[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"api:\u002Fnav:{}":3,"api:\u002Frecords\u002F40:{}":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":146,"rank":43,"ranked_count":72,"samples":161,"other_harnesses":165,"distribution":166,"cases":177},{"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":73,"num_samples":54,"benchmark_id":72,"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},40,null,"0.2867",{"accuracy":110,"hallucination_rate":111},"0.43833333333333335","0.27002967359050445",{"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,"2026-10-19",73127,959547,"140.81",1121487,{"access":128,"effort":129,"family":36,"is_tier":121,"hardware":107,"model_id":54,"provider":107,"data_date":130,"precision":107,"categories":131,"is_primary":121,"model_name":36,"model_slug":37,"short_name":36,"variant_id":73,"effort_rank":141,"input_price":107,"vendor_name":32,"vendor_slug":33,"architecture":107,"output_price":107,"overall_rank":43,"ranked_count":72,"release_date":142,"variant_name":143,"variant_slug":144,"vendor_order":145,"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":121,"is_open_weights":121,"inference_engine":107},"api","max","2026-10-23",[132,134,137,139],{"name":41,"rank":54,"slug":42,"score":133,"expected":43,"available":54,"ranked_count":72},"72.997032640949555000000000",{"name":45,"rank":135,"slug":46,"score":136,"expected":47,"available":72,"ranked_count":72},3,"59.363333333333333750000000",{"name":49,"rank":54,"slug":50,"score":138,"expected":43,"available":43,"ranked_count":72},"54.225000000000000000000000",{"name":52,"rank":54,"slug":53,"score":140,"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":72,"name":84,"slug":85,"license":147,"metrics":148,"version":107,"is_active":121,"num_cases":120,"parent_id":107,"score_max":152,"score_min":157,"created_at":158,"is_agentic":4,"sort_order":145,"updated_at":158,"description":107,"metric_name":159,"homepage_url":107,"license_note":107,"scoring_method":107,"composite_weight":152,"higher_is_better":121,"bundle_size_bytes":160},"public",[149,154],{"key":150,"name":151,"score":110,"score_max":152,"score_min":153,"higher_is_better":121},"accuracy","Accuracy","1.0000","0.0000",{"key":155,"name":156,"score":111,"score_max":152,"score_min":153,"higher_is_better":4},"hallucination_rate","Hallucination Rate","-1.0000","2026-10-28T09:47:38.906402+08:00","Omniscience Index",73171079,[162],{"total":120,"failed":163,"passed":164,"run_id":106,"ungraded":145,"sample_idx":145,"trajectories":120},337,263,[],[167,170,171,174],{"name":28,"rank":54,"score":168,"run_id":169,"model_slug":29,"vendor_slug":25},"0.3500",58,{"name":36,"rank":43,"score":108,"run_id":106,"model_slug":37,"vendor_slug":33},{"name":20,"rank":135,"score":172,"run_id":173,"model_slug":21,"vendor_slug":17},"0.1950",13,{"name":12,"rank":72,"score":175,"run_id":176,"model_slug":13,"vendor_slug":9},"-0.0367",113,{"restricted":4,"rows":178,"counts":510,"next_after":504},[179,188,195,201,208,215,222,229,236,243,250,257,264,271,277,284,290,297,304,311,318,325,330,337,344,351,357,364,370,376,382,389,396,403,408,414,421,427,433,440,447,453,459,465,471,477,484,490,496,503],{"id":180,"error":107,"extra":181,"score":152,"passed":121,"case_key":184,"cost_usd":107,"sample_idx":145,"input_tokens":185,"output_tokens":186,"has_trajectory":121,"duration_seconds":187},112015,{"status":182,"finish_reason":183},"completed","stop","0",119,284,"21.19",{"id":189,"error":107,"extra":190,"score":153,"passed":4,"case_key":191,"cost_usd":107,"sample_idx":145,"input_tokens":192,"output_tokens":193,"has_trajectory":121,"duration_seconds":194},112016,{"status":182,"finish_reason":183},"1",122,1766,"160.59",{"id":196,"error":107,"extra":197,"score":152,"passed":121,"case_key":198,"cost_usd":107,"sample_idx":145,"input_tokens":192,"output_tokens":199,"has_trajectory":121,"duration_seconds":200},112017,{"status":182,"finish_reason":183},"2",351,"24.97",{"id":202,"error