[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"api:\u002Fnav:{}":3,"api:\u002Frecords\u002F41:{}":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":124,"benchmark":143,"rank":54,"ranked_count":72,"samples":151,"other_harnesses":155,"distribution":156,"cases":167},{"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":73,"num_samples":54,"benchmark_id":43,"evaluated_at":119,"harness_name":107,"harness_slug":107,"input_tokens":120,"ttft_seconds":107,"output_tokens":121,"parent_run_id":107,"harness_version":107,"avg_case_seconds":122,"reasoning_tokens":107,"cost_per_case_usd":107,"trajectory_bundle_size_bytes":123},41,null,"0.5250",{},{"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","0.00",{"top_k":114},-1,"OPT 1478395",32768,600,true,"2026-10-19",281739014,6962692,"868.68",22105164,{"access":125,"effort":126,"family":36,"is_tier":118,"hardware":107,"model_id":54,"provider":107,"data_date":127,"precision":107,"categories":128,"is_primary":118,"model_name":36,"model_slug":37,"short_name":36,"variant_id":73,"effort_rank":138,"input_price":107,"vendor_name":32,"vendor_slug":33,"architecture":107,"output_price":107,"overall_rank":43,"ranked_count":72,"release_date":139,"variant_name":140,"variant_slug":141,"vendor_order":142,"weights_repo":107,"missing_count":43,"overall_score":38,"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","2026-10-23",[129,131,134,136],{"name":41,"rank":54,"slug":42,"score":130,"expected":43,"available":54,"ranked_count":72},"72.997032640949555000000000",{"name":45,"rank":132,"slug":46,"score":133,"expected":47,"available":72,"ranked_count":72},3,"59.363333333333333750000000",{"name":49,"rank":54,"slug":50,"score":135,"expected":43,"available":43,"ranked_count":72},"54.225000000000000000000000",{"name":52,"rank":54,"slug":53,"score":137,"expected":54,"available":54,"ranked_count":72},"52.500000000000000000000000",6,"2026-08-18","GLM-5.3 官方 API max","glm-5-3-api-max",0,{"id":43,"name":87,"slug":88,"license":144,"metrics":145,"version":107,"is_active":118,"num_cases":117,"parent_id":107,"score_max":146,"score_min":147,"created_at":148,"is_agentic":118,"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":118,"bundle_size_bytes":150},"public",[],"1.0000","0.0000","2026-10-28T09:47:38.906402+08:00","Pass Rate",2028958067,[152],{"total":117,"failed":153,"passed":154,"run_id":106,"ungraded":142,"sample_idx":142,"trajectories":117},285,315,[],[157,158,161,164],{"name":36,"rank":54,"score":108,"run_id":106,"model_slug":37,"vendor_slug":33},{"name":20,"rank":43,"score":159,"run_id":160,"model_slug":21,"vendor_slug":17},"0.4567",14,{"name":12,"rank":132,"score":162,"run_id":163,"model_slug":13,"vendor_slug":9},"0.4150",114,{"name":28,"rank":72,"score":165,"run_id":166,"model_slug":29,"vendor_slug":25},"0.0350",59,{"restricted":4,"rows":168,"counts":538,"next_after":531},[169,178,185,193,200,207,214,221,228,235,242,249,256,263,270,277,285,292,300,307,315,322,329,337,344,351,358,365,373,380,388,396,404,412,419,427,435,442,449,456,463,470,477,484,491,500,508,515,523,530],{"id":170,"error":107,"extra":171,"score":146,"passed":118,"case_key":174,"cost_usd":107,"sample_idx":142,"input_tokens":175,"output_tokens":176,"has_trajectory":118,"duration_seconds":177},112615,{"status":172,"finish_reason":173},"completed","stop","0",625295,10280,"980.64",{"id":179,"error":107,"extra":180,"score":146,"passed":118,"case_key":181,"cost_usd":107,"sample_idx":142,"input_tokens":182,"output_tokens":183,"has_trajectory":118,"duration_seconds":184},112616,{"status":172,"finish_reason":173},"1",275667,6430,"619.71",{"id":186,"error":107,"extra":187,"score":188,"passed":4,"case_key":189,"cost_usd":107,"sample_idx":142,"input_tokens":190,"output_tokens":191,"has_trajectory":118,"duration_seconds":192},112617,{"status":172,"finish_reason":173},"0.7500","2",247428,14684,"1350.92",{"id":194,"error":107,"extra":195,"score":146,"passed":118,"case_key":196,"cost_usd":107,"sample_idx":142,"input_tokens":197,"output_tokens":198,"has_trajectory":118,"duration_seconds":199},112618