[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"api:\u002Fnav:{}":3,"api:\u002Frecords\u002F58:{}":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":128,"benchmark":146,"rank":54,"ranked_count":72,"samples":161,"other_harnesses":165,"distribution":166,"cases":177},{"id":106,"notes":107,"score":108,"metrics":109,"cost_usd":107,"settings":112,"num_cases":120,"score_std":107,"harness_id":107,"has_bundle":121,"is_primary":121,"output_tps":107,"variant_id":122,"num_samples":54,"benchmark_id":72,"evaluated_at":123,"harness_name":107,"harness_slug":107,"input_tokens":124,"ttft_seconds":107,"output_tokens":125,"parent_run_id":107,"harness_version":107,"avg_case_seconds":126,"reasoning_tokens":107,"cost_per_case_usd":107,"trajectory_bundle_size_bytes":127},58,null,"0.3500",{"accuracy":110,"hallucination_rate":111},"0.5183333333333333","0.3494809688581315",{"top_p":113,"recipe":107,"harness":107,"judge_model":114,"num_samples":54,"temperature":115,"extra_settings":116,"scoring_method":107,"harness_version":107,"framework_version":118,"max_output_tokens":119},"1.000","Qwen3-30B-A3B-Instruct-2507","0.60",{"top_k":117},-1,"OPT 1478395",65536,600,true,11,"2026-10-23",123914,2698650,"506.77",2985244,{"access":129,"effort":130,"family":28,"is_tier":121,"hardware":107,"model_id":131,"provider":107,"data_date":132,"precision":107,"categories":133,"is_primary":121,"model_name":28,"model_slug":29,"short_name":28,"variant_id":122,"effort_rank":141,"input_price":107,"vendor_name":24,"vendor_slug":25,"architecture":107,"output_price":107,"overall_rank":131,"ranked_count":72,"release_date":142,"variant_name":143,"variant_slug":144,"vendor_order":145,"weights_repo":107,"missing_count":131,"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":121,"is_open_weights":121,"inference_engine":107},"api","max",3,"2026-10-24",[134,136,138,140],{"name":41,"rank":43,"slug":42,"score":135,"expected":43,"available":54,"ranked_count":72},"65.051903114186850000000000",{"name":45,"rank":43,"slug":46,"score":137,"expected":47,"available":72,"ranked_count":72},"67.050833333333332500000000",{"name":49,"rank":72,"slug":50,"score":139,"expected":43,"available":54,"ranked_count":72},"3.500000000000000000000000",{"name":52,"rank":72,"slug":53,"score":139,"expected":54,"available":54,"ranked_count":72},6,"2026-07-16","Kimi-K3 官方 API max","kimi-k3-api-max",0,{"id":72,"name":84,"slug":85,"license":147,"metrics":148,"version":107,"is_active":121,"num_cases":120,"parent_id":107,"score_max":152,"score_min":157,"created_at":158,"is_agentic":4,"sort_order":145,"updated_at":158,"description":107,"metric_name":159,"homepage_url":107,"license_note":107,"scoring_method":107,"composite_weight":152,"higher_is_better":121,"bundle_size_bytes":160},"public",[149,154],{"key":150,"name":151,"score":110,"score_max":152,"score_min":153,"higher_is_better":121},"accuracy","Accuracy","1.0000","0.0000",{"key":155,"name":156,"score":111,"score_max":152,"score_min":153,"higher_is_better":4},"hallucination_rate","Hallucination Rate","-1.0000","2026-10-28T09:47:38.906402+08:00","Omniscience