[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"api:\u002Fnav:{}":3,"api:\u002Frecords\u002F57:{}":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":127,"benchmark":144,"rank":54,"ranked_count":72,"samples":152,"other_harnesses":165,"distribution":166,"cases":177},{"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":121,"evaluated_at":122,"harness_name":107,"harness_slug":107,"input_tokens":123,"ttft_seconds":107,"output_tokens":124,"parent_run_id":107,"harness_version":107,"avg_case_seconds":125,"reasoning_tokens":107,"cost_per_case_usd":107,"trajectory_bundle_size_bytes":126},57,null,"0.8300",{},{"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,11,3,"2026-10-22",38064536,445163,"147.42",51632013,{"access":128,"effort":129,"family":28,"is_tier":119,"hardware":107,"model_id":121,"provider":107,"data_date":130,"precision":107,"categories":131,"is_primary":119,"model_name":28,"model_slug":29,"short_name":28,"variant_id":120,"effort_rank":139,"input_price":107,"vendor_name":24,"vendor_slug":25,"architecture":107,"output_price":107,"overall_rank":121,"ranked_count":72,"release_date":140,"variant_name":141,"variant_slug":142,"vendor_order":143,"weights_repo":107,"missing_count":121,"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":119,"is_open_weights":119,"inference_engine":107},"api","max","2026-10-24",[132,134,136,138],{"name":41,"rank":43,"slug":42,"score":133,"expected":43,"available":54,"ranked_count":72},"65.051903114186850000000000",{"name":45,"rank":43,"slug":46,"score":135,"expected":47,"available":72,"ranked_count":72},"67.050833333333332500000000",{"name":49,"rank":72,"slug":50,"score":137,"expected":43,"available":54,"ranked_count":72},"3.500000000000000000000000",{"name":52,"rank":72,"slug":53,"score":137,"expected":54,"available":54,"ranked_count":72},6,"2026-07-16","Kimi-K3 官方 API max","kimi-k3-api-max",0,{"id":121,"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},18,82,{"total":118,"failed":157,"passed":158,"run_id":106,"ungraded":143,"sample_idx":54,"trajectories":118},16,84,{"total":118,"failed":160,"passed":161,"run_id":106,"ungraded":143,"sample_idx":43,"trajectories":118},14,86,{"total":118,"failed":163,"passed":164,"run_id":106,"ungraded":143,"sample_idx":121,"trajectories":118},20,80,[],[167,168,171,174],{"name":28,"rank":54,"score":108,"run_id":106,"model_slug":29,"vendor_slug":25},{"name":12,"rank":43,"score":169,"run_id":170,"model_slug":13,"vendor_slug":9},"0.8125",112,{"name":20,"rank":121,"score":172,"run_id":173,"model_slug":21,"vendor_slug":17},"0.7550",12,{"name":36,"rank":72,"score":175,"run_id":176,"model_slug":37,"vendor_slug":33},"0.6525",39,{"restricted":4,"rows":178,"counts":529,"next_after":524},[179,188,195,202,209,216,223,230,237,244,251,258,265,272,279,286,293,300,307,314,321,328,335,342,349,356,363,370,377,384,391,398,405,412,419,426,432,439,446,453,460,467,474,481,488,495,502,509,516,523],{"id":180,"error":107,"extra":181,"score":147,"passed":119,"case_key":184,"cost_usd":107,"sample_idx":143,"input_tokens":185,"output_tokens":186,"has_trajectory":119,"duration_seconds":187},160558,{"status":182,"finish_reason":183},"completed","stop","0",94579,316,"38.80",{"id":189,"error":107,"extra":190,"score":147,"passed":119,"case_key":191,"cost_usd":107,"sample_idx":143,"input_tokens":192,"output_tokens":193,"has_trajectory":119,"duration_seconds":194},160562,{"status":182,"finish_reason":183},"1",94570,5344,"577.78",{"id":196,"error":107,"extra":197,"score":147,"passed":119,"case_key":198,"cost_usd":107,"sample_idx":143,"input_tokens":199,"output_tokens":200,"has_trajectory":119,"duration_seconds":201},160566,{"status":182,"finish_reason":183},"2",94561,687,"63.80",{"id":203,"error":107,"extra":204,"score":147,"passed":119,"case_key":205,"cost_usd":107,"sample_idx":143,"input_tokens":206,"output_tokens":207,"has_trajectory":119,"duration_seconds":208},160570,{"status":182,"finish_reason":183},"3",112569,413,"53.99