[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"api:\u002Fnav:{}":3,"api:\u002Frecords\u002F13:{}":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":128,"benchmark":145,"rank":122,"ranked_count":72,"samples":160,"other_harnesses":164,"distribution":165,"cases":176},{"id":106,"notes":107,"score":108,"metrics":109,"cost_usd":107,"settings":112,"num_cases":120,"score_std":107,"harness_id":107,"has_bundle":121,"is_primary":121,"output_tps":107,"variant_id":122,"num_samples":54,"benchmark_id":72,"evaluated_at":123,"harness_name":107,"harness_slug":107,"input_tokens":124,"ttft_seconds":107,"output_tokens":125,"parent_run_id":107,"harness_version":107,"avg_case_seconds":126,"reasoning_tokens":107,"cost_per_case_usd":107,"trajectory_bundle_size_bytes":127},13,null,"0.1950",{"accuracy":110,"hallucination_rate":111},"0.5916666666666667","0.9714285714285714",{"top_p":113,"recipe":107,"harness":107,"judge_model":114,"num_samples":54,"temperature":115,"extra_settings":116,"scoring_method":107,"harness_version":107,"framework_version":118,"max_output_tokens":119},"1.000","Qwen3-30B-A3B-Instruct-2507","0.60",{"top_k":117},-1,"OPT 1478395",65536,600,true,3,"2026-10-26",123450,1061456,"98.54",979392,{"access":129,"effort":130,"family":131,"is_tier":121,"hardware":107,"model_id":72,"provider":107,"data_date":5,"precision":107,"categories":132,"is_primary":121,"model_name":20,"model_slug":21,"short_name":20,"variant_id":122,"effort_rank":140,"input_price":107,"vendor_name":16,"vendor_slug":17,"architecture":107,"output_price":107,"overall_rank":54,"ranked_count":72,"release_date":141,"variant_name":142,"variant_slug":143,"vendor_order":144,"weights_repo":107,"missing_count":122,"overall_score":22,"context_window":107,"total_cost_usd":107,"total_params_b":107,"weights_source":107,"active_params_b":107,"cache_hit_price":107,"cost_incomplete":121,"is_open_weights":121,"inference_engine":107},"self_hosted","max","DeepSeek-V4",[133,135,137,139],{"name":41,"rank":72,"slug":42,"score":134,"expected":43,"available":54,"ranked_count":72},"2.857142857142860000000000",{"name":45,"rank":54,"slug":46,"score":136,"expected":47,"available":72,"ranked_count":72},"69.724166666666667500000000",{"name":49,"rank":122,"slug":50,"score":138,"expected":43,"available":54,"ranked_count":72},"45.670000000000000000000000",{"name":52,"rank":43,"slug":53,"score":138,"expected":54,"available":54,"ranked_count":72},6,"2026-08-13","DeepSeek-V4-Pro 自部署 max","deepseek-v4-pro-self-hosted-max",0,{"id":72,"name":84,"slug":85,"license":146,"metrics":147,"version":107,"is_active":121,"num_cases":120,"parent_id":107,"score_max":151,"score_min":156,"created_at":157,"is_agentic":4,"sort_order":144,"updated_at":157,"description":107,"metric_name":158,"homepage_url":107,"license_note":107,"scoring_method":107,"composite_weight":151,"higher_is_better":121,"bundle_size_bytes":159},"public",[148,153],{"key":149,"name":150,"score":110,"score_max":151,"score_min":152,"higher_is_better":121},"accuracy","Accuracy","1.0000","0.0000",{"key":154,"name":155,"score":111,"score_max":151,"score_min":152,"higher_is_better":4},"hallucination_rate","Hallucination Rate","-1.0000","2026-10-28T09:47:38.906402+08:00","Omniscience