Index",73171079,[162],{"total":120,"failed":163,"passed":164,"run_id":106,"ungraded":145,"sample_idx":145,"trajectories":120},289,311,[],[167,168,171,174],{"name":28,"rank":54,"score":108,"run_id":106,"model_slug":29,"vendor_slug":25},{"name":36,"rank":43,"score":169,"run_id":170,"model_slug":37,"vendor_slug":33},"0.2867",40,{"name":20,"rank":131,"score":172,"run_id":173,"model_slug":21,"vendor_slug":17},"0.1950",13,{"name":12,"rank":72,"score":175,"run_id":176,"model_slug":13,"vendor_slug":9},"-0.0367",113,{"restricted":4,"rows":178,"counts":512,"next_after":506},[179,188,195,202,209,216,221,228,235,242,248,254,260,267,273,280,286,293,300,306,313,320,327,334,341,348,355,361,368,375,381,388,395,402,408,414,420,427,434,440,447,453,459,465,472,479,486,492,498,505],{"id":180,"error":107,"extra":181,"score":152,"passed":121,"case_key":184,"cost_usd":107,"sample_idx":145,"input_tokens":185,"output_tokens":186,"has_trajectory":121,"duration_seconds":187},160958,{"status":182,"finish_reason":183},"completed","stop","0",201,1394,"215.72",{"id":189,"error":107,"extra":190,"score":152,"passed":121,"case_key":191,"cost_usd":107,"sample_idx":145,"input_tokens":192,"output_tokens":193,"has_trajectory":121,"duration_seconds":194},160959,{"status":182,"finish_reason":183},"1",205,10403,"1152.64",{"id":196,"error":107,"extra":197,"score":157,"passed":4,"case_key":198,"cost_usd":107,"sample_idx":145,"input_tokens":199,"output_tokens":200,"has_trajectory":121,"duration_seconds":201},160960,{"status":182,"finish_reason":183},"2",204,1710,"252.66",{"id":203,"error":107,"extra":204,"score":152,"passed":121,"case_key":205,"cost_usd":107,"sample_idx":145,"input_tokens":206,"output_tokens":207,"has_trajectory":121,"duration_seconds":208},160961,{"status":182,"finish_reason":183},"3",197,1424,"219.35",{"id":210,"error":107,"extra":211,"score":152,"passed":121,"case_key":212,"cost_usd":107,"sample_idx":145,"input_tokens":213,"output_tokens":214,"has_trajectory":121,"duration_seconds":215},160962,{"status":182,"finish_reason":183},"4",225,7845,"876.75",{"id":217,"error":107,"extra":218,"score":153,"passed":4,"case_key":220,"cost_usd":107,"sample_idx":145,"input_tokens":107,"output_tokens":107,"has_trajectory":121,"duration_seconds":107},160963,{"status":219,"finish_reason":107},"failed","5",{"id":222,"error":107,"extra":223,"score":157,"passed":4,"case_key":224,"cost_usd":107,"sample_idx":145,"input_tokens":225,"output_tokens":226,"has_trajectory":121,"duration_seconds":227},160964,{"status":182,"finish_reason":183},"6",219,4487,"612.40",{"id":229,"error":107,"extra":230,"score":153,"passed":4,"case_key":231,"cost_usd":107,"sample_idx":145,"input_tokens":232,"output_tokens":233,"has_trajectory":121,"duration_seconds":234},160965,{"status":182,"finish_reason":183},"7",189,11789,"1251.32",{"id":236,"error":107,"extra":237,"score":152,"passed":121,"case_key":238,"cost_usd":107,"sample_idx":145,"input_tokens":239,"output_tokens":240,"has_trajectory":121,"duration_seconds":241},160966,{"status":182,"finish_reason":183},"8",212,1062,"176.02",{"id":243,"error":107,"extra":244,"score":152,"passed":121,"case_key":245,"cost_usd":107,"sample_idx":145,"input_tokens":192,"output_tokens":246,"has_trajectory":121,"duration_seconds":247},160967,{"status":182,"finish_reason":183},"9",1076,"177.62",{"id":249,"error":107,"extra":250,"score":153,"passed":4,"case_key":251,"cost_usd":107,"sample_idx":145,"input_tokens":206,"output_tokens":252,"has_trajectory":121,"duration_seconds":253},160968,{"status":182,"finish_reason":183},"10",