,{"status":172,"finish_reason":173},"3",345667,7975,"765.30",{"id":201,"error":107,"extra":202,"score":146,"passed":118,"case_key":203,"cost_usd":107,"sample_idx":142,"input_tokens":204,"output_tokens":205,"has_trajectory":118,"duration_seconds":206},112619,{"status":172,"finish_reason":173},"4",356689,12059,"1124.93",{"id":208,"error":107,"extra":209,"score":146,"passed":118,"case_key":210,"cost_usd":107,"sample_idx":142,"input_tokens":211,"output_tokens":212,"has_trajectory":118,"duration_seconds":213},112620,{"status":172,"finish_reason":173},"5",281075,4953,"494.24",{"id":215,"error":107,"extra":216,"score":146,"passed":118,"case_key":217,"cost_usd":107,"sample_idx":142,"input_tokens":218,"output_tokens":219,"has_trajectory":118,"duration_seconds":220},112621,{"status":172,"finish_reason":173},"6",739550,16026,"1468.23",{"id":222,"error":107,"extra":223,"score":146,"passed":118,"case_key":224,"cost_usd":107,"sample_idx":142,"input_tokens":225,"output_tokens":226,"has_trajectory":118,"duration_seconds":227},112622,{"status":172,"finish_reason":173},"7",408466,26267,"2379.26",{"id":229,"error":107,"extra":230,"score":147,"passed":4,"case_key":231,"cost_usd":107,"sample_idx":142,"input_tokens":232,"output_tokens":233,"has_trajectory":118,"duration_seconds":234},112623,{"status":172,"finish_reason":173},"8",436605,5314,"529.36",{"id":236,"error":107,"extra":237,"score":146,"passed":118,"case_key":238,"cost_usd":107,"sample_idx":142,"input_tokens":239,"output_tokens":240,"has_trajectory":118,"duration_seconds":241},112624,{"status":172,"finish_reason":173},"9",618173,6166,"609.81",{"id":243,"error":107,"extra":244,"score":146,"passed":118,"case_key":245,"cost_usd":107,"sample_idx":142,"input_tokens":246,"output_tokens":247,"has_trajectory":118,"duration_seconds":248},112625,{"status":172,"finish_reason":173},"10",108874,4500,"440.84",{"id":250,"error":107,"extra":251,"score":146,"passed":118,"case_key":252,"cost_usd":107,"sample_idx":142,"input_tokens":253,"output_tokens":254,"has_trajectory":118,"duration_seconds":255},112626,{"status":172,"finish_reason":173},"11",147532,7764,"733.80",{"id":257,"error":107,"extra":258,"score":146,"passed":118,"case_key":259,"cost_usd":107,"sample_idx":142,"input_tokens":260,"output_tokens":261,"has_trajectory":118,"duration_seconds":262},112627,{"status":172,"finish_reason":173},"12",604442,5583,"557.81",{"id":264,"error":107,"extra":265,"score":146,"passed":118,"case_key":266,"cost_usd":107,"sample_idx":142,"input_tokens":267,"output_tokens":268,"has_trajectory":118,"duration_seconds":269},112628,{"status":172,"finish_reason":173},"13",158867,2395,"267.25",{"id":271,"error":107,"extra":272,"score":146,"passed":118,"case_key":273,"cost_usd":107,"sample_idx":142,"input_tokens":274,"output_tokens":275,"has_trajectory":118,"duration_seconds":276},112629,{"status":172,"finish_reason":173},"14",162481,3113,"332.13",{"id":278,"error":107,"extra":279,"score":280,"passed":4,"case_key":281,"cost_usd":107,"sample_idx":142,"input_tokens":282,"output_tokens":283,"has_trajectory":118,"duration_seconds":284},112630,{"status":172,"finish_reason":173},"0.5000","15",2888819,35394,"3165.44",{"id":286,"error":107,"extra":287,"score":146,"passed":118,"case_key":288,"cost_usd":107,"sample_idx":142,"input_tokens":289,"output_tokens":290,"has_trajectory":118,"duration_seconds":291},112631,{"status":172,"finish_reason":173},"16",806219,21383,"1944.62",{"id":293,"error":107,"extra":294,"score":295,"passed":4,"case_key":296,"cost_usd":107,"sample_idx":142,"input_tokens":297,"output_tokens":298,"has_trajectory":118,"duration_seconds":299},112632,{"status":172,"finish_reason":173},"0.7143","17",526816,19977,"1813.80",{"id":301,"error":107,"extra":302,"score":146,"passed":118,"case_key":303,"cost_usd":107,"sample_idx":142,"input_tokens":304,"output_tokens":305,"has_trajectory":118,"duration_seconds":306},112633,{"status":172,"finish_reason":173},"18",526197,20082,"1821.07",{"id":308,"error":107,"extra":309,"score":310,"passed":4,"case_key":311,"cost_usd":107,"sample_idx":142,