[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"api:\u002Fnav:{}":3,"api:\u002Frecords\u002F15:{}":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":43,"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":120,"evaluated_at":5,"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},15,null,"0.8713",{},{"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",65536,12032,true,3,7,3552394,47930546,"138.95",45236996,{"access":126,"effort":127,"family":128,"is_tier":118,"hardware":107,"model_id":72,"provider":107,"data_date":5,"precision":107,"categories":129,"is_primary":118,"model_name":20,"model_slug":21,"short_name":20,"variant_id":119,"effort_rank":137,"input_price":107,"vendor_name":16,"vendor_slug":17,"architecture":107,"output_price":107,"overall_rank":54,"ranked_count":72,"release_date":138,"variant_name":139,"variant_slug":140,"vendor_order":141,"weights_repo":107,"missing_count":119,"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":118,"is_open_weights":118,"inference_engine":107},"self_hosted","max","DeepSeek-V4",[130,132,134,136],{"name":41,"rank":72,"slug":42,"score":131,"expected":43,"available":54,"ranked_count":72},"2.857142857142860000000000",{"name":45,"rank":54,"slug":46,"score":133,"expected":47,"available":72,"ranked_count":72},"69.724166666666667500000000",{"name":49,"rank":119,"slug":50,"score":135,"expected":43,"available":54,"ranked_count":72},"45.670000000000000000000000",{"name":52,"rank":43,"slug":53,"score":135,"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":120,"name":96,"slug":97,"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":4,"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","Accuracy",1829320613,[151],{"total":117,"failed":152,"passed":153,"run_id":106,"ungraded":141,"sample_idx":141,"trajectories":117},1548,10484,[],[156,159,160,163],{"name":28,"rank":54,"score":157,"run_id":158,"model_slug":29,"vendor_slug":25},"0.8877",60,{"name":20,"rank":43,"score":108,"run_id":106,"model_slug":21,"vendor_slug":17},{"name":12,"rank":119,"score":161,"run_id":162,"model_slug":13,"vendor_slug":9},"0.8516",117,{"name":36,"rank":72,"score":164,"run_id":165,"model_slug":37,"vendor_slug":33},"0.8507",42,{"restricted":4,"rows":167,"counts":510,"next_after":505},[168,177,184,191,198,205,212,219,226,233,240,246,253,260,267,274,281,288,295,302,309,316,323,330,337,344,351,358,364,371,378,385,391,398,405,412,418,424,431,438,445,452,457,464,469,476,483,490,497,504],{"id":169,"error":107,"extra":170,"score":145,"passed":118,"case_key":173,"cost_usd":107,"sample_idx":141,"input_tokens":174,"output_tokens":175,"has_trajectory":118,"duration_seconds":176},33023,{"status":171,"finish_reason":172},"completed","stop","0",273,367,"22.47",{"id":178,"error":107,"extra":179,"score":145,"passed":118,"case_key":180,"cost_usd":107,"sample_idx":141,"input_tokens":181,"output_tokens":182,"has_trajectory":118,"duration_seconds":183},33024,{"status":171,"finish_reason":172},"1",282,1222,"88.26",{"id":185,"error":107,"extra":186,"score":145,"passed":118,"case_key":187,"cost_usd":107,"sample_idx":141,"input_tokens":188,"output_tokens":189,"has_trajectory":118,"duration_seconds":190},33025,{"status":171,"finish_reason":172},"2",294,10313,"634.12",{"id":192,"error":107,"extra":193,"score":145,"passed":118,"case_key":194,"cost_usd":107,"sample_idx":141,"input_tokens":195,"output_tokens":196,"has_trajectory":118,"duration_seconds":197},33026,{"status":171,"finish_reason":172},"3",200,980,"68.44",{"id":199,"error":107,"extra":200,"score":145,"passed":118,"case_key":201,"cost_usd":107,"sample_idx":141,"input_tokens":202,"output_tokens":203,"has_trajectory":118,"duration_seconds":204},33027,{"status":171,"finish_reason":172},"4",296,220,"16.70",{"id":206,"error":107