[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"api:\u002Fnav:{}":3,"api:\u002Frecords\u002F12:{}":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":143,"rank":120,"ranked_count":72,"samples":151,"other_harnesses":164,"distribution":165,"cases":176},{"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":72,"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},12,null,"0.7550",{},{"top_p":111,"recipe":107,"harness":107,"judge_model":112,"num_samples":72,"temperature":113,"extra_settings":114,"scoring_method":107,"harness_version":107,"framework_version":116,"max_output_tokens":117},"1.000","Qwen3-235B-A22B","0.60",{"top_k":115},-1,"OPT 1478395",16384,100,true,3,"2026-10-26",38197780,1371986,"174.13",52355215,{"access":127,"effort":128,"family":129,"is_tier":119,"hardware":107,"model_id":72,"provider":107,"data_date":5,"precision":107,"categories":130,"is_primary":119,"model_name":20,"model_slug":21,"short_name":20,"variant_id":120,"effort_rank":138,"input_price":107,"vendor_name":16,"vendor_slug":17,"architecture":107,"output_price":107,"overall_rank":54,"ranked_count":72,"release_date":139,"variant_name":140,"variant_slug":141,"vendor_order":142,"weights_repo":107,"missing_count":120,"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":119,"is_open_weights":119,"inference_engine":107},"self_hosted","max","DeepSeek-V4",[131,133,135,137],{"name":41,"rank":72,"slug":42,"score":132,"expected":43,"available":54,"ranked_count":72},"2.857142857142860000000000",{"name":45,"rank":54,"slug":46,"score":134,"expected":47,"available":72,"ranked_count":72},"69.724166666666667500000000",{"name":49,"rank":120,"slug":50,"score":136,"expected":43,"available":54,"ranked_count":72},"45.670000000000000000000000",{"name":52,"rank":43,"slug":53,"score":136,"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":120,"name":81,"slug":82,"license":144,"metrics":145,"version":107,"is_active":119,"num_cases":118,"parent_id":107,"score_max":146,"score_min":147,"created_at":148,"is_agentic":4,"sort_order":142,"updated_at":148,"description":107,"metric_name":149,"homepage_url":107,"license_note":107,"scoring_method":107,"composite_weight":146,"higher_is_better":119,"bundle_size_bytes":150},"public",[],"1.0000","0.0000","2026-10-28T09:47:38.906402+08:00","Accuracy",3304837814,[152,155,158,161],{"total":118,"failed":153,"passed":154,"run_id":106,"ungraded":142,"sample_idx":142,"trajectories":118},26,74,{"total":118,"failed":156,"passed":157,"run_id":106,"ungraded":142,"sample_idx":54,"trajectories":118},21,79,{"total":118,"failed":159,"passed":160,"run_id":106,"ungraded":142,"sample_idx":43,"trajectories":118},27,73,{"total":118,"failed":162,"passed":163,"run_id":106,"ungraded":142,"sample_idx":120,"trajectories":118},24,76,[],[166,169,172,173],{"name":28,"rank":54,"score":167,"run_id":168,"model_slug":29,"vendor_slug":25},"0.8300",57,{"name":12,"rank":43,"score":170,"run_id":171,"model_slug":13,"vendor_slug":9},"0.8125",112,{"name":20,"rank":120,"score":108,"run_id":106,"model_slug":21,"vendor_slug":17},{"name":36,"rank":72,"score":174,"run_id":175,"model_slug":37,"vendor_slug":33},"0.6525",39,{"restricted":4,"rows":177,"counts":530,"next_after":525},[178,187,194,201,208,215,222,229,236,243,250,257,264,271,