[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"api:\u002Fnav:{}":3,"api:\u002Frecords\u002F39:{}":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":72,"ranked_count":72,"samples":152,"other_harnesses":163,"distribution":164,"cases":175},{"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":73,"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},39,null,"0.6525",{},{"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,"2026-10-19",38927244,1903602,"360.45",52569044,{"access":127,"effort":128,"family":36,"is_tier":119,"hardware":107,"model_id":54,"provider":107,"data_date":129,"precision":107,"categories":130,"is_primary":119,"model_name":36,"model_slug":37,"short_name":36,"variant_id":73,"effort_rank":139,"input_price":107,"vendor_name":32,"vendor_slug":33,"architecture":107,"output_price":107,"overall_rank":43,"ranked_count":72,"release_date":140,"variant_name":141,"variant_slug":142,"vendor_order":143,"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":119,"is_open_weights":119,"inference_engine":107},"api","max","2026-10-23",[131,133,135,137],{"name":41,"rank":54,"slug":42,"score":132,"expected":43,"available":54,"ranked_count":72},"72.997032640949555000000000",{"name":45,"rank":120,"slug":46,"score":134,"expected":47,"available":72,"ranked_count":72},"59.363333333333333750000000",{"name":49,"rank":54,"slug":50,"score":136,"expected":43,"available":43,"ranked_count":72},"54.225000000000000000000000",{"name":52,"rank":54,"slug":53,"score":138,"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":120,"name":81,"slug":82,"license":145,"metrics":146,"version":107,"is_active":119,"num_cases":118,"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":119,"bundle_size_bytes":151},"public",[],"1.0000","0.0000","2026-10-28T09:47:38.906402+08:00","Accuracy",3304837814,[153,156,159,162],{"total":118,"failed":154,"passed":155,"run_id":106,"ungraded":143,"sample_idx":143,"trajectories":118},36,64,{"total":118,"failed":157,"passed":158,"run_id":106,"ungraded":143,"sample_idx":54,"trajectories":118},32,68,{"total":118,"failed":160,"passed":161,"run_id":106,"ungraded":143,"sample_idx":43,"trajectories":118},35,65,{"total":118,"failed":154,"passed":155,"run_id":106,"ungraded":143,"sample_idx":120,"trajectories":118},[],[165,168,171,174],{"name":28,"rank":54,"score":166,"run_id":167,"model_slug":29,"vendor_slug":25},"0.8300",57,{"name":12,"rank":43,"score":169,"run_id":170,"model_slug":13,"vendor_slug":9},"0.8125",112,{"name":20,"rank":120,"score":172,"run_id":173,"model_slug":21,"vendor_slug":17},"0.7550",12,{"name":36,"rank":72,"score":108,"run_id":106,"model_slug":37,"vendor_slug":33},{"restricted":4,"rows":176,"counts":517,"next_after":512},[177,186,194,201,208,215,222,229,235,242,249,256,262,269,276,283,289,295,301,308,315,322,329,336,342,349,355,361,367,373,379,386,393,400,407,414,421,428,435,442,449,456,463,470,477,484,491,498,504,511],{"id":178,"error":107,"extra":179,"score":147,"passed":119,"case_key":182,"cost_usd":107,"sample_idx":143,"input_tokens":183,"output_tokens":184,"has_trajectory":119,"duration_seconds":185},111615,{"status":180,"finish_reason":181},"completed","stop","0",95407,886,"63.03",{"id":187,"error":107,"extra":188,"score":148,"passed":4,"case_key":191,"cost_usd":107,"sample_idx":143,"input_tokens":192,"output_tokens":117,"has_trajectory":119,"duration_seconds":193},111619,{"status":189,"finish_reason":190},"failed","length","1",95398,"1468.16",{"id":195,"error":107,"extra":196,"score":147,"passed":119,"case_key":197,"cost_usd":107,"sample_idx":143,"input_tokens":198,"output_tokens":199,"has_trajectory":119,"duration_seconds":200},111623,{"status":180,"finish_reason":181},"2",95389,773,"53.11",{"id":202,"error":107,"extra":203,"score":147,"passed":119,"case_key":204,"cost_usd":107,"sample_idx":143,"input_tokens":205,"output_tokens":206,"has_trajectory":119,"duration_seconds":207},111627,{"status":180,"finish_reason":181},"3",113694