[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"api:\u002Fnav:{}":3,"api:\u002Frecords\u002F59:{}":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":142,"rank":72,"ranked_count":72,"samples":150,"other_harnesses":154,"distribution":155,"cases":166},{"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":119,"num_samples":54,"benchmark_id":43,"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},59,null,"0.0350",{},{"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},"0.950","1.00",{"top_k":114},-1,"OPT 1478395",32768,600,true,11,"2026-10-24",1389600376,15364108,"4843.73",26581258,{"access":126,"effort":127,"family":28,"is_tier":118,"hardware":107,"model_id":128,"provider":107,"data_date":120,"precision":107,"categories":129,"is_primary":118,"model_name":28,"model_slug":29,"short_name":28,"variant_id":119,"effort_rank":137,"input_price":107,"vendor_name":24,"vendor_slug":25,"architecture":107,"output_price":107,"overall_rank":128,"ranked_count":72,"release_date":138,"variant_name":139,"variant_slug":140,"vendor_order":141,"weights_repo":107,"missing_count":128,"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":118,"is_open_weights":118,"inference_engine":107},"api","max",3,[130,132,134,136],{"name":41,"rank":43,"slug":42,"score":131,"expected":43,"available":54,"ranked_count":72},"65.051903114186850000000000",{"name":45,"rank":43,"slug":46,"score":133,"expected":47,"available":72,"ranked_count":72},"67.050833333333332500000000",{"name":49,"rank":72,"slug":50,"score":135,"expected":43,"available":54,"ranked_count":72},"3.500000000000000000000000",{"name":52,"rank":72,"slug":53,"score":135,"expected":54,"available":54,"ranked_count":72},6,"2026-07-16","Kimi-K3 官方 API max","kimi-k3-api-max",0,{"id":43,"name":87,"slug":88,"license":143,"metrics":144,"version":107,"is_active":118,"num_cases":117,"parent_id":107,"score_max":145,"score_min":146,"created_at":147,"is_agentic":118,"sort_order":141,"updated_at":147,"description":107,"metric_name":148,"homepage_url":107,"license_note":107,"scoring_method":107,"composite_weight":145,"higher_is_better":118,"bundle_size_bytes":149},"public",[],"1.0000","0.0000","2026-10-28T09:47:38.906402+08:00","Pass Rate",2028958067,[151],{"total":117,"failed":152,"passed":153,"run_id":106,"ungraded":141,"sample_idx":141,"trajectories":117},579,21,[],[156,159,162,165],{"name":36,"rank":54,"score":157,"run_id":158,"model_slug":37,"vendor_slug":33},"0.5250",41,{"name":20,"rank":43,"score":160,"run_id":161,"model_slug":21,"vendor_slug":17},"0.4567",14,{"name":12,"rank":128,"score":163,"run_id":164,"model_slug":13,"vendor_slug":9},"0.4150",114,{"name":28,"rank":72,"score":108,"run_id":106,"model_slug":29,"vendor_slug":25},{"restricted":4,"rows":167,"counts":525,"next_after":519},[168,177,186,193,200,207,214,221,228,235,242,249,256,263,271,278,285,292,299,306,313,320,327,334,341,348,355,362,369,376,384,391,398,405,413,420,427,434,441,448,455,462,469,476,483,490,497,504,511,518],{"id":169,"error":107,"extra":170,"score":146,"passed":4,"case_key":173,"cost_usd":107,"sample_idx":141,"input_tokens":174,"output_tokens":175,"has_trajectory":118,"duration_seconds":176},161558,{"status":171,"finish_reason":172},"truncated","tool_calls","0",3415368,20285,"8888.94",{"id":178,"error":107,"extra":179,"score":146,"passed":4,"case_key":182,"cost_usd":107,"sample_idx":141,"input_tokens":183,"output_tokens":184,"has_trajectory":118,"duration_seconds":185},161559,{"status":180,"finish_reason":181},"completed","stop","1",3976367,29321,"7453.27",{"id":187,"error":107,"extra":188,"score":146,"passed":4,"case_key":189,"cost_usd":107,"sample_idx":141,"input_tokens":190,"output_tokens":191,"has_trajectory":118,"duration_seconds":192},161560,{"status":180,"finish_reason":181},"2",1492735,21724,"5742.98",{"id":194,"error":107,"extra":195,"score":146,"passed":4,"case_key":196,"cost_usd":107,"sample_idx":141,"input_tokens":197,"output_tokens":198,"has_trajectory":118,"duration_seconds":199},161561,{"status":171,"finish_reason":172},"3",