278,285,292,299,306,313,320,327,334,341,348,355,362,369,376,384,391,398,405,412,419,426,433,440,447,454,461,468,475,482,489,496,503,510,517,524],{"id":179,"error":107,"extra":180,"score":146,"passed":119,"case_key":183,"cost_usd":107,"sample_idx":142,"input_tokens":184,"output_tokens":185,"has_trajectory":119,"duration_seconds":186},31423,{"status":181,"finish_reason":182},"completed","stop","0",94027,454,"33.58",{"id":188,"error":107,"extra":189,"score":146,"passed":119,"case_key":190,"cost_usd":107,"sample_idx":142,"input_tokens":191,"output_tokens":192,"has_trajectory":119,"duration_seconds":193},31427,{"status":181,"finish_reason":182},"1",94020,4287,"261.16",{"id":195,"error":107,"extra":196,"score":146,"passed":119,"case_key":197,"cost_usd":107,"sample_idx":142,"input_tokens":198,"output_tokens":199,"has_trajectory":119,"duration_seconds":200},31431,{"status":181,"finish_reason":182},"2",94010,1165,"84.75",{"id":202,"error":107,"extra":203,"score":146,"passed":119,"case_key":204,"cost_usd":107,"sample_idx":142,"input_tokens":205,"output_tokens":206,"has_trajectory":119,"duration_seconds":207},31435,{"status":181,"finish_reason":182},"3",112341,683,"51.39",{"id":209,"error":107,"extra":210,"score":146,"passed":119,"case_key":211,"cost_usd":107,"sample_idx":142,"input_tokens":212,"output_tokens":213,"has_trajectory":119,"duration_seconds":214},31439,{"status":181,"finish_reason":182},"4",112342,1725,"117.22",{"id":216,"error":107,"extra":217,"score":147,"passed":4,"case_key":218,"cost_usd":107,"sample_idx":142,"input_tokens":219,"output_tokens":220,"has_trajectory":119,"duration_seconds":221},31443,{"status":181,"finish_reason":182},"5",71333,1537,"93.60",{"id":223,"error":107,"extra":224,"score":146,"passed":119,"case_key":225,"cost_usd":107,"sample_idx":142,"input_tokens":226,"output_tokens":227,"has_trajectory":119,"duration_seconds":228},31447,{"status":181,"finish_reason":182},"6",71345,467,"24.39",{"id":230,"error":107,"extra":231,"score":146,"passed":119,"case_key":232,"cost_usd":107,"sample_idx":142,"input_tokens":233,"output_tokens":234,"has_trajectory":119,"duration_seconds":235},31451,{"status":181,"finish_reason":182},"7",71382,1183,"66.70",{"id":237,"error":107,"extra":238,"score":146,"passed":119,"case_key":239,"cost_usd":107,"sample_idx":142,"input_tokens":240,"output_tokens":241,"has_trajectory":119,"duration_seconds":242},31455,{"status":181,"finish_reason":182},"8",71317,4164,"227.09",{"id":244,"error":107,"extra":245,"score":146,"passed":119,"case_key":246,"cost_usd":107,"sample_idx":142,"input_tokens":247,"output_tokens":248,"has_trajectory":119,"duration_seconds":249},31459,{"status":181,"finish_reason":182},"9",73319,6418,"378.02",{"id":251,"error":107,"extra":252,"score":146,"passed":119,"case_key":253,"cost_usd":107,"sample_idx":142,"input_tokens":254,"output_tokens":255,"has_trajectory":119,"duration_seconds":256},31463,{"status":181,"finish_reason":182},"10",73329,1358,"90.29",{"id":258,"error":107,"extra":259,"score":147,"passed":4,"case_key":260,"cost_usd":107,"sample_idx":142,"input_tokens":261,"output_tokens":262,"has_trajectory":119,"duration_seconds":263},31467,{"status":181,"finish_reason":182},"11",73328,377,"23.69",{"id":265,"error":107,"extra":266,"score":