"input_tokens":312,"output_tokens":313,"has_trajectory":118,"duration_seconds":314},112634,{"status":172,"finish_reason":173},"0.8000","19",473266,7836,"756.11",{"id":316,"error":107,"extra":317,"score":280,"passed":4,"case_key":318,"cost_usd":107,"sample_idx":142,"input_tokens":319,"output_tokens":320,"has_trajectory":118,"duration_seconds":321},112635,{"status":172,"finish_reason":173},"20",183839,6664,"645.38",{"id":323,"error":107,"extra":324,"score":310,"passed":4,"case_key":325,"cost_usd":107,"sample_idx":142,"input_tokens":326,"output_tokens":327,"has_trajectory":118,"duration_seconds":328},112636,{"status":172,"finish_reason":173},"21",1731506,24930,"2274.84",{"id":330,"error":107,"extra":331,"score":332,"passed":4,"case_key":333,"cost_usd":107,"sample_idx":142,"input_tokens":334,"output_tokens":335,"has_trajectory":118,"duration_seconds":336},112637,{"status":172,"finish_reason":173},"0.6667","22",425508,8821,"850.58",{"id":338,"error":107,"extra":339,"score":146,"passed":118,"case_key":340,"cost_usd":107,"sample_idx":142,"input_tokens":341,"output_tokens":342,"has_trajectory":118,"duration_seconds":343},112638,{"status":172,"finish_reason":173},"23",477651,8925,"848.79",{"id":345,"error":107,"extra":346,"score":146,"passed":118,"case_key":347,"cost_usd":107,"sample_idx":142,"input_tokens":348,"output_tokens":349,"has_trajectory":118,"duration_seconds":350},112639,{"status":172,"finish_reason":173},"24",659281,9081,"865.27",{"id":352,"error":107,"extra":353,"score":146,"passed":118,"case_key":354,"cost_usd":107,"sample_idx":142,"input_tokens":355,"output_tokens":356,"has_trajectory":118,"duration_seconds":357},112640,{"status":172,"finish_reason":173},"25",513809,15577,"1438.20",{"id":359,"error":107,"extra":360,"score":147,"passed":4,"case_key":361,"cost_usd":107,"sample_idx":142,"input_tokens":362,"output_tokens":363,"has_trajectory":118,"duration_seconds":364},112641,{"status":172,"finish_reason":173},"26",89305,2213,"252.04",{"id":366,"error":107,"extra":367,"score":368,"passed":4,"case_key":369,"cost_usd":107,"sample_idx":142,"input_tokens":370,"output_tokens":371,"has_trajectory":118,"duration_seconds":372},112642,{"status":172,"finish_reason":173},"0.6250","27",958435,12913,"1199.68",{"id":374,"error":107,"extra":375,"score":146,"passed":118,"case_key":376,"cost_usd":107,"sample_idx":142,"input_tokens":377,"output_tokens":378,"has_trajectory":118,"duration_seconds":379},112643,{"status":172,"finish_reason":173},"28",252693,2602,"288.61",{"id":381,"error":107,"extra":382,"score":383,"passed":4,"case_key":384,"cost_usd":107,"sample_idx":142,"input_tokens":385,"output_tokens":386,"has_trajectory":118,"duration_seconds":387},112644,{"status":172,"finish_reason":173},"0.9000","29",279495,4143,"424.72",{"id":389,"error":107,"extra":390,"score":391,"passed":4,"case_key":392,"cost_usd":107,"sample_idx":142,"input_tokens":393,"output_tokens":394,"has_trajectory":118,"duration_seconds":395},112645,{"status":172,"finish_reason":173},"0.8333","30",204984,7647,"734.97",{"id":397,"error":107,"extra":398,"score":399,"passed":4,"case_key":400,"cost_usd":107,"sample_idx":142,"input_tokens":401,"output_tokens":402,"has_trajectory":118,"duration_seconds":403},112646,{"status":172,"finish_reason":173},"0.5833","31",728610,6199,"609.69",{"id":405,"error":107,"extra":406,"score":407,"passed":4,"case_key":408,"cost_usd":107,"sample_idx":142,"input_tokens":409,"output_tokens":410,"has_trajectory":118,"duration_seconds":411},112647,{"status":172,"finish_reason":173},"0.7778","32",447045,6586,"603.70",{"id":413,"error":107,"extra":414,"score":391,"passed":4,"case_key":415,"cost_usd":107,"sample_idx":142,"input_tokens":416,"output_tokens":417,"has_trajectory":118,"duration_seconds":418},112648,{"status":172,"finish_reason":173},"33",711974,23420,"2077.95",{"id":420,"error":107,"extra":421,"score":422,"passed":4,"case_key":423,"cost_usd":107,"sample_idx":142,"input_tokens":424,"output_tokens":425,"has_trajectory":118,"duration_seconds":426},112649,{"status":172,"finish_reason":173},"0.3333","34