5243,"612.58",{"id":255,"error":107,"extra":256,"score":152,"passed":121,"case_key":257,"cost_usd":107,"sample_idx":145,"input_tokens":258,"output_tokens":259,"has_trajectory":121,"duration_seconds":227},160969,{"status":182,"finish_reason":183},"11",215,4616,{"id":261,"error":107,"extra":262,"score":152,"passed":121,"case_key":263,"cost_usd":107,"sample_idx":145,"input_tokens":264,"output_tokens":265,"has_trajectory":121,"duration_seconds":266},160970,{"status":182,"finish_reason":183},"12",226,14899,"1724.51",{"id":268,"error":107,"extra":269,"score":157,"passed":4,"case_key":270,"cost_usd":107,"sample_idx":145,"input_tokens":232,"output_tokens":271,"has_trajectory":121,"duration_seconds":272},160971,{"status":182,"finish_reason":183},"13",1908,"274.47",{"id":274,"error":107,"extra":275,"score":157,"passed":4,"case_key":276,"cost_usd":107,"sample_idx":145,"input_tokens":277,"output_tokens":278,"has_trajectory":121,"duration_seconds":279},160972,{"status":182,"finish_reason":183},"14",193,810,"146.83",{"id":281,"error":107,"extra":282,"score":152,"passed":121,"case_key":283,"cost_usd":107,"sample_idx":145,"input_tokens":206,"output_tokens":284,"has_trajectory":121,"duration_seconds":285},160973,{"status":182,"finish_reason":183},"15",4565,"612.39",{"id":287,"error":107,"extra":288,"score":152,"passed":121,"case_key":289,"cost_usd":107,"sample_idx":145,"input_tokens":290,"output_tokens":291,"has_trajectory":121,"duration_seconds":292},160974,{"status":182,"finish_reason":183},"16",207,2101,"295.47",{"id":294,"error":107,"extra":295,"score":152,"passed":121,"case_key":296,"cost_usd":107,"sample_idx":145,"input_tokens":297,"output_tokens":298,"has_trajectory":121,"duration_seconds":299},160975,{"status":182,"finish_reason":183},"17",202,588,"120.80",{"id":301,"error":107,"extra":302,"score":152,"passed":121,"case_key":303,"cost_usd":107,"sample_idx":145,"input_tokens":304,"output_tokens":206,"has_trajectory":121,"duration_seconds":305},160976,{"status":182,"finish_reason":183},"18",210,"76.27",{"id":307,"error":107,"extra":308,"score":152,"passed":121,"case_key":309,"cost_usd":107,"sample_idx":145,"input_tokens":310,"output_tokens":311,"has_trajectory":121,"duration_seconds":312},160977,{"status":182,"finish_reason":183},"19",209,4354,"612.57",{"id":314,"error":107,"extra":315,"score":152,"passed":121,"case_key":316,"cost_usd":107,"sample_idx":145,"input_tokens":317,"output_tokens":318,"has_trajectory":121,"duration_seconds":319},160978,{"status":182,"finish_reason":183},"20",187,3082,"404.55",{"id":321,"error":107,"extra":322,"score":152,"passed":121,"case_key":323,"cost_usd":107,"sample_idx":145,"input_tokens":324,"output_tokens":325,"has_trajectory":121,"duration_seconds":326},160979,{"status":182,"finish_reason":183},"21",208,227,"79.32",{"id":328,"error":107,"extra":329,"score":152,"passed":121,"case_key":330,"cost_usd":107,"sample_idx":145,"input_tokens":331,"output_tokens":332,"has_trajectory":121,"duration_seconds":333},160980,{"status":182,"finish_reason":183},"22",190,802,"145.97",{"id":335,"error":107,"extra":336,"score":157,"passed":4,"case_key":337,"cost_usd":107,"sample_idx":145,"input_tokens":338,"output_tokens":339,"has_trajectory":121,"duration_seconds":340},160981,{"status":182,"finish_reason":183},"23",184,5471,"621.60",{"id":342,"error":