146,"passed":119,"case_key":267,"cost_usd":107,"sample_idx":142,"input_tokens":268,"output_tokens":269,"has_trajectory":119,"duration_seconds":270},31471,{"status":181,"finish_reason":182},"12",73303,335,"18.40",{"id":272,"error":107,"extra":273,"score":146,"passed":119,"case_key":274,"cost_usd":107,"sample_idx":142,"input_tokens":275,"output_tokens":276,"has_trajectory":119,"duration_seconds":277},31475,{"status":181,"finish_reason":182},"13",73808,5407,"296.39",{"id":279,"error":107,"extra":280,"score":146,"passed":119,"case_key":281,"cost_usd":107,"sample_idx":142,"input_tokens":282,"output_tokens":283,"has_trajectory":119,"duration_seconds":284},31479,{"status":181,"finish_reason":182},"14",78079,772,"45.30",{"id":286,"error":107,"extra":287,"score":146,"passed":119,"case_key":288,"cost_usd":107,"sample_idx":142,"input_tokens":289,"output_tokens":290,"has_trajectory":119,"duration_seconds":291},31483,{"status":181,"finish_reason":182},"15",78191,13949,"771.61",{"id":293,"error":107,"extra":294,"score":146,"passed":119,"case_key":295,"cost_usd":107,"sample_idx":142,"input_tokens":296,"output_tokens":297,"has_trajectory":119,"duration_seconds":298},31487,{"status":181,"finish_reason":182},"16",78098,7447,"377.10",{"id":300,"error":107,"extra":301,"score":147,"passed":4,"case_key":302,"cost_usd":107,"sample_idx":142,"input_tokens":303,"output_tokens":304,"has_trajectory":119,"duration_seconds":305},31491,{"status":181,"finish_reason":182},"17",74918,3733,"215.80",{"id":307,"error":107,"extra":308,"score":147,"passed":4,"case_key":309,"cost_usd":107,"sample_idx":142,"input_tokens":310,"output_tokens":311,"has_trajectory":119,"duration_seconds":312},31495,{"status":181,"finish_reason":182},"18",96344,7010,"334.21",{"id":314,"error":107,"extra":315,"score":146,"passed":119,"case_key":316,"cost_usd":107,"sample_idx":142,"input_tokens":317,"output_tokens":318,"has_trajectory":119,"duration_seconds":319},31499,{"status":181,"finish_reason":182},"19",96346,5428,"264.99",{"id":321,"error":107,"extra":322,"score":146,"passed":119,"case_key":323,"cost_usd":107,"sample_idx":142,"input_tokens":324,"output_tokens":325,"has_trajectory":119,"duration_seconds":326},31503,{"status":181,"finish_reason":182},"20",96301,441,"26.82",{"id":328,"error":107,"extra":329,"score":147,"passed":4,"case_key":330,"cost_usd":107,"sample_idx":142,"input_tokens":331,"output_tokens":332,"has_trajectory":119,"duration_seconds":333},31507,{"status":181,"finish_reason":182},"21",95433,1753,"107.60",{"id":335,"error":107,"extra":336,"score":146,"passed":119,"case_key":337,"cost_usd":107,"sample_idx":142,"input_tokens":338,"output_tokens":339,"has_trajectory":119,"duration_seconds":340},31511,{"status":181,"finish_reason":182},"22",95383,1168,"78.55",{"id":342,"error":107,"extra":343,"score":147,"passed":4,"case_key":344,"cost_usd":107,"sample_idx":142,"input_tokens":345,"output_tokens":346,"has_trajectory":119,"duration_seconds":347},31515,{"status":181,"finish_reason":182},"23",95429,1439,"76.17",{"id":349,"error":107,"extra":350,"score":146,"passed":119,"case_key":351,"cost_usd":107,"sample_idx":142,"input_tokens":352,"output_tokens":353,"has_trajectory":119,"duration_seconds":354},31519,{"status":181,"finish_reason":182},"24",95