":107,"extra":203,"score":152,"passed":121,"case_key":204,"cost_usd":107,"sample_idx":145,"input_tokens":205,"output_tokens":206,"has_trajectory":121,"duration_seconds":207},112018,{"status":182,"finish_reason":183},"3",116,1109,"89.76",{"id":209,"error":107,"extra":210,"score":153,"passed":4,"case_key":211,"cost_usd":107,"sample_idx":145,"input_tokens":212,"output_tokens":213,"has_trajectory":121,"duration_seconds":214},112019,{"status":182,"finish_reason":183},"4",141,574,"43.04",{"id":216,"error":107,"extra":217,"score":153,"passed":4,"case_key":218,"cost_usd":107,"sample_idx":145,"input_tokens":219,"output_tokens":220,"has_trajectory":121,"duration_seconds":221},112020,{"status":182,"finish_reason":183},"5",124,336,"27.02",{"id":223,"error":107,"extra":224,"score":153,"passed":4,"case_key":225,"cost_usd":107,"sample_idx":145,"input_tokens":226,"output_tokens":227,"has_trajectory":121,"duration_seconds":228},112021,{"status":182,"finish_reason":183},"6",137,541,"40.57",{"id":230,"error":107,"extra":231,"score":153,"passed":4,"case_key":232,"cost_usd":107,"sample_idx":145,"input_tokens":233,"output_tokens":234,"has_trajectory":121,"duration_seconds":235},112022,{"status":182,"finish_reason":183},"7",106,666,"51.63",{"id":237,"error":107,"extra":238,"score":152,"passed":121,"case_key":239,"cost_usd":107,"sample_idx":145,"input_tokens":240,"output_tokens":241,"has_trajectory":121,"duration_seconds":242},112023,{"status":182,"finish_reason":183},"8",129,390,"27.67",{"id":244,"error":107,"extra":245,"score":152,"passed":121,"case_key":246,"cost_usd":107,"sample_idx":145,"input_tokens":247,"output_tokens":248,"has_trajectory":121,"duration_seconds":249},112024,{"status":182,"finish_reason":183},"9",123,167,"12.67",{"id":251,"error":107,"extra":252,"score":153,"passed":4,"case_key":253,"cost_usd":107,"sample_idx":145,"input_tokens":254,"output_tokens":255,"has_trajectory":121,"duration_seconds":256},112025,{"status":182,"finish_reason":183},"10",114,712,"55.59",{"id":258,"error":107,"extra":259,"score":152,"passed":121,"case_key":260,"cost_usd":107,"sample_idx":145,"input_tokens":261,"output_tokens":262,"has_trajectory":121,"duration_seconds":263},112026,{"status":182,"finish_reason":183},"11",132,220,"16.58",{"id":265,"error":107,"extra":266,"score":153,"passed":4,"case_key":267,"cost_usd":107,"sample_idx":145,"input_tokens":268,"output_tokens":269,"has_trajectory":121,"duration_seconds":270},112027,{"status":182,"finish_reason":183},"12",142,665,"50.33",{"id":272,"error":107,"extra":273,"score":152,"passed":121,"case_key":274,"cost_usd":107,"sample_idx":145,"input_tokens":233,"output_tokens":275,"has_trajectory":121,"duration_seconds":276},112028,{"status":182,"finish_reason":183},"13",728,"56.91",{"id":278,"error":107,"extra":279,"score":153,"passed":4,"case_key":280,"cost_usd":107,"sample_idx":145,"input_tokens":281,"output_tokens":282,"has_trajectory":121,"duration_seconds":283},112029,{"status":182,"finish_reason":183},"14",111,465,"34.33",{"id":285,"error":107,"extra":286,"score":157,"passed":4,"case_key":287,"cost_usd":107,"sample_idx":145,"input_tokens":254,"output_tokens":288,"has_trajectory":121,"duration_seconds":289},112030,{"status":182,"finish_reason":183},"15",530,"39.43",{"id":291,"error":107,"extra":292,"score":152,"passed":121,"case_key":293,"cost_usd":107,"sample_idx":145,"input_tokens":294,"output_tokens":295,"has_trajectory":121,"duration_seconds":296},112031,{"status":182,"finish_reason":183},"16",126,149,"11.16",{"id":298,"error":107,"extra":299,"score":153,"passed":4,"case_key":300,"cost_usd":107,"sample_idx":145,"input_tokens":301,"output_tokens":302,"has_trajectory":121,"duration_seconds":303},112032,{"status":182,"finish_reason":183},"17",120,472,"34.77",{"id":305,"error":107,"extra":306,"score":152,"passed":121,"case_key":307,"cost_usd":107,"sample_idx":145,"input_tokens":308,"output_tokens":309,"has_trajectory":121,"duration_seconds":310},112033