[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"api:\u002Fnav:{}":3,"api:\u002Frecords\u002F42:{}":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":144,"rank":72,"ranked_count":72,"samples":152,"other_harnesses":156,"distribution":157,"cases":168},{"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":119,"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},42,null,"0.8507",{},{"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","0.60",{"top_k":114},-1,"OPT 1478395",32768,12032,true,7,"2026-10-16",2583897,50800608,"227.07",46257854,{"access":126,"effort":127,"family":36,"is_tier":118,"hardware":107,"model_id":54,"provider":107,"data_date":128,"precision":107,"categories":129,"is_primary":118,"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":118,"is_open_weights":118,"inference_engine":107},"api","max","2026-10-23",[130,132,135,137],{"name":41,"rank":54,"slug":42,"score":131,"expected":43,"available":54,"ranked_count":72},"72.997032640949555000000000",{"name":45,"rank":133,"slug":46,"score":134,"expected":47,"available":72,"ranked_count":72},3,"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":119,"name":96,"slug":97,"license":145,"metrics":146,"version":107,"is_active":118,"num_cases":117,"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":118,"bundle_size_bytes":151},"public",[],"1.0000","0.0000","2026-10-28T09:47:38.906402+08:00","Accuracy",1829320613,[153],{"total":117,"failed":154,"passed":155,"run_id":106,"ungraded":143,"sample_idx":143,"trajectories":117},1796,10236,[],[158,161,164,167],{"name":28,"rank":54,"score":159,"run_id":160,"model_slug":29,"vendor_slug":25},"0.8877",60,{"name":20,"rank":43,"score":162,"run_id":163,"model_slug":21,"vendor_slug":17},"0.8713",15,{"name":12,"rank":133,"score":165,"run_id":166,"model_slug":13,"vendor_slug":9},"0.8516",117,{"name":36,"rank":72,"score":108,"run_id":106,"model_slug":37,"vendor_slug":33},{"restricted":4,"rows":169,"counts":515,"next_after":510},[170,179,186,193,200,207,214,221,228,235,242,248,255,262,268,274,281,288,295,302,309,316,323,330,337,344,351,357,364,371,378,385,392,399,406,413,420,426,433,440,447,454,461,467,475,481,488,495,502,509],{"id":171,"error":107,"extra":172,"score":147,"passed":118,"case_key":175,"cost_usd":107,"sample_idx":143,"input_tokens":176,"output_tokens":177,"has_trajectory":118,"duration_seconds":178},113215,{"status":173,"finish_reason":174},"completed","stop","0",182,707,"214.80",{"id":180,"error":107,"extra":181,"score":147,"passed":118,"case_key":182,"cost_usd":107,"sample_idx":143,"input_tokens":183,"output_tokens":184,"has_trajectory":118,"duration_seconds":185},113216,{"status":173,"finish_reason":174},"1",199,10921,"1229.20",{"id":187,"error":107,"extra":188,"score":147,"passed":118,"case_key":189,"cost_usd":107,"sample_idx":143,"input_tokens":190,"output_tokens":191,"has_trajectory":118,"duration_seconds":192},113217,{"status":173,"finish_reason":174},"2",222,3090,"472.36",{"id":194,"error":107,"extra":195,"score":147,"passed":118,"case_key":196,"cost_usd":107,"sample_idx":143,"input_tokens":197,"output_tokens":198,"has_trajectory":118,"duration_seconds":199},113218,{"status":173,"finish_reason":174},"3",118,448,"187.40",{"id":201,"error":107,"extra":202,"score":147,"passed":118,"case_key":203,"cost_usd":107,"sample_idx":143,"input_tokens":204,"output_tokens":205,"has_trajectory":118,"duration_seconds":206},113219,{"status":173,"finish_reason":174},"4",219,367,"178.48",{"id":208,"error":107,"extra":209,"score":147,"passed":118,"case_key":210,"cost_usd":107,"sample_idx":143,"input_tokens":211,"output_tokens":212,"has_trajectory":118,"duration_seconds":213},113220,{"status":173,"finish_reason":174},"5",172,590,"202.68",{"id":215,"error":107,"extra":216