{"schemaVersion":1,"generatedAt":"2026-09-05T10:23:38.928Z","license":"Per-source licenses and terms apply. See each source and THIRD_PARTY_NOTICES.txt.","methodology":"Source-native model identifiers and configurations are retained. No fuzzy model matching, no combined score, no automatic overwrite of provider list prices. fetchedAt is retrieval time, not evaluation publication time.","sources":[{"id":"openrouter","name":"OpenRouter","kind":"catalog","url":"https://openrouter.ai/models","endpoint":"https://openrouter.ai/api/v1/models?output_modalities=all","note":"Route prices in USD per 1M tokens. Conditional tiers and per-request fees are retained. Availability and billing can differ by route.","noteKo":"OpenRouter 제공 경로의 100만 토큰당 USD 가격입니다. 긴 입력 등 조건별 요금과 요청당 비용을 보존합니다. 경로별 사용 가능 여부와 과금 조건이 다를 수 있습니다.","license":"OpenRouter terms","licenseUrl":"https://openrouter.ai/terms","refreshHours":24,"enabled":true,"checkedAt":"2026-09-05T10:23:26.581Z","file":"openrouter-5214dfa34d597bbc.json","groupFiles":[],"recordCount":582,"groupCount":0,"lastSuccess":"2026-09-05T10:23:26.916Z","status":"ok","error":null,"contentHash":"f8930df30ca9c480a22130fe7eda80b314bfbd1ec49b7865863b08a400e27778","added":0,"changed":false},{"id":"modelsdev","name":"Models.dev","kind":"catalog","url":"https://models.dev","endpoint":"https://models.dev/api.json","note":"Community-maintained provider-specific model specifications and prices; not an independent benchmark.","noteKo":"커뮤니티가 관리하는 제공업체별 모델 스펙과 가격입니다. 독립 성능 평가 자료가 아닙니다.","license":"MIT","licenseUrl":"https://github.com/anomalyco/models.dev/blob/dev/LICENSE","refreshHours":24,"enabled":true,"checkedAt":"2026-09-05T10:23:26.581Z","file":"modelsdev-f7cb9cfdf10b0780.json","groupFiles":[],"recordCount":7560,"groupCount":0,"lastSuccess":"2026-09-05T10:23:27.351Z","status":"ok","error":null,"contentHash":"53f888e73dfbc5222c91505cba8e1cf3c754c6892a1fe962ce49a9f253c3db63","added":0,"changed":false},{"id":"litellm","name":"LiteLLM","kind":"catalog","url":"https://github.com/BerriAI/litellm","endpoint":"https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json","note":"Community-maintained prices, limits and capabilities. Token prices are converted to USD per 1M; non-token billing stays in original units.","noteKo":"커뮤니티가 관리하는 가격·제한·지원 기능입니다. 토큰 가격은 100만 토큰당 USD로 변환하고 그 외 과금은 원래 단위로 보존합니다.","license":"MIT (pricing data repository)","licenseUrl":"https://github.com/BerriAI/litellm/blob/main/LICENSE","refreshHours":24,"enabled":true,"checkedAt":"2026-09-05T10:23:26.581Z","file":"litellm-210ac77a091c2d26.json","groupFiles":[],"recordCount":3559,"groupCount":0,"lastSuccess":"2026-09-05T10:23:26.809Z","status":"ok","error":null,"contentHash":"977316d6a5e2386f29795206c800d9e1f1cd63f4b1a0dbbcc16e8aeb1b7fa600","added":0,"changed":false},{"id":"arena","name":"Arena","kind":"benchmark","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","endpoint":"https://huggingface.co/api/datasets/lmarena-ai/leaderboard-dataset","note":"Latest snapshots for every published subset and category. Bradley–Terry ratings and agent IPS scores remain separate; confidence bounds and sample counts are preserved.","noteKo":"공개된 모든 평가 분류와 카테고리의 최신 스냅샷입니다. 