,645,"41.60",{"id":209,"error":107,"extra":210,"score":148,"passed":4,"case_key":211,"cost_usd":107,"sample_idx":143,"input_tokens":212,"output_tokens":213,"has_trajectory":119,"duration_seconds":214},111631,{"status":180,"finish_reason":181},"4",113695,1682,"169.52",{"id":216,"error":107,"extra":217,"score":147,"passed":119,"case_key":218,"cost_usd":107,"sample_idx":143,"input_tokens":219,"output_tokens":220,"has_trajectory":119,"duration_seconds":221},111635,{"status":180,"finish_reason":181},"5",76838,993,"105.24",{"id":223,"error":107,"extra":224,"score":147,"passed":119,"case_key":225,"cost_usd":107,"sample_idx":143,"input_tokens":226,"output_tokens":227,"has_trajectory":119,"duration_seconds":228},111639,{"status":180,"finish_reason":181},"6",76848,1492,"158.67",{"id":230,"error":107,"extra":231,"score":148,"passed":4,"case_key":232,"cost_usd":107,"sample_idx":143,"input_tokens":233,"output_tokens":117,"has_trajectory":119,"duration_seconds":234},111643,{"status":189,"finish_reason":190},"7",76886,"1460.48",{"id":236,"error":107,"extra":237,"score":148,"passed":4,"case_key":238,"cost_usd":107,"sample_idx":143,"input_tokens":239,"output_tokens":240,"has_trajectory":119,"duration_seconds":241},111647,{"status":180,"finish_reason":181},"8",76820,1899,"169.80",{"id":243,"error":107,"extra":244,"score":148,"passed":4,"case_key":245,"cost_usd":107,"sample_idx":143,"input_tokens":246,"output_tokens":247,"has_trajectory":119,"duration_seconds":248},111651,{"status":180,"finish_reason":181},"9",78787,14577,"1282.33",{"id":250,"error":107,"extra":251,"score":147,"passed":119,"case_key":252,"cost_usd":107,"sample_idx":143,"input_tokens":253,"output_tokens":254,"has_trajectory":119,"duration_seconds":255},111655,{"status":180,"finish_reason":181},"10",78797,1422,"127.52",{"id":257,"error":107,"extra":258,"score":147,"passed":119,"case_key":259,"cost_usd":107,"sample_idx":143,"input_tokens":253,"output_tokens":260,"has_trajectory":119,"duration_seconds":261},111659,{"status":180,"finish_reason":181},"11",860,"77.83",{"id":263,"error":107,"extra":264,"score":147,"passed":119,"case_key":265,"cost_usd":107,"sample_idx":143,"input_tokens":266,"output_tokens":267,"has_trajectory":119,"duration_seconds":268},111663,{"status":180,"finish_reason":181},"12",78771,610,"53.42",{"id":270,"error":107,"extra":271,"score":147,"passed":119,"case_key":272,"cost_usd":107,"sample_idx":143,"input_tokens":273,"output_tokens":274,"has_trajectory":119,"duration_seconds":275},111667,{"status":180,"finish_reason":181},"13",79129,1517,"132.74",{"id":277,"error":107,"extra":278,"score":147,"passed":119,"case_key":279,"cost_usd":107,"sample_idx":143,"input_tokens":280,"output_tokens":281,"has_trajectory":119,"duration_seconds":282},111671,{"status":180,"finish_reason":181},"14",83860,1063,"92.74",{"id":284,"error":107,"extra":285,"score":148,"passed":4,"case_key":286,"cost_usd":107,"sample_idx":143,"input_tokens":287,"output_tokens":117,"has_trajectory":119,"duration_seconds":288},111675,{"status":189,"finish_reason":190},"15",83970,"1419.80",{"id":290,"error":107,"extra":291,"score":148,"passed":4,"case_key":292,"cost_usd":107,"sample_idx":143,"input_tokens":293,"output_tokens":117,"has_trajectory":119,"duration_seconds":294},111679,{"status":189,"finish_reason":190},"16",83879,"1414.61",{"id":296,"error":107,"extra":297,"score":148,"passed":4,"case_key":298,"cost_usd":107,"sample_idx":143,"input_tokens":299,"output_tokens":117,"has_trajectory":119,"duration_seconds":300},111683,{"status":189,"finish_reason":190},"17",80554,"1374.63",{"id":302,"error":107,"extra":303,"score":148,"passed":4,"case_key":304,"cost_usd":107,"sample_idx":143,"input_tokens":305,"output_tokens":306,"has_trajectory":119,"duration_seconds":307},111687,{"status":180,"finish_reason":181},"18",101356,11434,"938.67",{"id":309,"error":107,"extra":310,"score":147,"passed":119,"case_key":311,"cost_usd":107,"sample_idx":143,"input_tokens":