,"score":147,"passed":118,"case_key":217,"cost_usd":107,"sample_idx":143,"input_tokens":218,"output_tokens":219,"has_trajectory":118,"duration_seconds":220},113221,{"status":173,"finish_reason":174},"6",139,429,"185.20",{"id":222,"error":107,"extra":223,"score":147,"passed":118,"case_key":224,"cost_usd":107,"sample_idx":143,"input_tokens":225,"output_tokens":226,"has_trajectory":118,"duration_seconds":227},113222,{"status":173,"finish_reason":174},"7",105,287,"169.22",{"id":229,"error":107,"extra":230,"score":147,"passed":118,"case_key":231,"cost_usd":107,"sample_idx":143,"input_tokens":232,"output_tokens":233,"has_trajectory":118,"duration_seconds":234},113223,{"status":173,"finish_reason":174},"8",111,500,"193.13",{"id":236,"error":107,"extra":237,"score":147,"passed":118,"case_key":238,"cost_usd":107,"sample_idx":143,"input_tokens":239,"output_tokens":240,"has_trajectory":118,"duration_seconds":241},113224,{"status":173,"finish_reason":174},"9",135,376,"179.25",{"id":243,"error":107,"extra":244,"score":147,"passed":118,"case_key":245,"cost_usd":107,"sample_idx":143,"input_tokens":166,"output_tokens":246,"has_trajectory":118,"duration_seconds":247},113225,{"status":173,"finish_reason":174},"10",130,"135.79",{"id":249,"error":107,"extra":250,"score":148,"passed":4,"case_key":251,"cost_usd":107,"sample_idx":143,"input_tokens":252,"output_tokens":253,"has_trajectory":118,"duration_seconds":254},113226,{"status":173,"finish_reason":174},"11",107,1784,"341.73",{"id":256,"error":107,"extra":257,"score":147,"passed":118,"case_key":258,"cost_usd":107,"sample_idx":143,"input_tokens":259,"output_tokens":260,"has_trajectory":118,"duration_seconds":261},113227,{"status":173,"finish_reason":174},"12",110,90,"126.10",{"id":263,"error":107,"extra":264,"score":148,"passed":4,"case_key":265,"cost_usd":107,"sample_idx":143,"input_tokens":225,"output_tokens":266,"has_trajectory":118,"duration_seconds":267},113228,{"status":173,"finish_reason":174},"13",300,"172.20",{"id":269,"error":107,"extra":270,"score":147,"passed":118,"case_key":271,"cost_usd":107,"sample_idx":143,"input_tokens":259,"output_tokens":272,"has_trajectory":118,"duration_seconds":273},113229,{"status":173,"finish_reason":174},"14",2593,"423.82",{"id":275,"error":107,"extra":276,"score":147,"passed":118,"case_key":277,"cost_usd":107,"sample_idx":143,"input_tokens":278,"output_tokens":279,"has_trajectory":118,"duration_seconds":280},113230,{"status":173,"finish_reason":174},"15",137,882,"233.52",{"id":282,"error":107,"extra":283,"score":147,"passed":118,"case_key":284,"cost_usd":107,"sample_idx":143,"input_tokens":285,"output_tokens":286,"has_trajectory":118,"duration_seconds":287},113231,{"status":173,"finish_reason":174},"16",202,19496,"1554.03",{"id":289,"error":107,"extra":290,"score":147,"passed":118,"case_key":291,"cost_usd":107,"sample_idx":143,"input_tokens":292,"output_tokens":293,"has_trajectory":118,"duration_seconds":294},113232,{"status":173,"finish_reason":174},"17",165,803,"224.98",{"id":296,"error":107,"extra":297,"score":147,"passed":118,"case_key":298,"cost_usd":107,"sample_idx":143,"input_tokens":299,"output_tokens":300,"has_trajectory":118,"duration_seconds":301},113233,{"status":173,"finish_reason":174},"18",398,1671,"330.21",{"id":303,"error":107,"extra":304,"score":147,"passed":118,"case_key":305,"cost_usd":107,"sample_idx":143,"input_tokens":306,"output_tokens":307,"has_trajectory":118,"duration_seconds":308},113234,{"status":173,"finish_reason":174},"19",176,292,"170.22",{"id":310,"error":107,"extra":311,"score":147,"passed":118,"case_key":312,"cost_usd":107,"sample_idx":143,"input_tokens":313,"output_tokens":314,"has_trajectory":118,"duration_seconds":315},113235,{"status":173,"finish_reason":174},"20