369,4504,"267.02",{"id":356,"error":107,"extra":357,"score":147,"passed":4,"case_key":358,"cost_usd":107,"sample_idx":142,"input_tokens":359,"output_tokens":360,"has_trajectory":119,"duration_seconds":361},31523,{"status":181,"finish_reason":182},"25",95412,16229,"923.97",{"id":363,"error":107,"extra":364,"score":146,"passed":119,"case_key":365,"cost_usd":107,"sample_idx":142,"input_tokens":366,"output_tokens":367,"has_trajectory":119,"duration_seconds":368},31527,{"status":181,"finish_reason":182},"26",93849,6044,"394.67",{"id":370,"error":107,"extra":371,"score":146,"passed":119,"case_key":372,"cost_usd":107,"sample_idx":142,"input_tokens":373,"output_tokens":374,"has_trajectory":119,"duration_seconds":375},31531,{"status":181,"finish_reason":182},"27",93870,12609,"669.63",{"id":377,"error":107,"extra":378,"score":147,"passed":4,"case_key":381,"cost_usd":107,"sample_idx":142,"input_tokens":382,"output_tokens":117,"has_trajectory":119,"duration_seconds":383},31535,{"status":379,"finish_reason":380},"failed","length","28",93872,"826.50",{"id":385,"error":107,"extra":386,"score":146,"passed":119,"case_key":387,"cost_usd":107,"sample_idx":142,"input_tokens":388,"output_tokens":389,"has_trajectory":119,"duration_seconds":390},31539,{"status":181,"finish_reason":182},"29",93929,10349,"580.19",{"id":392,"error":107,"extra":393,"score":146,"passed":119,"case_key":394,"cost_usd":107,"sample_idx":142,"input_tokens":395,"output_tokens":396,"has_trajectory":119,"duration_seconds":397},31543,{"status":181,"finish_reason":182},"30",73397,2910,"139.19",{"id":399,"error":107,"extra":400,"score":146,"passed":119,"case_key":401,"cost_usd":107,"sample_idx":142,"input_tokens":402,"output_tokens":403,"has_trajectory":119,"duration_seconds":404},31547,{"status":181,"finish_reason":182},"31",73395,2363,"133.29",{"id":406,"error":107,"extra":407,"score":146,"passed":119,"case_key":408,"cost_usd":107,"sample_idx":142,"input_tokens":409,"output_tokens":410,"has_trajectory":119,"duration_seconds":411},31551,{"status":181,"finish_reason":182},"32",97833,1692,"82.64",{"id":413,"error":107,"extra":414,"score":146,"passed":119,"case_key":415,"cost_usd":107,"sample_idx":142,"input_tokens":416,"output_tokens":417,"has_trajectory":119,"duration_seconds":418},31555,{"status":181,"finish_reason":182},"33",97834,3490,"164.44",{"id":420,"error":107,"extra":421,"score":146,"passed":119,"case_key":422,"cost_usd":107,"sample_idx":142,"input_tokens":423,"output_tokens":424,"has_trajectory":119,"duration_seconds":425},31559,{"status":181,"finish_reason":182},"34",97847,1901,"95.50",{"id":427,"error":107,"extra":428,"score":146,"passed":119,"case_key":429,"cost_usd":107,"sample_idx":142,"input_tokens":430,"output_tokens":431,"has_trajectory":119,"duration_seconds":432},31563,{"status":181,"finish_reason":182},"35",80486,1821,"84.42",{"id":434,"error":107,"extra":435,"score":146,"passed":119,"case_key":436,"cost_usd":107,"sample_idx":142,"input_tokens":437,"output_tokens":438,"has_trajectory":119,"duration_seconds":439},31567,{"status":181,"finish_reason":182},"36",80464,689,"32.24",{"id":441,"error":107,"extra":442,"score":147,"passed":4,"case_key":443,"cost_usd":107,"sample_idx":142,"input_tokens":444,"output_tokens":445,"has_trajectory