4427030,17012,"5928.93",{"id":201,"error":107,"extra":202,"score":146,"passed":4,"case_key":203,"cost_usd":107,"sample_idx":141,"input_tokens":204,"output_tokens":205,"has_trajectory":118,"duration_seconds":206},161562,{"status":171,"finish_reason":172},"4",2941214,19694,"6598.78",{"id":208,"error":107,"extra":209,"score":146,"passed":4,"case_key":210,"cost_usd":107,"sample_idx":141,"input_tokens":211,"output_tokens":212,"has_trajectory":118,"duration_seconds":213},161563,{"status":180,"finish_reason":181},"5",3036974,25373,"6524.05",{"id":215,"error":107,"extra":216,"score":146,"passed":4,"case_key":217,"cost_usd":107,"sample_idx":141,"input_tokens":218,"output_tokens":219,"has_trajectory":118,"duration_seconds":220},161564,{"status":180,"finish_reason":181},"6",1430128,24375,"5317.76",{"id":222,"error":107,"extra":223,"score":146,"passed":4,"case_key":224,"cost_usd":107,"sample_idx":141,"input_tokens":225,"output_tokens":226,"has_trajectory":118,"duration_seconds":227},161565,{"status":180,"finish_reason":181},"7",853077,15137,"3370.62",{"id":229,"error":107,"extra":230,"score":146,"passed":4,"case_key":231,"cost_usd":107,"sample_idx":141,"input_tokens":232,"output_tokens":233,"has_trajectory":118,"duration_seconds":234},161566,{"status":180,"finish_reason":181},"8",838377,10607,"2553.60",{"id":236,"error":107,"extra":237,"score":146,"passed":4,"case_key":238,"cost_usd":107,"sample_idx":141,"input_tokens":239,"output_tokens":240,"has_trajectory":118,"duration_seconds":241},161567,{"status":180,"finish_reason":181},"9",3660497,31683,"5380.32",{"id":243,"error":107,"extra":244,"score":146,"passed":4,"case_key":245,"cost_usd":107,"sample_idx":141,"input_tokens":246,"output_tokens":247,"has_trajectory":118,"duration_seconds":248},161568,{"status":180,"finish_reason":181},"10",2741767,22687,"6748.33",{"id":250,"error":107,"extra":251,"score":146,"passed":4,"case_key":252,"cost_usd":107,"sample_idx":141,"input_tokens":253,"output_tokens":254,"has_trajectory":118,"duration_seconds":255},161569,{"status":171,"finish_reason":172},"11",2800943,21326,"5985.00",{"id":257,"error":107,"extra":258,"score":146,"passed":4,"case_key":259,"cost_usd":107,"sample_idx":141,"input_tokens":260,"output_tokens":261,"has_trajectory":118,"duration_seconds":262},161570,{"status":180,"finish_reason":181},"12",2258018,32495,"8477.79",{"id":264,"error":107,"extra":265,"score":266,"passed":4,"case_key":267,"cost_usd":107,"sample_idx":141,"input_tokens":268,"output_tokens":269,"has_trajectory":118,"duration_seconds":270},161571,{"status":180,"finish_reason":181},"0.5000","13",104111,2815,"377.48",{"id":272,"error":107,"extra":273,"score":146,"passed":4,"case_key":274,"cost_usd":107,"sample_idx":141,"input_tokens":275,"output_tokens":276,"has_trajectory":118,"duration_seconds":277},161572,{"status":180,"finish_reason":181},"14",1642357,22510,"3876.53",{"id":279,"error":107,"extra":280,"score":146,"passed":4,"case_key":281,"cost_usd":107,"sample_idx":141,"input_tokens":282,"output_tokens":283,"has_trajectory":118,"duration_seconds":284},161573,{"status":171,"finish_reason":172},"15",9013986,47090,"11081.58",{"id":286,"error":107,"extra":287,"score":146,"passed":4,"case_key":288,"cost_usd":107,"sample_idx":141,"input_tokens":289,"output_tokens":290,"has_trajectory":118,"duration_seconds":291},161574,{"status":180,"finish_reason":181},"16",4053152,38539,"9546.32",{"id":293,"error":107,"extra":294,"score":146,"passed":4,"case_key":295,"cost_usd":107,"sample_idx":141,"input_tokens":296,"output_tokens":297,"has_trajectory":118,"duration_seconds":298},161575,{"status":180,"finish_reason":181},"17",4230401,47034,"10601.83",{"id":300,"error":107,"extra":301,"score":146,"passed":4,"case_key":302,"cost_usd":107,"sample_idx":141,"input_tokens":303,"output_tokens":304,"has_trajectory":118,"duration_seconds":305},161576,{"status":180,"finish_reason":181},"18",1399320,22239,"5064.01",{"id":307,"error":107,"extra":308,"score":146,"passed":4,"case_key":309,"cost_usd":107,"sample_idx":141,"input_