",337,1233,"285.28",{"id":317,"error":107,"extra":318,"score":147,"passed":118,"case_key":319,"cost_usd":107,"sample_idx":143,"input_tokens":320,"output_tokens":321,"has_trajectory":118,"duration_seconds":322},113236,{"status":173,"finish_reason":174},"21",231,257,"162.74",{"id":324,"error":107,"extra":325,"score":147,"passed":118,"case_key":326,"cost_usd":107,"sample_idx":143,"input_tokens":327,"output_tokens":328,"has_trajectory":118,"duration_seconds":329},113237,{"status":173,"finish_reason":174},"22",156,255,"162.45",{"id":331,"error":107,"extra":332,"score":148,"passed":4,"case_key":333,"cost_usd":107,"sample_idx":143,"input_tokens":334,"output_tokens":335,"has_trajectory":118,"duration_seconds":336},113238,{"status":173,"finish_reason":174},"23",147,635,"206.79",{"id":338,"error":107,"extra":339,"score":147,"passed":118,"case_key":340,"cost_usd":107,"sample_idx":143,"input_tokens":341,"output_tokens":342,"has_trajectory":118,"duration_seconds":343},113239,{"status":173,"finish_reason":174},"24",178,725,"216.62",{"id":345,"error":107,"extra":346,"score":147,"passed":118,"case_key":347,"cost_usd":107,"sample_idx":143,"input_tokens":348,"output_tokens":349,"has_trajectory":118,"duration_seconds":350},113240,{"status":173,"finish_reason":174},"25",417,238,"159.11",{"id":352,"error":107,"extra":353,"score":147,"passed":118,"case_key":354,"cost_usd":107,"sample_idx":143,"input_tokens":349,"output_tokens":355,"has_trajectory":118,"duration_seconds":356},113241,{"status":173,"finish_reason":174},"26",683,"211.84",{"id":358,"error":107,"extra":359,"score":147,"passed":118,"case_key":360,"cost_usd":107,"sample_idx":143,"input_tokens":361,"output_tokens":362,"has_trajectory":118,"duration_seconds":363},113242,{"status":173,"finish_reason":174},"27",129,175,"145.91",{"id":365,"error":107,"extra":366,"score":147,"passed":118,"case_key":367,"cost_usd":107,"sample_idx":143,"input_tokens":368,"output_tokens":369,"has_trajectory":118,"duration_seconds":370},113243,{"status":173,"finish_reason":174},"28",150,575,"201.17",{"id":372,"error":107,"extra":373,"score":147,"passed":118,"case_key":374,"cost_usd":107,"sample_idx":143,"input_tokens":375,"output_tokens":376,"has_trajectory":118,"duration_seconds":377},113244,{"status":173,"finish_reason":174},"29",146,269,"165.65",{"id":379,"error":107,"extra":380,"score":147,"passed":118,"case_key":381,"cost_usd":107,"sample_idx":143,"input_tokens":382,"output_tokens":383,"has_trajectory":118,"duration_seconds":384},113245,{"status":173,"finish_reason":174},"30",141,140,"137.69",{"id":386,"error":107,"extra":387,"score":147,"passed":118,"case_key":388,"cost_usd":107,"sample_idx":143,"input_tokens":389,"output_tokens":390,"has_trajectory":118,"duration_seconds":391},113246,{"status":173,"finish_reason":174},"31",216,237,"159.00",{"id":393,"error":107,"extra":394,"score":147,"passed":118,"case_key":395,"cost_usd":107,"sample_idx":143,"input_tokens":396,"output_tokens":397,"has_trajectory":118,"duration_seconds":398},113247,{"status":173,"finish_reason":174},"32",277,4793,"627.10",{"id":400,"error":107,"extra":401,"score":147,"passed":118,"case_key":402,"cost_usd":107,"sample_idx":143,"input_tokens":403,"output_tokens":404,"has_trajectory":118,"duration_seconds":405},113248,{"status":173,"finish_reason":174},"33",348,680,"211.53",{"id":407,"error":107,"extra":408,"score":147,"passed":118,"case_key":409,"cost_usd":107,"sample_idx":143,"input_tokens":410,"output_tokens":411,"has_trajectory":118,"duration_seconds":412},113249,{"status":173,"finish_reason":174},"34",161,306,"170.75",{"id":414,"error":107,"extra":415,"score":147,"passed":118,"case_key":416,"cost_usd":107,"sample_idx":143,"input_tokens":417,"output_tokens":418,"has_trajectory":118,"duration