",{"id":210,"error":107,"extra":211,"score":147,"passed":119,"case_key":212,"cost_usd":107,"sample_idx":143,"input_tokens":213,"output_tokens":214,"has_trajectory":119,"duration_seconds":215},160574,{"status":182,"finish_reason":183},"4",112568,1024,"108.73",{"id":217,"error":107,"extra":218,"score":147,"passed":119,"case_key":219,"cost_usd":107,"sample_idx":143,"input_tokens":220,"output_tokens":221,"has_trajectory":119,"duration_seconds":222},160578,{"status":182,"finish_reason":183},"5",71150,1104,"123.37",{"id":224,"error":107,"extra":225,"score":148,"passed":4,"case_key":226,"cost_usd":107,"sample_idx":143,"input_tokens":227,"output_tokens":228,"has_trajectory":119,"duration_seconds":229},160582,{"status":182,"finish_reason":183},"6",71161,340,"36.94",{"id":231,"error":107,"extra":232,"score":147,"passed":119,"case_key":233,"cost_usd":107,"sample_idx":143,"input_tokens":234,"output_tokens":235,"has_trajectory":119,"duration_seconds":236},160586,{"status":182,"finish_reason":183},"7",71199,549,"69.25",{"id":238,"error":107,"extra":239,"score":147,"passed":119,"case_key":240,"cost_usd":107,"sample_idx":143,"input_tokens":241,"output_tokens":242,"has_trajectory":119,"duration_seconds":243},160590,{"status":182,"finish_reason":183},"8",71133,526,"72.58",{"id":245,"error":107,"extra":246,"score":147,"passed":119,"case_key":247,"cost_usd":107,"sample_idx":143,"input_tokens":248,"output_tokens":249,"has_trajectory":119,"duration_seconds":250},160594,{"status":182,"finish_reason":183},"9",73019,774,"164.12",{"id":252,"error":107,"extra":253,"score":147,"passed":119,"case_key":254,"cost_usd":107,"sample_idx":143,"input_tokens":255,"output_tokens":256,"has_trajectory":119,"duration_seconds":257},160598,{"status":182,"finish_reason":183},"10",73029,598,"74.97",{"id":259,"error":107,"extra":260,"score":147,"passed":119,"case_key":261,"cost_usd":107,"sample_idx":143,"input_tokens":262,"output_tokens":263,"has_trajectory":119,"duration_seconds":264},160602,{"status":182,"finish_reason":183},"11",73028,401,"45.91",{"id":266,"error":107,"extra":267,"score":147,"passed":119,"case_key":268,"cost_usd":107,"sample_idx":143,"input_tokens":269,"output_tokens":270,"has_trajectory":119,"duration_seconds":271},160606,{"status":182,"finish_reason":183},"12",73003,233,"36.72",{"id":273,"error":107,"extra":274,"score":147,"passed":119,"case_key":275,"cost_usd":107,"sample_idx":143,"input_tokens":276,"output_tokens":277,"has_trajectory":119,"duration_seconds":278},160610,{"status":182,"finish_reason":183},"13",73394,446,"63.32",{"id":280,"error":107,"extra":281,"score":148,"passed":4,"case_key":282,"cost_usd":107,"sample_idx":143,"input_tokens":283,"output_tokens":284,"has_trajectory":119,"duration_seconds":285},160614,{"status":182,"finish_reason":183},"14",77823,393,"72.49",{"id":287,"error":107,"extra":288,"score":147,"passed":119,"case_key":289,"cost_usd":107,"sample_idx":143,"input_tokens":290,"output_tokens":291,"has_trajectory":119,"duration_seconds":292},160618,{"status":182,"finish_reason":183},"15",77932,3362,"491.20",{"id":294,"error":107,"extra":295,"score":147,"passed":119,"case_key":296,"cost_usd":107,"sample_idx":143,"input_tokens":297,"output_tokens":298,"has_trajectory":119,"duration_seconds":299},160622,{"status":182,"finish_reason":183},"16",77842,1483,"254.11",{"id":301,"error":107,"extra":302,"score":148,"passed":4,"case_key":303,"cost_usd":107,"sample_idx":143,"input_tokens":304,"output_tokens":305,"has_trajectory":119,"duration_seconds":306},160626,{"status":182,"finish_reason":183},"17",74539,642,"161.65",{"id":308,"error":107,"extra":309,"score":147,"passed":119,"case_key":310,"cost_usd":107,"sample_idx":143,"input_tokens":311,"output_tokens":312,"has_trajectory":119,"duration_seconds":313},160630,{"status":182,"finish_reason":183},"18",95888,1093,"164.33",{"id":315,"error":107,"extra":316,"score":147,"passed":119,"case_key":317,"cost_usd":107,"sample_idx":143,"input_tokens":