107,"extra":343,"score":153,"passed":4,"case_key":344,"cost_usd":107,"sample_idx":145,"input_tokens":345,"output_tokens":346,"has_trajectory":121,"duration_seconds":347},160982,{"status":182,"finish_reason":183},"24",192,240,"29.31",{"id":349,"error":107,"extra":350,"score":153,"passed":4,"case_key":351,"cost_usd":107,"sample_idx":145,"input_tokens":352,"output_tokens":353,"has_trajectory":121,"duration_seconds":354},160983,{"status":182,"finish_reason":183},"25",196,1018,"121.16",{"id":356,"error":107,"extra":357,"score":152,"passed":121,"case_key":358,"cost_usd":107,"sample_idx":145,"input_tokens":232,"output_tokens":359,"has_trajectory":121,"duration_seconds":360},160984,{"status":182,"finish_reason":183},"26",831,"98.71",{"id":362,"error":107,"extra":363,"score":157,"passed":4,"case_key":364,"cost_usd":107,"sample_idx":145,"input_tokens":365,"output_tokens":366,"has_trajectory":121,"duration_seconds":367},160985,{"status":182,"finish_reason":183},"27",194,6526,"677.92",{"id":369,"error":107,"extra":370,"score":152,"passed":121,"case_key":371,"cost_usd":107,"sample_idx":145,"input_tokens":372,"output_tokens":373,"has_trajectory":121,"duration_seconds":374},160986,{"status":182,"finish_reason":183},"28",206,1133,"132.01",{"id":376,"error":107,"extra":377,"score":153,"passed":4,"case_key":378,"cost_usd":107,"sample_idx":145,"input_tokens":290,"output_tokens":379,"has_trajectory":121,"duration_seconds":380},160987,{"status":182,"finish_reason":183},"29",611,"74.16",{"id":382,"error":107,"extra":383,"score":152,"passed":121,"case_key":384,"cost_usd":107,"sample_idx":145,"input_tokens":385,"output_tokens":386,"has_trajectory":121,"duration_seconds":387},160988,{"status":182,"finish_reason":183},"30",200,124,"35.17",{"id":389,"error":107,"extra":390,"score":153,"passed":4,"case_key":391,"cost_usd":107,"sample_idx":145,"input_tokens":392,"output_tokens":393,"has_trajectory":121,"duration_seconds":394},160989,{"status":182,"finish_reason":183},"31",217,2893,"434.73",{"id":396,"error":107,"extra":397,"score":153,"passed":4,"case_key":398,"cost_usd":107,"sample_idx":145,"input_tokens":399,"output_tokens":400,"has_trajectory":121,"duration_seconds":401},160990,{"status":182,"finish_reason":183},"32",185,3012,"411.80",{"id":403,"error":107,"extra":404,"score":152,"passed":121,"case_key":405,"cost_usd":107,"sample_idx":145,"input_tokens":199,"output_tokens":406,"has_trajectory":121,"duration_seconds":407},160991,{"status":182,"finish_reason":183},"33",10243,"1085.68",{"id":409,"error":107,"extra":410,"score":152,"passed":121,"case_key":411,"cost_usd":107,"sample_idx":145,"input_tokens":385,"output_tokens":412,"has_trajectory":121,"duration_seconds":413},160992,{"status":182,"finish_reason":183},"34",2752,"401.31",{"id":415,"error":107,"extra":416,"score":152,"passed":121,"case_key":417,"cost_usd":107,"sample_idx":145,"input_tokens":239,"output_tokens":418,"has_trajectory":121,"duration_seconds":419},160993,{"status":182,"finish_reason":183},"35",5734,"595.15",{"id":421,"error":107,"extra":422,"score":152,"passed":121,"case_key":423,"cost_usd":107,"sample_idx":145,"input_tokens":424,"output_tokens":425,"has_trajectory":121,"duration_seconds":426},160994,{"status":182,"finish_reason":183},"36",198,265,"45.61",{"id":428,"error":107,"extra":429,"score":157,"passed":4,"case