tokens":310,"output_tokens":311,"has_trajectory":118,"duration_seconds":312},161577,{"status":180,"finish_reason":181},"19",3133958,41248,"7772.42",{"id":314,"error":107,"extra":315,"score":146,"passed":4,"case_key":316,"cost_usd":107,"sample_idx":141,"input_tokens":317,"output_tokens":318,"has_trajectory":118,"duration_seconds":319},161578,{"status":171,"finish_reason":172},"20",2893421,21390,"8122.78",{"id":321,"error":107,"extra":322,"score":146,"passed":4,"case_key":323,"cost_usd":107,"sample_idx":141,"input_tokens":324,"output_tokens":325,"has_trajectory":118,"duration_seconds":326},161579,{"status":180,"finish_reason":181},"21",3869585,38476,"9840.21",{"id":328,"error":107,"extra":329,"score":146,"passed":4,"case_key":330,"cost_usd":107,"sample_idx":141,"input_tokens":331,"output_tokens":332,"has_trajectory":118,"duration_seconds":333},161580,{"status":180,"finish_reason":181},"22",2842616,36603,"9541.23",{"id":335,"error":107,"extra":336,"score":146,"passed":4,"case_key":337,"cost_usd":107,"sample_idx":141,"input_tokens":338,"output_tokens":339,"has_trajectory":118,"duration_seconds":340},161581,{"status":171,"finish_reason":172},"23",2643446,22283,"8221.13",{"id":342,"error":107,"extra":343,"score":146,"passed":4,"case_key":344,"cost_usd":107,"sample_idx":141,"input_tokens":345,"output_tokens":346,"has_trajectory":118,"duration_seconds":347},161582,{"status":171,"finish_reason":172},"24",3043106,21854,"7909.97",{"id":349,"error":107,"extra":350,"score":146,"passed":4,"case_key":351,"cost_usd":107,"sample_idx":141,"input_tokens":352,"output_tokens":353,"has_trajectory":118,"duration_seconds":354},161583,{"status":180,"finish_reason":181},"25",2778784,28787,"5461.97",{"id":356,"error":107,"extra":357,"score":146,"passed":4,"case_key":358,"cost_usd":107,"sample_idx":141,"input_tokens":359,"output_tokens":360,"has_trajectory":118,"duration_seconds":361},161584,{"status":171,"finish_reason":172},"26",4902813,20760,"8275.20",{"id":363,"error":107,"extra":364,"score":146,"passed":4,"case_key":365,"cost_usd":107,"sample_idx":141,"input_tokens":366,"output_tokens":367,"has_trajectory":118,"duration_seconds":368},161585,{"status":180,"finish_reason":181},"27",1586753,24743,"5148.05",{"id":370,"error":107,"extra":371,"score":146,"passed":4,"case_key":372,"cost_usd":107,"sample_idx":141,"input_tokens":373,"output_tokens":374,"has_trajectory":118,"duration_seconds":375},161586,{"status":180,"finish_reason":181},"28",2577869,25552,"6781.57",{"id":377,"error":107,"extra":378,"score":379,"passed":4,"case_key":380,"cost_usd":107,"sample_idx":141,"input_tokens":381,"output_tokens":382,"has_trajectory":118,"duration_seconds":383},161587,{"status":180,"finish_reason":181},"0.1000","29",3967837,37027,"9794.57",{"id":385,"error":107,"extra":386,"score":146,"passed":4,"case_key":387,"cost_usd":107,"sample_idx":141,"input_tokens":388,"output_tokens":389,"has_trajectory":118,"duration_seconds":390},161588,{"status":180,"finish_reason":181},"30",2486496,21619,"5964.28",{"id":392,"error":107,"extra":393,"score":146,"passed":4,"case_key":394,"cost_usd":107,"sample_idx":141,"input_tokens":395,"output_tokens":396,"has_trajectory":118,"duration_seconds":397},161589,{"status":180,"finish_reason":181},"31",4692939,37073,"9073.52",{"id":399,"error":107,"extra":400,"score":146,"passed":4,"case_key":401,"cost_usd":107,"sample_idx":141,"input_tokens":402,"output_tokens":403,"has_trajectory":118,"duration_seconds":404},161590,{"status":180,"finish_reason":181},"32",1572559,23346,"5949.24",{"id":406,"error":107,"extra":407,"score":408,"passed":4,"case_key":409,"cost_usd":107,"sample_idx":141,"input_tokens":410,"output_tokens":411,"has_trajectory":118,"duration_seconds":412},161591,{"status":180,"finish_reason":181},"0.1667","33",4036528,35332,"8595.01",{"id":414,"error":107,"extra":415,"score":146,"passed":4,"case_key":416,"cost_usd":107,"sample_idx":141,"input_tokens":417,"output_tokens":418,"has_trajectory":118,"duration_seconds":419},161592,{"status":180,"finish_reason":181