318,"output_tokens":319,"has_trajectory":119,"duration_seconds":320},160634,{"status":182,"finish_reason":183},"19",95889,1213,"145.59",{"id":322,"error":107,"extra":323,"score":147,"passed":119,"case_key":324,"cost_usd":107,"sample_idx":143,"input_tokens":325,"output_tokens":326,"has_trajectory":119,"duration_seconds":327},160638,{"status":182,"finish_reason":183},"20",95844,355,"85.36",{"id":329,"error":107,"extra":330,"score":148,"passed":4,"case_key":331,"cost_usd":107,"sample_idx":143,"input_tokens":332,"output_tokens":333,"has_trajectory":119,"duration_seconds":334},160642,{"status":182,"finish_reason":183},"21",95129,565,"87.85",{"id":336,"error":107,"extra":337,"score":147,"passed":119,"case_key":338,"cost_usd":107,"sample_idx":143,"input_tokens":339,"output_tokens":340,"has_trajectory":119,"duration_seconds":341},160646,{"status":182,"finish_reason":183},"22",95079,394,"43.77",{"id":343,"error":107,"extra":344,"score":148,"passed":4,"case_key":345,"cost_usd":107,"sample_idx":143,"input_tokens":346,"output_tokens":347,"has_trajectory":119,"duration_seconds":348},160650,{"status":182,"finish_reason":183},"23",95125,712,"95.92",{"id":350,"error":107,"extra":351,"score":147,"passed":119,"case_key":352,"cost_usd":107,"sample_idx":143,"input_tokens":353,"output_tokens":354,"has_trajectory":119,"duration_seconds":355},160654,{"status":182,"finish_reason":183},"24",95065,1793,"206.21",{"id":357,"error":107,"extra":358,"score":148,"passed":4,"case_key":359,"cost_usd":107,"sample_idx":143,"input_tokens":360,"output_tokens":361,"has_trajectory":119,"duration_seconds":362},160658,{"status":182,"finish_reason":183},"25",95108,8653,"986.20",{"id":364,"error":107,"extra":365,"score":147,"passed":119,"case_key":366,"cost_usd":107,"sample_idx":143,"input_tokens":367,"output_tokens":368,"has_trajectory":119,"duration_seconds":369},160662,{"status":182,"finish_reason":183},"26",93565,1234,"175.35",{"id":371,"error":107,"extra":372,"score":147,"passed":119,"case_key":373,"cost_usd":107,"sample_idx":143,"input_tokens":374,"output_tokens":375,"has_trajectory":119,"duration_seconds":376},160666,{"status":182,"finish_reason":183},"27",93586,1856,"238.57",{"id":378,"error":107,"extra":379,"score":147,"passed":119,"case_key":380,"cost_usd":107,"sample_idx":143,"input_tokens":381,"output_tokens":382,"has_trajectory":119,"duration_seconds":383},160670,{"status":182,"finish_reason":183},"28",93588,2354,"418.44",{"id":385,"error":107,"extra":386,"score":147,"passed":119,"case_key":387,"cost_usd":107,"sample_idx":143,"input_tokens":388,"output_tokens":389,"has_trajectory":119,"duration_seconds":390},160674,{"status":182,"finish_reason":183},"29",93642,1277,"230.31",{"id":392,"error":107,"extra":393,"score":147,"passed":119,"case_key":394,"cost_usd":107,"sample_idx":143,"input_tokens":395,"output_tokens":396,"has_trajectory":119,"duration_seconds":397},160678,{"status":182,"finish_reason":183},"30",73035,436,"73.75",{"id":399,"error":107,"extra":400,"score":147,"passed":119,"case_key":401,"cost_usd":107,"sample_idx":143,"input_tokens":402,"output_tokens":403,"has_trajectory":119,"duration_seconds":404},160682,{"status":182,"finish_reason":183},"31",73033,1155,"138.81",{"id":406,"error":107,"extra":407,"score":147,"passed":119,"case_key":408,"cost_usd":107,"sample_idx":143,"input_tokens":409,"output_tokens":410,"has_trajectory":119,"duration_seconds":411},160686,{"status":182,"finish_reason":183},"32",97357,377,"60.22",{"id":413,"error":107,"extra":414,"score":147,"passed":119,"case_key":415,"cost_usd":107,"sample_idx":143,"input_tokens":416,"output_tokens":417,"has_trajectory":119,"duration_seconds":418},160690,{"status":182,"finish_reason":183},"33",97358,698,"79.02",{"id":420,"error":107,"extra":421,"score":147,"passed":119,"case_key":422,"cost_usd":107,"sample_idx":143,"input_tokens":423,"output_tokens":424,"has_trajectory":119,"duration_seconds":425},160694,{"status":182,"finish_reason":183},"34