일반 평점과 에이전트 IPS 점수를 분리하고 신뢰구간·표본 수를 보존합니다.","license":"CC BY 4.0","licenseUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/main/README.md","refreshHours":24,"enabled":true,"checkedAt":"2026-09-05T10:23:26.581Z","file":"arena-e0ba93a403b98aab.json","groupFiles":[{"label":"text · industry_entertainment_and_sports_and_media · 2026-09-01","file":"arena-group-fac1b81fb648543c.json","count":396},{"label":"text · overall · 2026-09-01","file":"arena-group-a4885b113e139303.json","count":398},{"label":"text_style_control · hard_prompts_english · 2026-09-01","file":"arena-group-5f5e72b7cbd2247f.json","count":396},{"label":"text_style_control · industry_entertainment_and_sports_and_media · 2026-09-01","file":"arena-group-dca966eee8da6c15.json","count":396},{"label":"text · industry_life_and_physical_and_social_science · 2026-09-01","file":"arena-group-a0d1a8c20939d313.json","count":396},{"label":"text · french · 2026-09-01","file":"arena-group-1540323008505b9d.json","count":276},{"label":"text_style_control · creative_writing · 2026-09-01","file":"arena-group-74a304da0c22401d.json","count":396},{"label":"text_style_control · hard_prompts · 2026-09-01","file":"arena-group-df38dcd49ae9d5b4.json","count":398},{"label":"text_style_control · multi_turn · 2026-09-01","file":"arena-group-81444f39ab735e53.json","count":396},{"label":"vision_style_control · chinese · 2026-08-27","file":"arena-group-525869fff21ea948.json","count":115},{"label":"text_factuality · industry_business_and_management_and_financial_operations · 2026-09-01","file":"arena-group-c618b06a994adca2.json","count":143},{"label":"text_factuality · longer_query · 2026-09-01","file":"arena-group-fff9a60aad0a6a28.json","count":152},{"label":"text_style_control · industry_software_and_it_services · 2026-09-01","file":"arena-group-f23e53b4e1873a84.json","count":398},{"label":"text · multi_turn · 2026-09-01","file":"arena-group-ab5bfdaef0557702.json","count":396},{"label":"text · longer_query · 2026-09-01","file":"arena-group-e0a2ca41399f2471.json","count":376},{"label":"text_style_control · industry_life_and_physical_and_social_science · 2026-09-01","file":"arena-group-48d36dd335021d7e.json","count":396},{"label":"text · industry_legal_and_government · 2026-09-01","file":"arena-group-a25b3a9e76f7db33.json","count":371},{"label":"text · coding · 2026-09-01","file":"arena-group-3be6d1157846dfcf.json","count":393},{"label":"agent_tool_hallucination · overall · 2026-08-31","file":"arena-group-3fbe31526dc3ce51.json","count":56},{"label":"text_style_control · industry_medicine_and_healthcare · 2026-09-01","file":"arena-group-639ca9771e6980d8.json","count":367},{"label":"text · industry_business_and_management_and_financial_operations · 2026-09-01","file":"arena-group-a8067d9fe5755095.json","count":391},{"label":"text_factuality · non_english · 2026-09-01","file":"arena-group-7b2dce3e3d732da7.json","count":165},{"label":"text_factuality · russian · 2026-09-01","file":"arena-group-cdcc888bf7681df9.json","count":116},{"label":"text_style_control · industry_business_and_management_and_financial_operations · 2026-09-01","file":"arena-group-8bfbe9d46eee997e.json","count":391},{"label":"vision · creative_writing_vision · 2026-08-27","file":"arena-group-ad28e4f49e14c6a4.json","count":87},{"label":"text · polish · 2026-09-01","file":"arena-group-f2ce0286b1991983.json","count":219},{"label":"text_factuality · industry_software_and_it_services · 2026-09-01","file":"arena-group-995ed388590c5d20.json","count":155},{"label":"text_to_image · photorealistic · 2026-08-07","file":"arena-group-0f73d06de8699c4b.json","count":75},{"label":"text · german · 2026-09-01","file":"arena-group-155cd33b64a27904.json","count":296},{"label":"text_style_control · polish · 2026-09-01","file":"arena-group-d3e347fdaa21c6ea.json","count":219},{"label":"text_style_control · industry_legal_and_government · 2026-09-01","file":"arena-group-d1dcef60760beb3e.json","count":371},{"label":"vision_style_control · ocr · 2026-08-27","file":"arena-group-157f25ae9e0a6518.json","count":104},{"label":"text_factuality · french · 