Index",73171079,[161],{"total":120,"failed":162,"passed":163,"run_id":106,"ungraded":144,"sample_idx":144,"trajectories":120},245,355,[],[166,169,172,173],{"name":28,"rank":54,"score":167,"run_id":168,"model_slug":29,"vendor_slug":25},"0.3500",58,{"name":36,"rank":43,"score":170,"run_id":171,"model_slug":37,"vendor_slug":33},"0.2867",40,{"name":20,"rank":122,"score":108,"run_id":106,"model_slug":21,"vendor_slug":17},{"name":12,"rank":72,"score":174,"run_id":175,"model_slug":13,"vendor_slug":9},"-0.0367",113,{"restricted":4,"rows":177,"counts":512,"next_after":506},[178,187,194,201,208,215,222,229,236,243,249,256,263,270,276,283,289,295,302,309,315,322,329,336,343,350,357,363,370,376,382,388,394,401,408,415,422,428,434,441,448,454,460,466,472,479,486,492,498,505],{"id":179,"error":107,"extra":180,"score":151,"passed":121,"case_key":183,"cost_usd":107,"sample_idx":144,"input_tokens":184,"output_tokens":185,"has_trajectory":121,"duration_seconds":186},31823,{"status":181,"finish_reason":182},"completed","stop","0",201,1292,"83.49",{"id":188,"error":107,"extra":189,"score":151,"passed":121,"case_key":190,"cost_usd":107,"sample_idx":144,"input_tokens":191,"output_tokens":192,"has_trajectory":121,"duration_seconds":193},31824,{"status":181,"finish_reason":182},"1",206,447,"30.44",{"id":195,"error":107,"extra":196,"score":151,"passed":121,"case_key":197,"cost_usd":107,"sample_idx":144,"input_tokens":198,"output_tokens":199,"has_trajectory":121,"duration_seconds":200},31825,{"status":181,"finish_reason":182},"2",205,247,"12.39",{"id":202,"error":107,"extra":203,"score":151,"passed":121,"case_key":204,"cost_usd":107,"sample_idx":144,"input_tokens":205,"output_tokens":206,"has_trajectory":121,"duration_seconds":207},31826,{"status":181,"finish_reason":182},"3",197,2145,"106.86",{"id":209,"error":107,"extra":210,"score":156,"passed":4,"case_key":211,"cost_usd":107,"sample_idx":144,"input_tokens":212,"output_tokens":213,"has_trajectory":121,"duration_seconds":214},31827,{"status":181,"finish_reason":182},"4",225,1951,"111.86",{"id":216,"error":107,"extra":217,"score":151,"passed":121,"case_key":218,"cost_usd":107,"sample_idx":144,"input_tokens":219,"output_tokens":220,"has_trajectory":121,"duration_seconds":221},31828,{"status":181,"finish_reason":182},"5",208,1960,"112.25",{"id":223,"error":107,"extra":224,"score":151,"passed":121,"case_key":225,"cost_usd":107,"sample_idx":144,"input_tokens":226,"output_tokens":227,"has_trajectory":121,"duration_seconds":228},31829,{"status":181,"finish_reason":182},"6",221,364,"25.77",{"id":230,"error":107,"extra":231,"score":151,"passed":121,"case_key":232,"cost_usd":107,"sample_idx":144,"input_tokens":233,"output_tokens":234,"has_trajectory":121,"duration_seconds":235},31830,{"status":181,"finish_reason":182},"7",189,13834,"793.95",{"id":237,"error":107,"extra":238,"score":156,"passed":4,"case_key":239,"cost_usd":107,"sample_idx":144,"input_tokens":240,"output_tokens":241,"has_trajectory":121,"duration_seconds":242},31831,{"status":181,"finish_reason":182},"8",212,869,"51.34",{"id":244,"error":107,"extra":245,"score":151,"passed":121,"case_key":246,"cost_usd":107,"sample_idx":144,"input_tokens":191,"output_tokens":247,"has_trajectory":121,"duration_seconds":248},31832,{"status":181,"finish_reason":182},"9",5370,"340.95",{"id":250,"error":107,"extra":251,"score":156,"passed":4,"case_key":252,"cost_usd":107,"sample_idx":144,"input_tokens":253,"output