},"34",2381865,17814,"4798.56",{"id":421,"error":107,"extra":422,"score":146,"passed":4,"case_key":423,"cost_usd":107,"sample_idx":141,"input_tokens":424,"output_tokens":425,"has_trajectory":118,"duration_seconds":426},161593,{"status":180,"finish_reason":181},"35",2651799,23643,"5043.89",{"id":428,"error":107,"extra":429,"score":146,"passed":4,"case_key":430,"cost_usd":107,"sample_idx":141,"input_tokens":431,"output_tokens":432,"has_trajectory":118,"duration_seconds":433},161594,{"status":171,"finish_reason":172},"36",4236169,18886,"6537.57",{"id":435,"error":107,"extra":436,"score":146,"passed":4,"case_key":437,"cost_usd":107,"sample_idx":141,"input_tokens":438,"output_tokens":439,"has_trajectory":118,"duration_seconds":440},161595,{"status":171,"finish_reason":172},"37",3851428,18980,"6457.92",{"id":442,"error":107,"extra":443,"score":146,"passed":4,"case_key":444,"cost_usd":107,"sample_idx":141,"input_tokens":445,"output_tokens":446,"has_trajectory":118,"duration_seconds":447},161596,{"status":180,"finish_reason":181},"38",3423650,29977,"6642.43",{"id":449,"error":107,"extra":450,"score":146,"passed":4,"case_key":451,"cost_usd":107,"sample_idx":141,"input_tokens":452,"output_tokens":453,"has_trajectory":118,"duration_seconds":454},161597,{"status":180,"finish_reason":181},"39",3096211,21423,"5252.26",{"id":456,"error":107,"extra":457,"score":146,"passed":4,"case_key":458,"cost_usd":107,"sample_idx":141,"input_tokens":459,"output_tokens":460,"has_trajectory":118,"duration_seconds":461},161598,{"status":180,"finish_reason":181},"40",2539529,23886,"6045.83",{"id":463,"error":107,"extra":464,"score":146,"passed":4,"case_key":465,"cost_usd":107,"sample_idx":141,"input_tokens":466,"output_tokens":467,"has_trajectory":118,"duration_seconds":468},161599,{"status":180,"finish_reason":181},"41",1773506,18410,"5962.74",{"id":470,"error":107,"extra":471,"score":146,"passed":4,"case_key":472,"cost_usd":107,"sample_idx":141,"input_tokens":473,"output_tokens":474,"has_trajectory":118,"duration_seconds":475},161600,{"status":171,"finish_reason":172},"42",2268112,15692,"6096.45",{"id":477,"error":107,"extra":478,"score":146,"passed":4,"case_key":479,"cost_usd":107,"sample_idx":141,"input_tokens":480,"output_tokens":481,"has_trajectory":118,"duration_seconds":482},161601,{"status":180,"finish_reason":181},"43",3859779,42615,"11080.01",{"id":484,"error":107,"extra":485,"score":146,"passed":4,"case_key":486,"cost_usd":107,"sample_idx":141,"input_tokens":487,"output_tokens":488,"has_trajectory":118,"duration_seconds":489},161602,{"status":171,"finish_reason":172},"44",3123330,24646,"8180.38",{"id":491,"error":107,"extra":492,"score":146,"passed":4,"case_key":493,"cost_usd":107,"sample_idx":141,"input_tokens":494,"output_tokens":495,"has_trajectory":118,"duration_seconds":496},161603,{"status":180,"finish_reason":181},"45",2062469,20303,"4767.78",{"id":498,"error":107,"extra":499,"score":146,"passed":4,"case_key":500,"cost_usd":107,"sample_idx":141,"input_tokens":501,"output_tokens":502,"has_trajectory":118,"duration_seconds":503},161604,{"status":180,"finish_reason":181},"46",2546751,20336,"5752.82",{"id":505,"error":107,"extra":506,"score":146,"passed":4,"case_key":507,"cost_usd":107,"sample_idx":141,"input_tokens":508,"output_tokens":509,"has_trajectory":118,"duration_seconds":510},161605,{"status":180,"finish_reason":181},"47",2473001,21672,"5044.73",{"id":512,"error":107,"extra":513,"score":146,"passed":4,"case_key":514,"cost_usd":107,"sample_idx":141,"input_tokens":515,"output_tokens":516,"has_trajectory":118,"duration_seconds":517},161606,{"status":180,"finish_reason":181},"48",3089395,27109,"6248.82",{"id":519,"error":107,"extra":520,"score":146,"passed":4,"case_key":521,"cost_usd":107,"sample_idx":141,"input_tokens":522,"output_tokens":523,"has_trajectory":118,"duration_seconds":524},161607,{"status":171,"finish_reason":172},"49",2620050,17860,"7599.09",{"total":117,"failed":152,"passed":153,"run_id":106,"ungraded":141,"sample_idx":141,"trajectories":117}]