2026-09-01","file":"arena-group-a77fcefb2d830121.json","count":76},{"label":"text_style_control · coding · 2026-09-01","file":"arena-group-8948c12fe9ddba8a.json","count":393},{"label":"text_style_control · german · 2026-09-01","file":"arena-group-7e8d061ac5ab3ca5.json","count":296},{"label":"text_factuality · industry_life_and_physical_and_social_science · 2026-09-01","file":"arena-group-f335855eac24a9fc.json","count":131},{"label":"vision · english · 2026-08-27","file":"arena-group-cdca515506b04fc1.json","count":148},{"label":"text · industry_mathematical · 2026-09-01","file":"arena-group-c9b418a4d7083093.json","count":376},{"label":"text · russian · 2026-09-01","file":"arena-group-9901b7f6c7d17e8c.json","count":362},{"label":"text_factuality · chinese · 2026-09-01","file":"arena-group-81e004e51c0f9303.json","count":101},{"label":"text_factuality · industry_mathematical · 2026-09-01","file":"arena-group-de2ed6121ccb4421.json","count":97},{"label":"text_style_control · math · 2026-09-01","file":"arena-group-772fde246518402e.json","count":381},{"label":"text · english · 2026-09-01","file":"arena-group-e65562d93bf34481.json","count":398},{"label":"text · industry_software_and_it_services · 2026-09-01","file":"arena-group-993489eb87a73ef5.json","count":398},{"label":"text_style_control · expert · 2026-09-01","file":"arena-group-3c0a491c00e0a200.json","count":348},{"label":"text_factuality · industry_legal_and_government · 2026-09-01","file":"arena-group-60117615e4e359c9.json","count":104},{"label":"text · chinese · 2026-09-01","file":"arena-group-771b1e1a50837625.json","count":369},{"label":"text · exclude_ties · 2026-09-01","file":"arena-group-4df5b2c53063c864.json","count":398},{"label":"text · creative_writing · 2026-09-01","file":"arena-group-fa382c5053e1637d.json","count":396},{"label":"text · spanish · 2026-09-01","file":"arena-group-26ec00a4a7ecbb17.json","count":279},{"label":"text_factuality · expert · 2026-09-01","file":"arena-group-c53b8a2caf55fc51.json","count":107},{"label":"text_factuality · industry_medicine_and_healthcare · 2026-09-01","file":"arena-group-a99298b9ecf07f59.json","count":102},{"label":"webdev · overall · 2026-09-01","file":"arena-group-572ab5093f61d234.json","count":122},{"label":"text · non_english · 2026-09-01","file":"arena-group-6ce7f8835dcfca90.json","count":398},{"label":"text · expert · 2026-09-01","file":"arena-group-4d45f865297493d7.json","count":348},{"label":"text_style_control · non_english · 2026-09-01","file":"arena-group-d55fcd95db156564.json","count":398},{"label":"text_factuality · exclude_ties · 2026-09-01","file":"arena-group-4a1f4ea984f6579a.json","count":166},{"label":"text_style_control · overall · 2026-09-01","file":"arena-group-0c3c5a5bda36205d.json","count":398},{"label":"text · japanese · 2026-09-01","file":"arena-group-c1a24f6535d260c2.json","count":261},{"label":"text_to_image · cartoon · 2026-08-07","file":"arena-group-963afba572704f02.json","count":75},{"label":"vision_style_control · homework · 2026-08-27","file":"arena-group-3a5ab5e43da968aa.json","count":98},{"label":"text · instruction_following · 2026-09-01","file":"arena-group-d9a433b19b2c6e2a.json","count":398},{"label":"text_style_control · french · 2026-09-01","file":"arena-group-4b792f2c537b442e.json","count":276},{"label":"text_style_control · industry_mathematical · 2026-09-01","file":"arena-group-ff496a6e55ec7e86.json","count":376},{"label":"vision · chinese · 2026-08-27","file":"arena-group-35d429a1a964ad15.json","count":115},{"label":"vision · overall · 2026-08-27","file":"arena-group-880f22ad45d408d8.json","count":148},{"label":"text_style_control · longer_query · 