_key":430,"cost_usd":107,"sample_idx":145,"input_tokens":431,"output_tokens":432,"has_trajectory":121,"duration_seconds":433},160995,{"status":182,"finish_reason":183},"37",211,5833,"609.07",{"id":435,"error":107,"extra":436,"score":152,"passed":121,"case_key":437,"cost_usd":107,"sample_idx":145,"input_tokens":392,"output_tokens":438,"has_trajectory":121,"duration_seconds":439},160996,{"status":182,"finish_reason":183},"38",7926,"836.96",{"id":441,"error":107,"extra":442,"score":157,"passed":4,"case_key":443,"cost_usd":107,"sample_idx":145,"input_tokens":444,"output_tokens":445,"has_trajectory":121,"duration_seconds":446},160997,{"status":182,"finish_reason":183},"39",236,13284,"1382.10",{"id":448,"error":107,"extra":449,"score":153,"passed":4,"case_key":450,"cost_usd":107,"sample_idx":145,"input_tokens":431,"output_tokens":451,"has_trajectory":121,"duration_seconds":452},160998,{"status":182,"finish_reason":183},"40",8621,"906.32",{"id":454,"error":107,"extra":455,"score":157,"passed":4,"case_key":456,"cost_usd":107,"sample_idx":145,"input_tokens":277,"output_tokens":457,"has_trajectory":121,"duration_seconds":458},160999,{"status":182,"finish_reason":183},"41",7277,"761.45",{"id":460,"error":107,"extra":461,"score":153,"passed":4,"case_key":462,"cost_usd":107,"sample_idx":145,"input_tokens":372,"output_tokens":463,"has_trajectory":121,"duration_seconds":464},161000,{"status":182,"finish_reason":183},"42",3306,"331.18",{"id":466,"error":107,"extra":467,"score":153,"passed":4,"case_key":468,"cost_usd":107,"sample_idx":145,"input_tokens":469,"output_tokens":470,"has_trajectory":121,"duration_seconds":471},161001,{"status":182,"finish_reason":183},"43",220,3831,"379.83",{"id":473,"error":107,"extra":474,"score":153,"passed":4,"case_key":475,"cost_usd":107,"sample_idx":145,"input_tokens":476,"output_tokens":477,"has_trajectory":121,"duration_seconds":478},161002,{"status":182,"finish_reason":183},"44",216,1348,"148.72",{"id":480,"error":107,"extra":481,"score":152,"passed":121,"case_key":482,"cost_usd":107,"sample_idx":145,"input_tokens":483,"output_tokens":484,"has_trajectory":121,"duration_seconds":485},161003,{"status":182,"finish_reason":183},"45",234,362,"40.37",{"id":487,"error":107,"extra":488,"score":157,"passed":4,"case_key":489,"cost_usd":107,"sample_idx":145,"input_tokens":290,"output_tokens":490,"has_trajectory":121,"duration_seconds":491},161004,{"status":182,"finish_reason":183},"46",1128,"124.17",{"id":493,"error":107,"extra":494,"score":153,"passed":4,"case_key":495,"cost_usd":107,"sample_idx":145,"input_tokens":304,"output_tokens":496,"has_trajectory":121,"duration_seconds":497},161005,{"status":182,"finish_reason":183},"47",14273,"1619.45",{"id":499,"error":107,"extra":500,"score":152,"passed":121,"case_key":501,"cost_usd":107,"sample_idx":145,"input_tokens":502,"output_tokens":503,"has_trajectory":121,"duration_seconds":504},161006,{"status":182,"finish_reason":183},"48",286,1184,"130.51",{"id":506,"error":107,"extra":507,"score":152,"passed":121,"case_key":508,"cost_usd":107,"sample_idx":145,"input_tokens":509,"output_tokens":510,"has_trajectory":121,"duration_seconds":511},161007,{"status":182,"finish_reason":183},"49",291,847,"93.67",{"total":120,"failed":163,"passed":164,"run_id":106,"ungraded":145,"sample_idx":145,"trajectories":120}]