,{"status":182,"finish_reason":183},"18",128,83,"6.75",{"id":312,"error":107,"extra":313,"score":152,"passed":121,"case_key":314,"cost_usd":107,"sample_idx":145,"input_tokens":315,"output_tokens":316,"has_trajectory":121,"duration_seconds":317},112034,{"status":182,"finish_reason":183},"19",125,238,"17.86",{"id":319,"error":107,"extra":320,"score":157,"passed":4,"case_key":321,"cost_usd":107,"sample_idx":145,"input_tokens":322,"output_tokens":323,"has_trajectory":121,"duration_seconds":324},112035,{"status":182,"finish_reason":183},"20",104,1637,"138.50",{"id":326,"error":107,"extra":327,"score":152,"passed":121,"case_key":328,"cost_usd":107,"sample_idx":145,"input_tokens":219,"output_tokens":205,"has_trajectory":121,"duration_seconds":329},112036,{"status":182,"finish_reason":183},"21","8.97",{"id":331,"error":107,"extra":332,"score":152,"passed":121,"case_key":333,"cost_usd":107,"sample_idx":145,"input_tokens":334,"output_tokens":335,"has_trajectory":121,"duration_seconds":336},112037,{"status":182,"finish_reason":183},"22",107,273,"20.17",{"id":338,"error":107,"extra":339,"score":153,"passed":4,"case_key":340,"cost_usd":107,"sample_idx":145,"input_tokens":341,"output_tokens":342,"has_trajectory":121,"duration_seconds":343},112038,{"status":182,"finish_reason":183},"23",101,549,"41.07",{"id":345,"error":107,"extra":346,"score":153,"passed":4,"case_key":347,"cost_usd":107,"sample_idx":145,"input_tokens":348,"output_tokens":349,"has_trajectory":121,"duration_seconds":350},112039,{"status":182,"finish_reason":183},"24",110,630,"48.35",{"id":352,"error":107,"extra":353,"score":153,"passed":4,"case_key":354,"cost_usd":107,"sample_idx":145,"input_tokens":254,"output_tokens":355,"has_trajectory":121,"duration_seconds":356},112040,{"status":182,"finish_reason":183},"25",877,"69.69",{"id":358,"error":107,"extra":359,"score":152,"passed":121,"case_key":360,"cost_usd":107,"sample_idx":145,"input_tokens":361,"output_tokens":362,"has_trajectory":121,"duration_seconds":363},112041,{"status":182,"finish_reason":183},"26",105,240,"17.96",{"id":365,"error":107,"extra":366,"score":152,"passed":121,"case_key":367,"cost_usd":107,"sample_idx":145,"input_tokens":281,"output_tokens":368,"has_trajectory":121,"duration_seconds":369},112042,{"status":182,"finish_reason":183},"27",779,"61.17",{"id":371,"error":107,"extra":372,"score":152,"passed":121,"case_key":373,"cost_usd":107,"sample_idx":145,"input_tokens":247,"output_tokens":374,"has_trajectory":121,"duration_seconds":375},112043,{"status":182,"finish_reason":183},"28",170,"12.82",{"id":377,"error":107,"extra":378,"score":153,"passed":4,"case_key":379,"cost_usd":107,"sample_idx":145,"input_tokens":219,"output_tokens":380,"has_trajectory":121,"duration_seconds":381},112044,{"status":182,"finish_reason":183},"29",609,"46.50",{"id":383,"error":107,"extra":384,"score":152,"passed":121,"case_key":385,"cost_usd":107,"sample_idx":145,"input_tokens":386,"output_tokens":387,"has_trajectory":121,"duration_seconds":388},112045,{"status":182,"finish_reason":183},"30",117,62,"5.21",{"id":390,"error":107,"extra":391,"score":153,"passed":4,"case_key":392,"cost_usd":107,"sample_idx":145,"input_tokens":393,"output_tokens":394,"has_trajectory":121,"duration_seconds":395},112046,{"status":182,"finish_reason":183},"31",135,613,"45.82",{"id":397,"error":107,"extra":398,"score":157,"passed":4,"case_key":399,"cost_usd":107,"sample_idx":145,"input_tokens":400,"output_tokens":401,"has_trajectory":121,"duration_seconds":402},112047,{"status":182,"finish_reason":183},"32",102,182,"13.77",{"id":404,"error":107,"extra":405,"score":152,"passed":121,"case_key":406,"cost_usd":107,"sample_idx":145,"input_tokens":192,"output_tokens":407,"has_trajectory":121,"duration_seconds":214},112048,{"status":182,"finish_reason":183},"33",566,{"id":409,"error":107,"extra":410,"score":153,"passed":4,"case_key":411,"cost_usd":107,"sample_idx":145,"input_tokens":386,"output_tokens":412,"has