,"extra":207,"score":145,"passed":118,"case_key":208,"cost_usd":107,"sample_idx":141,"input_tokens":209,"output_tokens":210,"has_trajectory":118,"duration_seconds":211},33028,{"status":171,"finish_reason":172},"5",249,850,"61.65",{"id":213,"error":107,"extra":214,"score":145,"passed":118,"case_key":215,"cost_usd":107,"sample_idx":141,"input_tokens":216,"output_tokens":217,"has_trajectory":118,"duration_seconds":218},33029,{"status":171,"finish_reason":172},"6",224,140,"7.01",{"id":220,"error":107,"extra":221,"score":145,"passed":118,"case_key":222,"cost_usd":107,"sample_idx":141,"input_tokens":223,"output_tokens":224,"has_trajectory":118,"duration_seconds":225},33030,{"status":171,"finish_reason":172},"7",184,120,"6.07",{"id":227,"error":107,"extra":228,"score":145,"passed":118,"case_key":229,"cost_usd":107,"sample_idx":141,"input_tokens":230,"output_tokens":231,"has_trajectory":118,"duration_seconds":232},33031,{"status":171,"finish_reason":172},"8",197,70,"4.89",{"id":234,"error":107,"extra":235,"score":145,"passed":118,"case_key":236,"cost_usd":107,"sample_idx":141,"input_tokens":237,"output_tokens":238,"has_trajectory":118,"duration_seconds":239},33032,{"status":171,"finish_reason":172},"9",217,416,"24.72",{"id":241,"error":107,"extra":242,"score":145,"passed":118,"case_key":243,"cost_usd":107,"sample_idx":141,"input_tokens":244,"output_tokens":224,"has_trajectory":118,"duration_seconds":245},33033,{"status":171,"finish_reason":172},"10",202,"9.55",{"id":247,"error":107,"extra":248,"score":146,"passed":4,"case_key":249,"cost_usd":107,"sample_idx":141,"input_tokens":250,"output_tokens":251,"has_trajectory":118,"duration_seconds":252},33034,{"status":171,"finish_reason":172},"11",191,3839,"226.65",{"id":254,"error":107,"extra":255,"score":145,"passed":118,"case_key":256,"cost_usd":107,"sample_idx":141,"input_tokens":257,"output_tokens":258,"has_trajectory":118,"duration_seconds":259},33035,{"status":171,"finish_reason":172},"12",195,110,"10.83",{"id":261,"error":107,"extra":262,"score":146,"passed":4,"case_key":263,"cost_usd":107,"sample_idx":141,"input_tokens":264,"output_tokens":265,"has_trajectory":118,"duration_seconds":266},33036,{"status":171,"finish_reason":172},"13",190,798,"39.76",{"id":268,"error":107,"extra":269,"score":145,"passed":118,"case_key":270,"cost_usd":107,"sample_idx":141,"input_tokens":271,"output_tokens":272,"has_trajectory":118,"duration_seconds":273},33037,{"status":171,"finish_reason":172},"14",193,1192,"86.56",{"id":275,"error":107,"extra":276,"score":145,"passed":118,"case_key":277,"cost_usd":107,"sample_idx":141,"input_tokens":278,"output_tokens":279,"has_trajectory":118,"duration_seconds":280},33038,{"status":171,"finish_reason":172},"15",221,172,"7.46",{"id":282,"error":107,"extra":283,"score":145,"passed":118,"case_key":284,"cost_usd":107,"sample_idx":141,"input_tokens":285,"output_tokens":286,"has_trajectory":118,"duration_seconds":287},33039,{"status":171,"finish_reason":172},"16",286,14539,"888.10",{"id":289,"error":107,"extra":290,"score":145,"passed":118,"case_key":291,"cost_usd":107,"sample_idx":141,"input_tokens":292,"output_tokens":293,"has_trajectory":118,"duration_seconds":294},33040,{"status":171,"finish_reason":172},"17",247,1130,"74.85",{"id":296,"error":107,"extra":297,"score":145,"passed":118,"case_key":298,"cost_usd":107,"sample_idx":141,"input_tokens":299,"output_tokens":300,"has_trajectory":118,"duration_seconds":301},33041,{"status":171,"finish_reason":172},"18",455,890,"50.41",{"id":303,"error":107,"extra":304,"score":145,"passed":118,"case_key":305,"cost_usd":107,"sample_idx":141,"input_tokens":306,"output_tokens":307,"has_trajectory":118,"duration_seconds":308},33042,{"status":171,"finish_reason":172},"19",259,277,"18.22",{"id