312,"output_tokens":313,"has_trajectory":119,"duration_seconds":314},111691,{"status":180,"finish_reason":181},"19",101357,3070,"257.94",{"id":316,"error":107,"extra":317,"score":147,"passed":119,"case_key":318,"cost_usd":107,"sample_idx":143,"input_tokens":319,"output_tokens":320,"has_trajectory":119,"duration_seconds":321},111695,{"status":180,"finish_reason":181},"20",101312,385,"31.98",{"id":323,"error":107,"extra":324,"score":148,"passed":4,"case_key":325,"cost_usd":107,"sample_idx":143,"input_tokens":326,"output_tokens":327,"has_trajectory":119,"duration_seconds":328},111699,{"status":180,"finish_reason":181},"21",102060,2752,"213.29",{"id":330,"error":107,"extra":331,"score":147,"passed":119,"case_key":332,"cost_usd":107,"sample_idx":143,"input_tokens":333,"output_tokens":334,"has_trajectory":119,"duration_seconds":335},111703,{"status":180,"finish_reason":181},"22",102008,684,"52.92",{"id":337,"error":107,"extra":338,"score":148,"passed":4,"case_key":339,"cost_usd":107,"sample_idx":143,"input_tokens":326,"output_tokens":340,"has_trajectory":119,"duration_seconds":341},111707,{"status":180,"finish_reason":181},"23",1235,"103.08",{"id":343,"error":107,"extra":344,"score":147,"passed":119,"case_key":345,"cost_usd":107,"sample_idx":143,"input_tokens":346,"output_tokens":347,"has_trajectory":119,"duration_seconds":348},111711,{"status":180,"finish_reason":181},"24",101990,1986,"153.69",{"id":350,"error":107,"extra":351,"score":148,"passed":4,"case_key":352,"cost_usd":107,"sample_idx":143,"input_tokens":353,"output_tokens":117,"has_trajectory":119,"duration_seconds":354},111715,{"status":189,"finish_reason":190},"25",102038,"1277.44",{"id":356,"error":107,"extra":357,"score":148,"passed":4,"case_key":358,"cost_usd":107,"sample_idx":143,"input_tokens":359,"output_tokens":117,"has_trajectory":119,"duration_seconds":360},111719,{"status":189,"finish_reason":190},"26",99921,"1274.48",{"id":362,"error":107,"extra":363,"score":148,"passed":4,"case_key":364,"cost_usd":107,"sample_idx":143,"input_tokens":365,"output_tokens":117,"has_trajectory":119,"duration_seconds":366},111723,{"status":189,"finish_reason":190},"27",99942,"1281.76",{"id":368,"error":107,"extra":369,"score":148,"passed":4,"case_key":370,"cost_usd":107,"sample_idx":143,"input_tokens":371,"output_tokens":117,"has_trajectory":119,"duration_seconds":372},111727,{"status":189,"finish_reason":190},"28",99944,"1287.73",{"id":374,"error":107,"extra":375,"score":148,"passed":4,"case_key":376,"cost_usd":107,"sample_idx":143,"input_tokens":377,"output_tokens":117,"has_trajectory":119,"duration_seconds":378},111731,{"status":189,"finish_reason":190},"29",99999,"1327.59",{"id":380,"error":107,"extra":381,"score":147,"passed":119,"case_key":382,"cost_usd":107,"sample_idx":143,"input_tokens":383,"output_tokens":384,"has_trajectory":119,"duration_seconds":385},111735,{"status":180,"finish_reason":181},"30",79039,1441,"118.03",{"id":387,"error":107,"extra":388,"score":147,"passed":119,"case_key":389,"cost_usd":107,"sample_idx":143,"input_tokens":390,"output_tokens":391,"has_trajectory":119,"duration_seconds":392},111739,{"status":180,"finish_reason":181},"31",79037,9335,"728.55",{"id":394,"error":107,"extra":395,"score":147,"passed":119,"case_key":396,"cost_usd":107,"sample_idx":143,"input_tokens":397,"output_tokens":398,"has_trajectory":119,"duration_seconds":399},111743,{"status":180,"finish_reason":181},"32",103394,947,"78.32",{"id":401,"error":107,"extra":402,"score":147,"passed":119,"case_key":403,"cost_usd":107,"sample_idx":143,"input_tokens":404,"output_tokens":405,"has_trajectory":119,"duration_seconds":406},111747,{"status":180,"finish_reason":181},"33",103395,2212,"158.13",{"id":408,"error":107,"extra":409,"score":147,"passed":119,"case_key":410,"cost_usd":107,"sample_idx":143,"input_tokens":411,"output_tokens":412,"has_trajectory":119,"duration_seconds":413},111751,{"status":180,"finish_reason":181},"34",103408,5167,