_trajectory":121,"duration_seconds":413},112049,{"status":182,"finish_reason":183},"34",545,"40.81",{"id":415,"error":107,"extra":416,"score":152,"passed":121,"case_key":417,"cost_usd":107,"sample_idx":145,"input_tokens":418,"output_tokens":419,"has_trajectory":121,"duration_seconds":420},112050,{"status":182,"finish_reason":183},"35",127,153,"11.37",{"id":422,"error":107,"extra":423,"score":152,"passed":121,"case_key":424,"cost_usd":107,"sample_idx":145,"input_tokens":205,"output_tokens":425,"has_trajectory":121,"duration_seconds":426},112051,{"status":182,"finish_reason":183},"36",219,"16.52",{"id":428,"error":107,"extra":429,"score":153,"passed":4,"case_key":430,"cost_usd":107,"sample_idx":145,"input_tokens":418,"output_tokens":431,"has_trajectory":121,"duration_seconds":432},112052,{"status":182,"finish_reason":183},"37",5169,"483.24",{"id":434,"error":107,"extra":435,"score":153,"passed":4,"case_key":436,"cost_usd":107,"sample_idx":145,"input_tokens":437,"output_tokens":438,"has_trajectory":121,"duration_seconds":439},112053,{"status":182,"finish_reason":183},"38",133,850,"67.22",{"id":441,"error":107,"extra":442,"score":153,"passed":4,"case_key":443,"cost_usd":107,"sample_idx":145,"input_tokens":444,"output_tokens":445,"has_trajectory":121,"duration_seconds":446},112054,{"status":182,"finish_reason":183},"39",152,564,"42.91",{"id":448,"error":107,"extra":449,"score":153,"passed":4,"case_key":450,"cost_usd":107,"sample_idx":145,"input_tokens":308,"output_tokens":451,"has_trajectory":121,"duration_seconds":452},112055,{"status":182,"finish_reason":183},"40",991,"79.05",{"id":454,"error":107,"extra":455,"score":153,"passed":4,"case_key":456,"cost_usd":107,"sample_idx":145,"input_tokens":348,"output_tokens":457,"has_trajectory":121,"duration_seconds":458},112056,{"status":182,"finish_reason":183},"41",678,"52.69",{"id":460,"error":107,"extra":461,"score":153,"passed":4,"case_key":462,"cost_usd":107,"sample_idx":145,"input_tokens":315,"output_tokens":463,"has_trajectory":121,"duration_seconds":464},112057,{"status":182,"finish_reason":183},"42",790,"62.19",{"id":466,"error":107,"extra":467,"score":153,"passed":4,"case_key":468,"cost_usd":107,"sample_idx":145,"input_tokens":469,"output_tokens":394,"has_trajectory":121,"duration_seconds":470},112058,{"status":182,"finish_reason":183},"43",136,"46.74",{"id":472,"error":107,"extra":473,"score":153,"passed":4,"case_key":474,"cost_usd":107,"sample_idx":145,"input_tokens":437,"output_tokens":475,"has_trajectory":121,"duration_seconds":476},112059,{"status":182,"finish_reason":183},"44",598,"45.41",{"id":478,"error":107,"extra":479,"score":152,"passed":121,"case_key":480,"cost_usd":107,"sample_idx":145,"input_tokens":481,"output_tokens":482,"has_trajectory":121,"duration_seconds":483},112060,{"status":182,"finish_reason":183},"45",151,201,"15.10",{"id":485,"error":107,"extra":486,"score":153,"passed":4,"case_key":487,"cost_usd":107,"sample_idx":145,"input_tokens":219,"output_tokens":488,"has_trajectory":121,"duration_seconds":489},112061,{"status":182,"finish_reason":183},"46",605,"45.85",{"id":491,"error":107,"extra":492,"score":157,"passed":4,"case_key":493,"cost_usd":107,"sample_idx":145,"input_tokens":308,"output_tokens":494,"has_trajectory":121,"duration_seconds":495},112062,{"status":182,"finish_reason":183},"47",934,"74.44",{"id":497,"error":107,"extra":498,"score":152,"passed":121,"case_key":499,"cost_usd":107,"sample_idx":145,"input_tokens":500,"output_tokens":501,"has_trajectory":121,"duration_seconds":502},112063,{"status":182,"finish_reason":183},"48",203,432,"32.47",{"id":504,"error":107,"extra":505,"score":152,"passed":121,"case_key":506,"cost_usd":107,"sample_idx":145,"input_tokens":507,"output_tokens":508,"has_trajectory":121,"duration_seconds":509},112064,{"status":182,"finish_reason":183},"49",214,197,"14.58",{"total":120,"failed":163,"passed":164,"run_id":106,"ungraded":145,"sample_idx":145,"trajectories":120}]