_tokens":254,"has_trajectory":121,"duration_seconds":255},31833,{"status":181,"finish_reason":182},"10",199,1498,"96.18",{"id":257,"error":107,"extra":258,"score":151,"passed":121,"case_key":259,"cost_usd":107,"sample_idx":144,"input_tokens":260,"output_tokens":261,"has_trajectory":121,"duration_seconds":262},31834,{"status":181,"finish_reason":182},"11",219,432,"32.10",{"id":264,"error":107,"extra":265,"score":151,"passed":121,"case_key":266,"cost_usd":107,"sample_idx":144,"input_tokens":267,"output_tokens":268,"has_trajectory":121,"duration_seconds":269},31835,{"status":181,"finish_reason":182},"12",226,10714,"706.96",{"id":271,"error":107,"extra":272,"score":151,"passed":121,"case_key":273,"cost_usd":107,"sample_idx":144,"input_tokens":233,"output_tokens":274,"has_trajectory":121,"duration_seconds":275},31836,{"status":181,"finish_reason":182},"13",3267,"189.90",{"id":277,"error":107,"extra":278,"score":156,"passed":4,"case_key":279,"cost_usd":107,"sample_idx":144,"input_tokens":280,"output_tokens":281,"has_trajectory":121,"duration_seconds":282},31837,{"status":181,"finish_reason":182},"14",195,334,"20.53",{"id":284,"error":107,"extra":285,"score":156,"passed":4,"case_key":286,"cost_usd":107,"sample_idx":144,"input_tokens":205,"output_tokens":287,"has_trajectory":121,"duration_seconds":288},31838,{"status":181,"finish_reason":182},"15",1953,"136.38",{"id":290,"error":107,"extra":291,"score":151,"passed":121,"case_key":292,"cost_usd":107,"sample_idx":144,"input_tokens":191,"output_tokens":293,"has_trajectory":121,"duration_seconds":294},31839,{"status":181,"finish_reason":182},"16",635,"45.25",{"id":296,"error":107,"extra":297,"score":151,"passed":121,"case_key":298,"cost_usd":107,"sample_idx":144,"input_tokens":299,"output_tokens":300,"has_trajectory":121,"duration_seconds":301},31840,{"status":181,"finish_reason":182},"17",203,321,"20.07",{"id":303,"error":107,"extra":304,"score":151,"passed":121,"case_key":305,"cost_usd":107,"sample_idx":144,"input_tokens":306,"output_tokens":307,"has_trajectory":121,"duration_seconds":308},31841,{"status":181,"finish_reason":182},"18",210,904,"62.60",{"id":310,"error":107,"extra":311,"score":151,"passed":121,"case_key":312,"cost_usd":107,"sample_idx":144,"input_tokens":219,"output_tokens":313,"has_trajectory":121,"duration_seconds":314},31842,{"status":181,"finish_reason":182},"19",1467,"82.19",{"id":316,"error":107,"extra":317,"score":156,"passed":4,"case_key":318,"cost_usd":107,"sample_idx":144,"input_tokens":319,"output_tokens":320,"has_trajectory":121,"duration_seconds":321},31843,{"status":181,"finish_reason":182},"20",187,1058,"65.29",{"id":323,"error":107,"extra":324,"score":151,"passed":121,"case_key":325,"cost_usd":107,"sample_idx":144,"input_tokens":326,"output_tokens":327,"has_trajectory":121,"duration_seconds":328},31844,{"status":181,"finish_reason":182},"21",209,289,"20.88",{"id":330,"error":107,"extra":331,"score":151,"passed":121,"case_key":332,"cost_usd":107,"sample_idx":144,"input_tokens":333,"output_tokens":334,"has_trajectory":121,"duration_seconds":335},31845,{"status":181,"finish_reason":182},"22",190,342,"20.82",{"id":337,"error":107,"extra":338,"score":156,"passed":4,"case_key":339,"cost_usd":107,"sample_idx":144,"input_tokens":340,"output_tokens":341,"has_trajectory":121,"duration_seconds":342},31846