"384.58",{"id":415,"error":107,"extra":416,"score":147,"passed":119,"case_key":417,"cost_usd":107,"sample_idx":143,"input_tokens":418,"output_tokens":419,"has_trajectory":119,"duration_seconds":420},111755,{"status":180,"finish_reason":181},"35",82094,1638,"123.92",{"id":422,"error":107,"extra":423,"score":147,"passed":119,"case_key":424,"cost_usd":107,"sample_idx":143,"input_tokens":425,"output_tokens":426,"has_trajectory":119,"duration_seconds":427},111759,{"status":180,"finish_reason":181},"36",82072,633,"46.87",{"id":429,"error":107,"extra":430,"score":147,"passed":119,"case_key":431,"cost_usd":107,"sample_idx":143,"input_tokens":432,"output_tokens":433,"has_trajectory":119,"duration_seconds":434},111763,{"status":180,"finish_reason":181},"37",82089,6024,"442.16",{"id":436,"error":107,"extra":437,"score":147,"passed":119,"case_key":438,"cost_usd":107,"sample_idx":143,"input_tokens":439,"output_tokens":440,"has_trajectory":119,"duration_seconds":441},111767,{"status":180,"finish_reason":181},"38",82079,3930,"290.71",{"id":443,"error":107,"extra":444,"score":148,"passed":4,"case_key":445,"cost_usd":107,"sample_idx":143,"input_tokens":446,"output_tokens":447,"has_trajectory":119,"duration_seconds":448},111771,{"status":180,"finish_reason":181},"39",82088,2314,"177.06",{"id":450,"error":107,"extra":451,"score":147,"passed":119,"case_key":452,"cost_usd":107,"sample_idx":143,"input_tokens":453,"output_tokens":454,"has_trajectory":119,"duration_seconds":455},111775,{"status":180,"finish_reason":181},"40",97924,429,"36.35",{"id":457,"error":107,"extra":458,"score":147,"passed":119,"case_key":459,"cost_usd":107,"sample_idx":143,"input_tokens":460,"output_tokens":461,"has_trajectory":119,"duration_seconds":462},111779,{"status":180,"finish_reason":181},"41",97950,1162,"92.07",{"id":464,"error":107,"extra":465,"score":147,"passed":119,"case_key":466,"cost_usd":107,"sample_idx":143,"input_tokens":467,"output_tokens":468,"has_trajectory":119,"duration_seconds":469},111783,{"status":180,"finish_reason":181},"42",84460,5232,"382.54",{"id":471,"error":107,"extra":472,"score":147,"passed":119,"case_key":473,"cost_usd":107,"sample_idx":143,"input_tokens":474,"output_tokens":475,"has_trajectory":119,"duration_seconds":476},111787,{"status":180,"finish_reason":181},"43",84450,13918,"987.41",{"id":478,"error":107,"extra":479,"score":147,"passed":119,"case_key":480,"cost_usd":107,"sample_idx":143,"input_tokens":481,"output_tokens":482,"has_trajectory":119,"duration_seconds":483},111791,{"status":180,"finish_reason":181},"44",84446,583,"39.69",{"id":485,"error":107,"extra":486,"score":147,"passed":119,"case_key":487,"cost_usd":107,"sample_idx":143,"input_tokens":488,"output_tokens":489,"has_trajectory":119,"duration_seconds":490},111795,{"status":180,"finish_reason":181},"45",84510,1288,"88.77",{"id":492,"error":107,"extra":493,"score":148,"passed":4,"case_key":494,"cost_usd":107,"sample_idx":143,"input_tokens":495,"output_tokens":496,"has_trajectory":119,"duration_seconds":497},111799,{"status":180,"finish_reason":181},"46",84454,11833,"834.53",{"id":499,"error":107,"extra":500,"score":148,"passed":4,"case_key":501,"cost_usd":107,"sample_idx":143,"input_tokens":502,"output_tokens":117,"has_trajectory":119,"duration_seconds":503},111803,{"status":189,"finish_reason":190},"47",84489,"1176.83",{"id":505,"error":107,"extra":506,"score":148,"passed":4,"case_key":507,"cost_usd":107,"sample_idx":143,"input_tokens":508,"output_tokens":509,"has_trajectory":119,"duration_seconds":510},111807,{"status":180,"finish_reason":181},"48",84456,4100,"295.16",{"id":512,"error":107,"extra":513,"score":147,"passed":119,"case_key":514,"cost_usd":107,"sample_idx":143,"input_tokens":495,"output_tokens":515,"has_trajectory":119,"duration_seconds":516},111811,{"status":180,"finish_reason":181},"49",1431,"101.69",{"total":118,"failed":154,"passed":155,"run_id":106,"ungraded":143,"sample_idx":143,"trajectories":118}]