":310,"error":107,"extra":311,"score":145,"passed":118,"case_key":312,"cost_usd":107,"sample_idx":141,"input_tokens":313,"output_tokens":314,"has_trajectory":118,"duration_seconds":315},33043,{"status":171,"finish_reason":172},"20",422,1160,"83.96",{"id":317,"error":107,"extra":318,"score":145,"passed":118,"case_key":319,"cost_usd":107,"sample_idx":141,"input_tokens":320,"output_tokens":321,"has_trajectory":118,"duration_seconds":322},33044,{"status":171,"finish_reason":172},"21",306,329,"24.06",{"id":324,"error":107,"extra":325,"score":145,"passed":118,"case_key":326,"cost_usd":107,"sample_idx":141,"input_tokens":327,"output_tokens":328,"has_trajectory":118,"duration_seconds":329},33045,{"status":171,"finish_reason":172},"22",237,650,"36.74",{"id":331,"error":107,"extra":332,"score":145,"passed":118,"case_key":333,"cost_usd":107,"sample_idx":141,"input_tokens":334,"output_tokens":335,"has_trajectory":118,"duration_seconds":336},33046,{"status":171,"finish_reason":172},"23",232,836,"48.38",{"id":338,"error":107,"extra":339,"score":145,"passed":118,"case_key":340,"cost_usd":107,"sample_idx":141,"input_tokens":341,"output_tokens":342,"has_trajectory":118,"duration_seconds":343},33047,{"status":171,"finish_reason":172},"24",258,1030,"56.21",{"id":345,"error":107,"extra":346,"score":145,"passed":118,"case_key":347,"cost_usd":107,"sample_idx":141,"input_tokens":348,"output_tokens":349,"has_trajectory":118,"duration_seconds":350},33048,{"status":171,"finish_reason":172},"25",502,269,"19.09",{"id":352,"error":107,"extra":353,"score":145,"passed":118,"case_key":354,"cost_usd":107,"sample_idx":141,"input_tokens":355,"output_tokens":356,"has_trajectory":118,"duration_seconds":357},33049,{"status":171,"finish_reason":172},"26",319,706,"50.07",{"id":359,"error":107,"extra":360,"score":145,"passed":118,"case_key":361,"cost_usd":107,"sample_idx":141,"input_tokens":362,"output_tokens":258,"has_trajectory":118,"duration_seconds":363},33050,{"status":171,"finish_reason":172},"27",214,"5.36",{"id":365,"error":107,"extra":366,"score":145,"passed":118,"case_key":367,"cost_usd":107,"sample_idx":141,"input_tokens":368,"output_tokens":369,"has_trajectory":118,"duration_seconds":370},33051,{"status":171,"finish_reason":172},"28",235,1278,"72.61",{"id":372,"error":107,"extra":373,"score":145,"passed":118,"case_key":374,"cost_usd":107,"sample_idx":141,"input_tokens":375,"output_tokens":376,"has_trajectory":118,"duration_seconds":377},33052,{"status":171,"finish_reason":172},"29",230,292,"22.15",{"id":379,"error":107,"extra":380,"score":145,"passed":118,"case_key":381,"cost_usd":107,"sample_idx":141,"input_tokens":382,"output_tokens":383,"has_trajectory":118,"duration_seconds":384},33053,{"status":171,"finish_reason":172},"30",225,206,"9.09",{"id":386,"error":107,"extra":387,"score":145,"passed":118,"case_key":388,"cost_usd":107,"sample_idx":141,"input_tokens":202,"output_tokens":389,"has_trajectory":118,"duration_seconds":390},33054,{"status":171,"finish_reason":172},"31",262,"11.30",{"id":392,"error":107,"extra":393,"score":145,"passed":118,"case_key":394,"cost_usd":107,"sample_idx":141,"input_tokens":395,"output_tokens":396,"has_trajectory":118,"duration_seconds":397},33055,{"status":171,"finish_reason":172},"32",352,14998,"825.70",{"id":399,"error":107,"extra":400,"score":145,"passed":118,"case_key":401,"cost_usd":107,"sample_idx":141,"input_tokens":402,"output_tokens":403,"has_trajectory":118,"duration_seconds":404},33056,{"status":171,"finish_reason":172},"33",432,310,"22.92",{"id":406,"error":107,"extra":407,"score":145,"passed":118,"case_key":408,"cost_usd":107,"sample_idx":141,"input_tokens":409,"output_tokens":410,"has_trajectory":118,"duration_seconds":411},33057,{"status":171,"finish_reason":172},