_seconds":419},113250,{"status":173,"finish_reason":174},"35",209,4289,"581.80",{"id":421,"error":107,"extra":422,"score":147,"passed":118,"case_key":423,"cost_usd":107,"sample_idx":143,"input_tokens":382,"output_tokens":424,"has_trajectory":118,"duration_seconds":425},113251,{"status":173,"finish_reason":174},"36",619,"205.12",{"id":427,"error":107,"extra":428,"score":147,"passed":118,"case_key":429,"cost_usd":107,"sample_idx":143,"input_tokens":430,"output_tokens":431,"has_trajectory":118,"duration_seconds":432},113252,{"status":173,"finish_reason":174},"37",145,166,"142.66",{"id":434,"error":107,"extra":435,"score":147,"passed":118,"case_key":436,"cost_usd":107,"sample_idx":143,"input_tokens":437,"output_tokens":438,"has_trajectory":118,"duration_seconds":439},113253,{"status":173,"finish_reason":174},"38",282,317,"173.63",{"id":441,"error":107,"extra":442,"score":147,"passed":118,"case_key":443,"cost_usd":107,"sample_idx":143,"input_tokens":444,"output_tokens":445,"has_trajectory":118,"duration_seconds":446},113254,{"status":173,"finish_reason":174},"39",230,835,"66.18",{"id":448,"error":107,"extra":449,"score":147,"passed":118,"case_key":450,"cost_usd":107,"sample_idx":143,"input_tokens":451,"output_tokens":452,"has_trajectory":118,"duration_seconds":453},113255,{"status":173,"finish_reason":174},"40",121,319,"173.77",{"id":455,"error":107,"extra":456,"score":147,"passed":118,"case_key":457,"cost_usd":107,"sample_idx":143,"input_tokens":458,"output_tokens":459,"has_trajectory":118,"duration_seconds":460},113256,{"status":173,"finish_reason":174},"41",173,203,"153.26",{"id":462,"error":107,"extra":463,"score":147,"passed":118,"case_key":464,"cost_usd":107,"sample_idx":143,"input_tokens":375,"output_tokens":465,"has_trajectory":118,"duration_seconds":466},113257,{"status":173,"finish_reason":174},"42",7942,"920.70",{"id":468,"error":107,"extra":469,"score":148,"passed":4,"case_key":472,"cost_usd":107,"sample_idx":143,"input_tokens":473,"output_tokens":116,"has_trajectory":118,"duration_seconds":474},113258,{"status":470,"finish_reason":471},"truncated","length","43",285,"1653.26",{"id":476,"error":107,"extra":477,"score":147,"passed":118,"case_key":478,"cost_usd":107,"sample_idx":143,"input_tokens":285,"output_tokens":479,"has_trajectory":118,"duration_seconds":480},113259,{"status":173,"finish_reason":174},"44",256,"162.67",{"id":482,"error":107,"extra":483,"score":147,"passed":118,"case_key":484,"cost_usd":107,"sample_idx":143,"input_tokens":485,"output_tokens":486,"has_trajectory":118,"duration_seconds":487},113260,{"status":173,"finish_reason":174},"45",134,3057,"467.92",{"id":489,"error":107,"extra":490,"score":147,"passed":118,"case_key":491,"cost_usd":107,"sample_idx":143,"input_tokens":492,"output_tokens":493,"has_trajectory":118,"duration_seconds":494},113261,{"status":173,"finish_reason":174},"46",212,2030,"367.62",{"id":496,"error":107,"extra":497,"score":147,"passed":118,"case_key":498,"cost_usd":107,"sample_idx":143,"input_tokens":499,"output_tokens":500,"has_trajectory":118,"duration_seconds":501},113262,{"status":173,"finish_reason":174},"47",138,87,"124.36",{"id":503,"error":107,"extra":504,"score":147,"passed":118,"case_key":505,"cost_usd":107,"sample_idx":143,"input_tokens":506,"output_tokens":507,"has_trajectory":118,"duration_seconds":508},113263,{"status":173,"finish_reason":174},"48",315,792,"224.25",{"id":510,"error":107,"extra":511,"score":147,"passed":118,"case_key":512,"cost_usd":107,"sample_idx":143,"input_tokens":513,"output_tokens":341,"has_trajectory":118,"duration_seconds":514},113264,{"status":173,"finish_reason":174},"49",159,"146.61",{"total":117,"failed":154,"passed":155,"run_id":106,"ungraded":143,"sample_idx":143,"trajectories":117}]