,{"status":181,"finish_reason":182},"23",184,171,"13.04",{"id":344,"error":107,"extra":345,"score":156,"passed":4,"case_key":346,"cost_usd":107,"sample_idx":144,"input_tokens":347,"output_tokens":348,"has_trajectory":121,"duration_seconds":349},31847,{"status":181,"finish_reason":182},"24",193,839,"61.17",{"id":351,"error":107,"extra":352,"score":156,"passed":4,"case_key":353,"cost_usd":107,"sample_idx":144,"input_tokens":354,"output_tokens":355,"has_trajectory":121,"duration_seconds":356},31848,{"status":181,"finish_reason":182},"25",196,589,"30.20",{"id":358,"error":107,"extra":359,"score":151,"passed":121,"case_key":360,"cost_usd":107,"sample_idx":144,"input_tokens":233,"output_tokens":361,"has_trajectory":121,"duration_seconds":362},31849,{"status":181,"finish_reason":182},"26",146,"10.78",{"id":364,"error":107,"extra":365,"score":151,"passed":121,"case_key":366,"cost_usd":107,"sample_idx":144,"input_tokens":367,"output_tokens":368,"has_trajectory":121,"duration_seconds":369},31850,{"status":181,"finish_reason":182},"27",194,493,"30.13",{"id":371,"error":107,"extra":372,"score":151,"passed":121,"case_key":373,"cost_usd":107,"sample_idx":144,"input_tokens":191,"output_tokens":374,"has_trajectory":121,"duration_seconds":375},31851,{"status":181,"finish_reason":182},"28",215,"16.45",{"id":377,"error":107,"extra":378,"score":156,"passed":4,"case_key":379,"cost_usd":107,"sample_idx":144,"input_tokens":219,"output_tokens":380,"has_trajectory":121,"duration_seconds":381},31852,{"status":181,"finish_reason":182},"29",1099,"72.94",{"id":383,"error":107,"extra":384,"score":151,"passed":121,"case_key":385,"cost_usd":107,"sample_idx":144,"input_tokens":184,"output_tokens":386,"has_trajectory":121,"duration_seconds":387},31853,{"status":181,"finish_reason":182},"30",96,"7.08",{"id":389,"error":107,"extra":390,"score":156,"passed":4,"case_key":391,"cost_usd":107,"sample_idx":144,"input_tokens":260,"output_tokens":392,"has_trajectory":121,"duration_seconds":393},31854,{"status":181,"finish_reason":182},"31",5271,"321.46",{"id":395,"error":107,"extra":396,"score":156,"passed":4,"case_key":397,"cost_usd":107,"sample_idx":144,"input_tokens":398,"output_tokens":399,"has_trajectory":121,"duration_seconds":400},31855,{"status":181,"finish_reason":182},"32",186,407,"29.68",{"id":402,"error":107,"extra":403,"score":151,"passed":121,"case_key":404,"cost_usd":107,"sample_idx":144,"input_tokens":405,"output_tokens":406,"has_trajectory":121,"duration_seconds":407},31856,{"status":181,"finish_reason":182},"33",207,790,"55.66",{"id":409,"error":107,"extra":410,"score":156,"passed":4,"case_key":411,"cost_usd":107,"sample_idx":144,"input_tokens":412,"output_tokens":413,"has_trajectory":121,"duration_seconds":414},31857,{"status":181,"finish_reason":182},"34",200,522,"39.22",{"id":416,"error":107,"extra":417,"score":156,"passed":4,"case_key":418,"cost_usd":107,"sample_idx":144,"input_tokens":419,"output_tokens":420,"has_trajectory":121,"duration_seconds":421},31858,{"status":181,"finish_reason":182},"35",211,718,"55.18",{"id":423,"error":107,"extra":424,"score":151,"passed":121,"case_key":425,"cost_usd":107,"sample_idx":144,"input_tokens":253,"output_tokens":426,"has_trajectory":121,"duration_seconds":427},31859,{"status":181,"finish_reason":182},"36",313,"13.71",{"id":429,"error":107,"extra":430