"34",243,567,"43.58",{"id":413,"error":107,"extra":414,"score":145,"passed":118,"case_key":415,"cost_usd":107,"sample_idx":141,"input_tokens":376,"output_tokens":416,"has_trajectory":118,"duration_seconds":417},33058,{"status":171,"finish_reason":172},"35",3199,"202.63",{"id":419,"error":107,"extra":420,"score":145,"passed":118,"case_key":421,"cost_usd":107,"sample_idx":141,"input_tokens":216,"output_tokens":422,"has_trajectory":118,"duration_seconds":423},33059,{"status":171,"finish_reason":172},"36",397,"24.13",{"id":425,"error":107,"extra":426,"score":145,"passed":118,"case_key":427,"cost_usd":107,"sample_idx":141,"input_tokens":428,"output_tokens":429,"has_trajectory":118,"duration_seconds":430},33060,{"status":171,"finish_reason":172},"37",228,119,"11.21",{"id":432,"error":107,"extra":433,"score":145,"passed":118,"case_key":434,"cost_usd":107,"sample_idx":141,"input_tokens":435,"output_tokens":436,"has_trajectory":118,"duration_seconds":437},33061,{"status":171,"finish_reason":172},"38",366,198,"8.84",{"id":439,"error":107,"extra":440,"score":145,"passed":118,"case_key":441,"cost_usd":107,"sample_idx":141,"input_tokens":442,"output_tokens":443,"has_trajectory":118,"duration_seconds":444},33062,{"status":171,"finish_reason":172},"39",309,11322,"640.90",{"id":446,"error":107,"extra":447,"score":145,"passed":118,"case_key":448,"cost_usd":107,"sample_idx":141,"input_tokens":449,"output_tokens":450,"has_trajectory":118,"duration_seconds":451},33063,{"status":171,"finish_reason":172},"40",205,423,"25.00",{"id":453,"error":107,"extra":454,"score":145,"passed":118,"case_key":455,"cost_usd":107,"sample_idx":141,"input_tokens":341,"output_tokens":341,"has_trajectory":118,"duration_seconds":456},33064,{"status":171,"finish_reason":172},"41","20.38",{"id":458,"error":107,"extra":459,"score":145,"passed":118,"case_key":460,"cost_usd":107,"sample_idx":141,"input_tokens":461,"output_tokens":462,"has_trajectory":118,"duration_seconds":463},33065,{"status":171,"finish_reason":172},"42",231,1940,"100.54",{"id":465,"error":107,"extra":466,"score":146,"passed":4,"case_key":468,"cost_usd":107,"sample_idx":141,"input_tokens":107,"output_tokens":107,"has_trajectory":118,"duration_seconds":107},33066,{"status":467,"finish_reason":107},"failed","43",{"id":470,"error":107,"extra":471,"score":145,"passed":118,"case_key":472,"cost_usd":107,"sample_idx":141,"input_tokens":473,"output_tokens":474,"has_trajectory":118,"duration_seconds":475},33067,{"status":171,"finish_reason":172},"44",287,311,"20.78",{"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},33068,{"status":171,"finish_reason":172},"45",219,3556,"192.08",{"id":484,"error":107,"extra":485,"score":145,"passed":118,"case_key":486,"cost_usd":107,"sample_idx":141,"input_tokens":487,"output_tokens":488,"has_trajectory":118,"duration_seconds":489},33069,{"status":171,"finish_reason":172},"46",297,3251,"175.17",{"id":491,"error":107,"extra":492,"score":145,"passed":118,"case_key":493,"cost_usd":107,"sample_idx":141,"input_tokens":494,"output_tokens":495,"has_trajectory":118,"duration_seconds":496},33070,{"status":171,"finish_reason":172},"47",223,95,"4.52",{"id":498,"error":107,"extra":499,"score":145,"passed":118,"case_key":500,"cost_usd":107,"sample_idx":141,"input_tokens":501,"output_tokens":502,"has_trajectory":118,"duration_seconds":503},33071,{"status":171,"finish_reason":172},"48",400,1304,"82.32",{"id":505,"error":107,"extra":506,"score":145,"passed":118,"case_key":507,"cost_usd":107,"sample_idx":141,"input_tokens":409,"output_tokens":508,"has_trajectory":118,"duration_seconds":509},33072,{"status":171,"finish_reason":172},"49",498,"26.50",{"total":117,"failed":152,"passed":153,"run_id":106,"ungraded":141,"sample_idx":141,"trajectories":117}]