",787370,18359,"1627.09",{"id":428,"error":107,"extra":429,"score":430,"passed":4,"case_key":431,"cost_usd":107,"sample_idx":142,"input_tokens":432,"output_tokens":433,"has_trajectory":118,"duration_seconds":434},112650,{"status":172,"finish_reason":173},"0.3750","35",356764,11775,"1058.31",{"id":436,"error":107,"extra":437,"score":188,"passed":4,"case_key":438,"cost_usd":107,"sample_idx":142,"input_tokens":439,"output_tokens":440,"has_trajectory":118,"duration_seconds":441},112651,{"status":172,"finish_reason":173},"36",322912,4611,"429.84",{"id":443,"error":107,"extra":444,"score":391,"passed":4,"case_key":445,"cost_usd":107,"sample_idx":142,"input_tokens":446,"output_tokens":447,"has_trajectory":118,"duration_seconds":448},112652,{"status":172,"finish_reason":173},"37",1446151,12617,"1133.67",{"id":450,"error":107,"extra":451,"score":146,"passed":118,"case_key":452,"cost_usd":107,"sample_idx":142,"input_tokens":453,"output_tokens":454,"has_trajectory":118,"duration_seconds":455},112653,{"status":172,"finish_reason":173},"38",567681,8084,"733.68",{"id":457,"error":107,"extra":458,"score":146,"passed":118,"case_key":459,"cost_usd":107,"sample_idx":142,"input_tokens":460,"output_tokens":461,"has_trajectory":118,"duration_seconds":462},112654,{"status":172,"finish_reason":173},"39",761008,7918,"720.97",{"id":464,"error":107,"extra":465,"score":146,"passed":118,"case_key":466,"cost_usd":107,"sample_idx":142,"input_tokens":467,"output_tokens":468,"has_trajectory":118,"duration_seconds":469},112655,{"status":172,"finish_reason":173},"40",499954,7291,"661.86",{"id":471,"error":107,"extra":472,"score":146,"passed":118,"case_key":473,"cost_usd":107,"sample_idx":142,"input_tokens":474,"output_tokens":475,"has_trajectory":118,"duration_seconds":476},112656,{"status":172,"finish_reason":173},"41",672022,10768,"964.31",{"id":478,"error":107,"extra":479,"score":146,"passed":118,"case_key":480,"cost_usd":107,"sample_idx":142,"input_tokens":481,"output_tokens":482,"has_trajectory":118,"duration_seconds":483},112657,{"status":172,"finish_reason":173},"42",256110,2093,"204.55",{"id":485,"error":107,"extra":486,"score":146,"passed":118,"case_key":487,"cost_usd":107,"sample_idx":142,"input_tokens":488,"output_tokens":489,"has_trajectory":118,"duration_seconds":490},112658,{"status":172,"finish_reason":173},"43",411611,5358,"494.72",{"id":492,"error":107,"extra":493,"score":147,"passed":4,"case_key":496,"cost_usd":107,"sample_idx":142,"input_tokens":497,"output_tokens":498,"has_trajectory":118,"duration_seconds":499},112659,{"status":494,"finish_reason":495},"truncated","tool_calls","44",2730427,40463,"3472.61",{"id":501,"error":107,"extra":502,"score":503,"passed":4,"case_key":504,"cost_usd":107,"sample_idx":142,"input_tokens":505,"output_tokens":506,"has_trajectory":118,"duration_seconds":507},112660,{"status":172,"finish_reason":173},"0.8182","45",457647,6609,"602.80",{"id":509,"error":107,"extra":510,"score":146,"passed":118,"case_key":511,"cost_usd":107,"sample_idx":142,"input_tokens":512,"output_tokens":513,"has_trajectory":118,"duration_seconds":514},112661,{"status":172,"finish_reason":173},"46",637289,6713,"612.28",{"id":516,"error":107,"extra":517,"score":518,"passed":4,"case_key":519,"cost_usd":107,"sample_idx":142,"input_tokens":520,"output_tokens":521,"has_trajectory":118,"duration_seconds":522},112662,{"status":172,"finish_reason":173},"0.2500","47",877183,12771,"1135.02",{"id":524,"error":107,"extra":525,"score":146,"passed":118,"case_key":526,"cost_usd":107,"sample_idx":142,"input_tokens":527,"output_tokens":528,"has_trajectory":118,"duration_seconds":529},112663,{"status":172,"finish_reason":173},"48",746412,8617,"773.23",{"id":531,"error":107,"extra":532,"score":533,"passed":4,"case_key":534,"cost_usd":107,"sample_idx":142,"input_tokens":535,"output_tokens":536,"has_trajectory":118,"duration_seconds":537},112664,{"status":172,"finish_reason":173},"0.5714","49",422187,5448,"492.68",{"total":117,"failed":153,"passed":154,"run_id":106,"ungraded":142,"sample_idx":142,"trajectories":117}]