":119,"duration_seconds":446},31571,{"status":181,"finish_reason":182},"37",80481,12041,"631.74",{"id":448,"error":107,"extra":449,"score":146,"passed":119,"case_key":450,"cost_usd":107,"sample_idx":142,"input_tokens":451,"output_tokens":452,"has_trajectory":119,"duration_seconds":453},31575,{"status":181,"finish_reason":182},"38",80471,3048,"149.57",{"id":455,"error":107,"extra":456,"score":147,"passed":4,"case_key":457,"cost_usd":107,"sample_idx":142,"input_tokens":458,"output_tokens":459,"has_trajectory":119,"duration_seconds":460},31579,{"status":181,"finish_reason":182},"39",80480,3510,"171.84",{"id":462,"error":107,"extra":463,"score":146,"passed":119,"case_key":464,"cost_usd":107,"sample_idx":142,"input_tokens":465,"output_tokens":466,"has_trajectory":119,"duration_seconds":467},31583,{"status":181,"finish_reason":182},"40",94367,566,"32.13",{"id":469,"error":107,"extra":470,"score":146,"passed":119,"case_key":471,"cost_usd":107,"sample_idx":142,"input_tokens":472,"output_tokens":473,"has_trajectory":119,"duration_seconds":474},31587,{"status":181,"finish_reason":182},"41",94393,1211,"72.72",{"id":476,"error":107,"extra":477,"score":146,"passed":119,"case_key":478,"cost_usd":107,"sample_idx":142,"input_tokens":479,"output_tokens":480,"has_trajectory":119,"duration_seconds":481},31591,{"status":181,"finish_reason":182},"42",84714,4917,"216.50",{"id":483,"error":107,"extra":484,"score":146,"passed":119,"case_key":485,"cost_usd":107,"sample_idx":142,"input_tokens":486,"output_tokens":487,"has_trajectory":119,"duration_seconds":488},31595,{"status":181,"finish_reason":182},"43",84704,8069,"427.50",{"id":490,"error":107,"extra":491,"score":146,"passed":119,"case_key":492,"cost_usd":107,"sample_idx":142,"input_tokens":493,"output_tokens":494,"has_trajectory":119,"duration_seconds":495},31599,{"status":181,"finish_reason":182},"44",84699,550,"26.86",{"id":497,"error":107,"extra":498,"score":146,"passed":119,"case_key":499,"cost_usd":107,"sample_idx":142,"input_tokens":500,"output_tokens":501,"has_trajectory":119,"duration_seconds":502},31603,{"status":181,"finish_reason":182},"45",84764,1230,"66.91",{"id":504,"error":107,"extra":505,"score":147,"passed":4,"case_key":506,"cost_usd":107,"sample_idx":142,"input_tokens":507,"output_tokens":508,"has_trajectory":119,"duration_seconds":509},31607,{"status":181,"finish_reason":182},"46",84708,3410,"173.45",{"id":511,"error":107,"extra":512,"score":147,"passed":4,"case_key":513,"cost_usd":107,"sample_idx":142,"input_tokens":514,"output_tokens":515,"has_trajectory":119,"duration_seconds":516},31611,{"status":181,"finish_reason":182},"47",84743,15080,"721.75",{"id":518,"error":107,"extra":519,"score":147,"passed":4,"case_key":520,"cost_usd":107,"sample_idx":142,"input_tokens":521,"output_tokens":522,"has_trajectory":119,"duration_seconds":523},31615,{"status":181,"finish_reason":182},"48",84710,5565,"272.05",{"id":525,"error":107,"extra":526,"score":147,"passed":4,"case_key":527,"cost_usd":107,"sample_idx":142,"input_tokens":507,"output_tokens":528,"has_trajectory":119,"duration_seconds":529},31619,{"status":181,"finish_reason":182},"49",2802,"130.87",{"total":118,"failed":153,"passed":154,"run_id":106,"ungraded":142,"sample_idx":142,"trajectories":118}]