,"has_trajectory":118,"duration_seconds":350},32447,{"status":171,"finish_reason":172},"24",432249,10229,"650.19",{"id":352,"error":107,"extra":353,"score":145,"passed":118,"case_key":354,"cost_usd":107,"sample_idx":141,"input_tokens":355,"output_tokens":356,"has_trajectory":118,"duration_seconds":357},32448,{"status":171,"finish_reason":172},"25",718966,13040,"842.44",{"id":359,"error":107,"extra":360,"score":145,"passed":118,"case_key":361,"cost_usd":107,"sample_idx":141,"input_tokens":362,"output_tokens":363,"has_trajectory":118,"duration_seconds":364},32449,{"status":171,"finish_reason":172},"26",162659,9324,"552.68",{"id":366,"error":107,"extra":367,"score":368,"passed":4,"case_key":369,"cost_usd":107,"sample_idx":141,"input_tokens":370,"output_tokens":371,"has_trajectory":118,"duration_seconds":372},32450,{"status":171,"finish_reason":172},"0.6250","27",993586,19519,"1181.30",{"id":374,"error":107,"extra":375,"score":376,"passed":4,"case_key":377,"cost_usd":107,"sample_idx":141,"input_tokens":378,"output_tokens":379,"has_trajectory":118,"duration_seconds":380},32451,{"status":171,"finish_reason":172},"0.8750","28",1563057,14168,"902.78",{"id":382,"error":107,"extra":383,"score":384,"passed":4,"case_key":385,"cost_usd":107,"sample_idx":141,"input_tokens":386,"output_tokens":387,"has_trajectory":118,"duration_seconds":388},32452,{"status":171,"finish_reason":172},"0.9000","29",478235,15774,"920.61",{"id":390,"error":107,"extra":391,"score":295,"passed":4,"case_key":392,"cost_usd":107,"sample_idx":141,"input_tokens":393,"output_tokens":394,"has_trajectory":118,"duration_seconds":395},32453,{"status":171,"finish_reason":172},"30",66635,4356,"286.27",{"id":397,"error":107,"extra":398,"score":399,"passed":4,"case_key":400,"cost_usd":107,"sample_idx":141,"input_tokens":401,"output_tokens":402,"has_trajectory":118,"duration_seconds":403},32454,{"status":171,"finish_reason":172},"0.9091","31",770002,11522,"722.36",{"id":405,"error":107,"extra":406,"score":407,"passed":4,"case_key":408,"cost_usd":107,"sample_idx":141,"input_tokens":409,"output_tokens":410,"has_trajectory":118,"duration_seconds":411},32455,{"status":171,"finish_reason":172},"0.3333","32",6418903,35416,"2085.90",{"id":413,"error":107,"extra":414,"score":173,"passed":4,"case_key":415,"cost_usd":107,"sample_idx":141,"input_tokens":416,"output_tokens":417,"has_trajectory":118,"duration_seconds":418},32456,{"status":171,"finish_reason":172},"33",1508085,34037,"1986.06",{"id":420,"error":107,"extra":421,"score":173,"passed":4,"case_key":422,"cost_usd":107,"sample_idx":141,"input_tokens":423,"output_tokens":424,"has_trajectory":118,"duration_seconds":425},32457,{"status":171,"finish_reason":172},"34",9209279,47719,"2858.32",{"id":427,"error":107,"extra":428,"score":429,"passed":4,"case_key":430,"cost_usd":107,"sample_idx":141,"input_tokens":431,"output_tokens":432,"has_trajectory":118,"duration_seconds":433},32458,{"status":171,"finish_reason":172},"0.1250","35",578714,20634,"1105.11",{"id":435,"error":107,"extra":436,"score":318,"passed":4,"case_key":437,"cost_usd":107,"sample_idx":141,"input_tokens":438,"output_tokens":439,"has_trajectory":118,"duration_seconds":440},32459,{"status":171,"finish_reason":172},"36",387618,14072,"818.20",{"id":442,"error":107,"extra":443,"score":444,"passed":4,"case_key":445,"cost_usd":107,"sample_idx":141,"input_tokens":446,"output