",97371,389,"31.55",{"id":427,"error":107,"extra":428,"score":147,"passed":119,"case_key":429,"cost_usd":107,"sample_idx":143,"input_tokens":430,"output_tokens":228,"has_trajectory":119,"duration_seconds":431},160698,{"status":182,"finish_reason":183},"35",80260,"73.08",{"id":433,"error":107,"extra":434,"score":147,"passed":119,"case_key":435,"cost_usd":107,"sample_idx":143,"input_tokens":436,"output_tokens":437,"has_trajectory":119,"duration_seconds":438},160702,{"status":182,"finish_reason":183},"36",80239,469,"42.12",{"id":440,"error":107,"extra":441,"score":147,"passed":119,"case_key":442,"cost_usd":107,"sample_idx":143,"input_tokens":443,"output_tokens":444,"has_trajectory":119,"duration_seconds":445},160706,{"status":182,"finish_reason":183},"37",80256,936,"113.29",{"id":447,"error":107,"extra":448,"score":147,"passed":119,"case_key":449,"cost_usd":107,"sample_idx":143,"input_tokens":450,"output_tokens":451,"has_trajectory":119,"duration_seconds":452},160710,{"status":182,"finish_reason":183},"38",80246,415,"71.39",{"id":454,"error":107,"extra":455,"score":148,"passed":4,"case_key":456,"cost_usd":107,"sample_idx":143,"input_tokens":457,"output_tokens":458,"has_trajectory":119,"duration_seconds":459},160714,{"status":182,"finish_reason":183},"39",80255,306,"33.48",{"id":461,"error":107,"extra":462,"score":147,"passed":119,"case_key":463,"cost_usd":107,"sample_idx":143,"input_tokens":464,"output_tokens":465,"has_trajectory":119,"duration_seconds":466},160718,{"status":182,"finish_reason":183},"40",94339,150,"30.47",{"id":468,"error":107,"extra":469,"score":147,"passed":119,"case_key":470,"cost_usd":107,"sample_idx":143,"input_tokens":471,"output_tokens":472,"has_trajectory":119,"duration_seconds":473},160722,{"status":182,"finish_reason":183},"41",94365,530,"67.72",{"id":475,"error":107,"extra":476,"score":147,"passed":119,"case_key":477,"cost_usd":107,"sample_idx":143,"input_tokens":478,"output_tokens":479,"has_trajectory":119,"duration_seconds":480},160726,{"status":182,"finish_reason":183},"42",84718,2093,"306.58",{"id":482,"error":107,"extra":483,"score":147,"passed":119,"case_key":484,"cost_usd":107,"sample_idx":143,"input_tokens":485,"output_tokens":486,"has_trajectory":119,"duration_seconds":487},160730,{"status":182,"finish_reason":183},"43",84708,1079,"156.65",{"id":489,"error":107,"extra":490,"score":147,"passed":119,"case_key":491,"cost_usd":107,"sample_idx":143,"input_tokens":492,"output_tokens":493,"has_trajectory":119,"duration_seconds":494},160734,{"status":182,"finish_reason":183},"44",84704,461,"67.48",{"id":496,"error":107,"extra":497,"score":147,"passed":119,"case_key":498,"cost_usd":107,"sample_idx":143,"input_tokens":499,"output_tokens":500,"has_trajectory":119,"duration_seconds":501},160738,{"status":182,"finish_reason":183},"45",84768,711,"83.82",{"id":503,"error":107,"extra":504,"score":147,"passed":119,"case_key":505,"cost_usd":107,"sample_idx":143,"input_tokens":506,"output_tokens":507,"has_trajectory":119,"duration_seconds":508},160742,{"status":182,"finish_reason":183},"46",84712,1535,"177.44",{"id":510,"error":107,"extra":511,"score":147,"passed":119,"case_key":512,"cost_usd":107,"sample_idx":143,"input_tokens":513,"output_tokens":514,"has_trajectory":119,"duration_seconds":515},160746,{"status":182,"finish_reason":183},"47",84747,1855,"204.61",{"id":517,"error":107,"extra":518,"score":148,"passed":4,"case_key":519,"cost_usd":107,"sample_idx":143,"input_tokens":520,"output_tokens":521,"has_trajectory":119,"duration_seconds":522},160750,{"status":182,"finish_reason":183},"48",84714,2261,"279.85",{"id":524,"error":107,"extra":525,"score":147,"passed":119,"case_key":526,"cost_usd":107,"sample_idx":143,"input_tokens":506,"output_tokens":527,"has_trajectory":119,"duration_seconds":528},160754,{"status":182,"finish_reason":183},"49",1625,"183.03",{"total":118,"failed":154,"passed":155,"run_id":106,"ungraded":143,"sample_idx":143,"trajectories":118}]