,"score":151,"passed":121,"case_key":431,"cost_usd":107,"sample_idx":144,"input_tokens":419,"output_tokens":432,"has_trajectory":121,"duration_seconds":433},31860,{"status":181,"finish_reason":182},"37",476,"26.19",{"id":435,"error":107,"extra":436,"score":151,"passed":121,"case_key":437,"cost_usd":107,"sample_idx":144,"input_tokens":438,"output_tokens":439,"has_trajectory":121,"duration_seconds":440},31861,{"status":181,"finish_reason":182},"38",217,922,"66.44",{"id":442,"error":107,"extra":443,"score":151,"passed":121,"case_key":444,"cost_usd":107,"sample_idx":144,"input_tokens":445,"output_tokens":446,"has_trajectory":121,"duration_seconds":447},31862,{"status":181,"finish_reason":182},"39",237,512,"37.96",{"id":449,"error":107,"extra":450,"score":156,"passed":4,"case_key":451,"cost_usd":107,"sample_idx":144,"input_tokens":240,"output_tokens":452,"has_trajectory":121,"duration_seconds":453},31863,{"status":181,"finish_reason":182},"40",13727,"684.00",{"id":455,"error":107,"extra":456,"score":156,"passed":4,"case_key":457,"cost_usd":107,"sample_idx":144,"input_tokens":367,"output_tokens":458,"has_trajectory":121,"duration_seconds":459},31864,{"status":181,"finish_reason":182},"41",2319,"142.51",{"id":461,"error":107,"extra":462,"score":151,"passed":121,"case_key":463,"cost_usd":107,"sample_idx":144,"input_tokens":405,"output_tokens":464,"has_trajectory":121,"duration_seconds":465},31865,{"status":181,"finish_reason":182},"42",653,"32.12",{"id":467,"error":107,"extra":468,"score":151,"passed":121,"case_key":469,"cost_usd":107,"sample_idx":144,"input_tokens":438,"output_tokens":470,"has_trajectory":121,"duration_seconds":471},31866,{"status":181,"finish_reason":182},"43",353,"26.23",{"id":473,"error":107,"extra":474,"score":151,"passed":121,"case_key":475,"cost_usd":107,"sample_idx":144,"input_tokens":476,"output_tokens":477,"has_trajectory":121,"duration_seconds":478},31867,{"status":181,"finish_reason":182},"44",218,1364,"73.33",{"id":480,"error":107,"extra":481,"score":151,"passed":121,"case_key":482,"cost_usd":107,"sample_idx":144,"input_tokens":483,"output_tokens":484,"has_trajectory":121,"duration_seconds":485},31868,{"status":181,"finish_reason":182},"45",234,1059,"64.01",{"id":487,"error":107,"extra":488,"score":156,"passed":4,"case_key":489,"cost_usd":107,"sample_idx":144,"input_tokens":405,"output_tokens":490,"has_trajectory":121,"duration_seconds":491},31869,{"status":181,"finish_reason":182},"46",490,"36.22",{"id":493,"error":107,"extra":494,"score":151,"passed":121,"case_key":495,"cost_usd":107,"sample_idx":144,"input_tokens":240,"output_tokens":496,"has_trajectory":121,"duration_seconds":497},31870,{"status":181,"finish_reason":182},"47",285,"18.57",{"id":499,"error":107,"extra":500,"score":151,"passed":121,"case_key":501,"cost_usd":107,"sample_idx":144,"input_tokens":502,"output_tokens":503,"has_trajectory":121,"duration_seconds":504},31871,{"status":181,"finish_reason":182},"48",282,1735,"103.79",{"id":506,"error":107,"extra":507,"score":151,"passed":121,"case_key":508,"cost_usd":107,"sample_idx":144,"input_tokens":509,"output_tokens":510,"has_trajectory":121,"duration_seconds":511},31872,{"status":181,"finish_reason":182},"49",292,1826,"108.07",{"total":120,"failed":162,"passed":163,"run_id":106,"ungraded":144,"sample_idx":144,"trajectories":120}]