_tokens":447,"has_trajectory":118,"duration_seconds":448},32460,{"status":171,"finish_reason":172},"0.4167","37",1027976,16861,"902.93",{"id":450,"error":107,"extra":451,"score":145,"passed":118,"case_key":452,"cost_usd":107,"sample_idx":141,"input_tokens":453,"output_tokens":454,"has_trajectory":118,"duration_seconds":455},32461,{"status":171,"finish_reason":172},"38",897392,15447,"882.86",{"id":457,"error":107,"extra":458,"score":145,"passed":118,"case_key":459,"cost_usd":107,"sample_idx":141,"input_tokens":460,"output_tokens":461,"has_trajectory":118,"duration_seconds":462},32462,{"status":171,"finish_reason":172},"39",460010,16435,"907.72",{"id":464,"error":107,"extra":465,"score":145,"passed":118,"case_key":466,"cost_usd":107,"sample_idx":141,"input_tokens":467,"output_tokens":468,"has_trajectory":118,"duration_seconds":469},32463,{"status":171,"finish_reason":172},"40",774764,15545,"916.31",{"id":471,"error":107,"extra":472,"score":473,"passed":4,"case_key":474,"cost_usd":107,"sample_idx":141,"input_tokens":475,"output_tokens":476,"has_trajectory":118,"duration_seconds":477},32464,{"status":171,"finish_reason":172},"0.7000","41",409526,19052,"1081.42",{"id":479,"error":107,"extra":480,"score":145,"passed":118,"case_key":481,"cost_usd":107,"sample_idx":141,"input_tokens":482,"output_tokens":483,"has_trajectory":118,"duration_seconds":484},32465,{"status":171,"finish_reason":172},"42",104781,3353,"188.41",{"id":486,"error":107,"extra":487,"score":488,"passed":4,"case_key":489,"cost_usd":107,"sample_idx":141,"input_tokens":490,"output_tokens":491,"has_trajectory":118,"duration_seconds":492},32466,{"status":171,"finish_reason":172},"0.7500","43",893146,13062,"752.14",{"id":494,"error":107,"extra":495,"score":145,"passed":118,"case_key":496,"cost_usd":107,"sample_idx":141,"input_tokens":497,"output_tokens":498,"has_trajectory":118,"duration_seconds":499},32467,{"status":171,"finish_reason":172},"44",11946511,40807,"2469.93",{"id":501,"error":107,"extra":502,"score":145,"passed":118,"case_key":503,"cost_usd":107,"sample_idx":141,"input_tokens":504,"output_tokens":505,"has_trajectory":118,"duration_seconds":506},32468,{"status":171,"finish_reason":172},"45",8366697,37338,"2346.03",{"id":508,"error":107,"extra":509,"score":145,"passed":118,"case_key":510,"cost_usd":107,"sample_idx":141,"input_tokens":511,"output_tokens":512,"has_trajectory":118,"duration_seconds":513},32469,{"status":171,"finish_reason":172},"46",2916672,22175,"1330.20",{"id":515,"error":107,"extra":516,"score":517,"passed":4,"case_key":518,"cost_usd":107,"sample_idx":141,"input_tokens":519,"output_tokens":520,"has_trajectory":118,"duration_seconds":521},32470,{"status":171,"finish_reason":172},"0.2500","47",2680460,35486,"1987.13",{"id":523,"error":107,"extra":524,"score":145,"passed":118,"case_key":525,"cost_usd":107,"sample_idx":141,"input_tokens":526,"output_tokens":527,"has_trajectory":118,"duration_seconds":528},32471,{"status":171,"finish_reason":172},"48",1776551,25008,"1576.29",{"id":530,"error":107,"extra":531,"score":532,"passed":4,"case_key":533,"cost_usd":107,"sample_idx":141,"input_tokens":534,"output_tokens":535,"has_trajectory":118,"duration_seconds":536},32472,{"status":171,"finish_reason":172},"0.7778","49",2036596,38422,"2086.22",{"total":117,"failed":152,"passed":153,"run_id":106,"ungraded":141,"sample_idx":141,"trajectories":117}]