2026-09-01","file":"arena-group-11a6c4a8803bc8dd.json","count":376},{"label":"vision_style_control · humor · 2026-08-27","file":"arena-group-0cd7d362f10f9fa0.json","count":82},{"label":"text_style_control · instruction_following · 2026-09-01","file":"arena-group-0d4954adcf2a9bc7.json","count":398},{"label":"text · industry_medicine_and_healthcare · 2026-09-01","file":"arena-group-9ecdb2ab5cbde2c6.json","count":367},{"label":"text · hard_prompts_english · 2026-09-01","file":"arena-group-207b721c1bd42dc3.json","count":396},{"label":"text_style_control · korean · 2026-09-01","file":"arena-group-d218ac3f213e140d.json","count":265},{"label":"text_factuality · creative_writing · 2026-09-01","file":"arena-group-bce13c34306c92fb.json","count":133},{"label":"text · korean · 2026-09-01","file":"arena-group-96267186d9202d3f.json","count":265},{"label":"text_style_control · chinese · 2026-09-01","file":"arena-group-896b2e4bc1060c1c.json","count":369},{"label":"text_factuality · overall · 2026-09-01","file":"arena-group-4886d734cd8969ff.json","count":167},{"label":"agent · overall · 2026-08-31","file":"arena-group-abf1c1b90c29e685.json","count":56},{"label":"agent_steerability · overall · 2026-08-31","file":"arena-group-e8d119eff94ee9d7.json","count":56},{"label":"text_factuality · multi_turn · 2026-09-01","file":"arena-group-18a5039a39be6129.json","count":135},{"label":"agent_praise_complaint · overall · 2026-08-31","file":"arena-group-763b4386cf333bea.json","count":56},{"label":"text_style_control · exclude_ties · 2026-09-01","file":"arena-group-50a923f7cd58973e.json","count":398},{"label":"webdev · webdev-react · 2026-09-01","file":"arena-group-834404d57477c869.json","count":106},{"label":"text_style_control · japanese · 2026-09-01","file":"arena-group-8f37b5dbf41a9ca3.json","count":261},{"label":"text_factuality · english · 2026-09-01","file":"arena-group-0c5a7f275d16534d.json","count":162},{"label":"vision · entity_recognition · 2026-08-27","file":"arena-group-519d300382c48181.json","count":46},{"label":"text · hard_prompts · 2026-09-01","file":"arena-group-248dd812b5b25a0c.json","count":398},{"label":"text_to_image · overall · 2026-08-07","file":"arena-group-97f517536ef2300f.json","count":75},{"label":"text_style_control · industry_writing_and_literature_and_language · 2026-09-01","file":"arena-group-2fff4ad8bbd9668b.json","count":397},{"label":"text · math · 2026-09-01","file":"arena-group-77fb9a6c1d060cec.json","count":381},{"label":"vision · diagram · 2026-08-27","file":"arena-group-a8dc5cb799fc692f.json","count":104},{"label":"text · industry_writing_and_literature_and_language · 2026-09-01","file":"arena-group-2b79957b410c77ca.json","count":397},{"label":"text_style_control · english · 2026-09-01","file":"arena-group-17a1767ad23883d3.json","count":398},{"label":"vision_style_control · diagram · 2026-08-27","file":"arena-group-3c7b252965b22656.json","count":104},{"label":"webdev · webdev-html · 2026-09-01","file":"arena-group-1ebb2ef649287dfa.json","count":121},{"label":"text_style_control · spanish · 2026-09-01","file":"arena-group-39e9224102a65745.json","count":279},{"label":"vision · ocr · 2026-08-27","file":"arena-group-d2e175743ffaff55.json","count":104},{"label":"vision · homework · 2026-08-27","file":"arena-group-b8464931c3ba8d16.json","count":98},{"label":"webdev · webdev · 2026-09-01","file":"arena-group-30932e1d58f42e36.json","count":122},{"label":"text_factuality · math · 2026-09-01","file":"arena-group-679874d2256ec266.json","count":101},{"label":"text_factuality · industry_entertainment_and_sports_and_media · 2026-09-01","file":"arena-group-3d302d02807d96b9.json","count":142},{"label":"text_to_image · text_rendering · 2026-08-07","file":"arena-group-b6a44ef78177637b.json","count":75},{"label":"text_style_control · russian · 2026-09-01","file":"arena-group-46db89944df9c98b.json","count":362},{"label":"vision_style_control · overall · 2026-08-27","file":"arena-group-84d3f2e05e088a8b.json","count":148},{"label":"text_factuality · coding · 2026-09-01","file":"arena-group-85b83e3cfe50c155.json","count":147},{"label":"text_factuality · korean · 2026-09-01","file":"arena-group-23869188744d5f49.json","count":49},{"label":"vision_style_control · creative_writing_vision · 2026-08-27","file":"arena-group-7e2654a4ae750e70.json","count":87},{"label":"document · overall · 2026-07-30","file":"arena-group-17cf9f97164ed919.json","count":38},{"label":"text_to_image · 3d_modeling · 2026-08-07","file":"arena-group-7cfb4da0982f1c84.json","count":75},{"label":"text_factuality · instruction_following · 2026-09-01","file":"arena-group-0d500411fc65928b.json","count":153},{"label":"vision · creative_writing · 2026-01-09","file":"arena-group-9c1e4fd528347da0.json","count":34},{"label":"text_to_image · commercial_design · 2026-08-07","file":"arena-group-4c8212cd9811ecae.json","count":75},{"label":"webdev · image_to_webdev · 2026-08-25","file":"arena-group-a5f190eacb0770b5.json","count":44},{"label":"text_factuality · hard_prompts_english · 2026-09-01","file":"arena-group-1bd5ff035b25dd7c.json","count":150},{"label":"agent_task_outcome_explicit · overall · 2026-08-31","file":"arena-group-c32d3e9f49ee8ca9.json","count":56},{"label":"text_factuality · polish · 2026-09-01","file":"arena-group-b9f5aa07ac836526.json","count":58},{"label":"text_factuality · hard_prompts · 2026-09-01","file":"arena-group-5e025d1c02b5abad.json","count":164},{"label":"vision_style_control · english · 2026-08-27","file":"arena-group-af1704a3595cdcb1.json","count":148},{"label":"text_to_image · russian · 2025-01-24","file":"arena-group-72c262d1b877d101.json","count":8},{"label":"text_to_image · portraits · 2026-08-07","file":"arena-group-8b3a7b9ab236dcda.json","count":75},{"label":"vision · humor · 2026-08-27","file":"arena-group-350ecef46688d585.json","count":82},{"label":"text_factuality · industry_writing_and_literature_and_language · 2026-09-01","file":"arena-group-a05b43eb1935dbe0.json","count":147},{"label":"vision_style_control · captioning · 2026-08-27","file":"arena-group-439833854bf63259.json","count":32},{"label":"image_edit · overall · 2026-08-18","file":"arena-group-ed6a89bb5c6cc55c.json","count":53},{"label":"text_factuality · spanish · 2026-09-01","file":"arena-group-7d45905f0dec993c.json","count":74},{"label":"search · overall · 2026-08-24","file":"arena-group-b9c3257ec294fc6b.json","count":34},{"label":"agent_bash_recovery_steps · overall · 2026-08-31","file":"arena-group-f49422c694dd3789.json","count":56},{"label":"document_style_control · overall · 2026-07-30","file":"arena-group-b930c6496051e60a.json","count":38},{"label":"text_to_image · art · 2026-08-07","file":"arena-group-8732165c89e72be9.json","count":75},{"label":"search_factuality · overall · 2026-08-24","file":"arena-group-fac1c390929d07e3.json","count":32},{"label":"vision_style_control · entity_recognition · 2026-08-27","file":"arena-group-5d8de00120c03d51.json","count":46},{"label":"text_factuality · japanese · 2026-09-01","file":"arena-group-e30c2a31946d226c.json","count":42},{"label":"image_to_video · overall · 2026-08-27","file":"arena-group-044134ecc634d2b9.json","count":46},{"label":"text_to_image · chinese · 2025-01-24","file":"arena-group-fd483fe8e0923695.json","count":8},{"label":"text_factuality · german · 2026-09-01","file":"arena-group-0caf9865c94f5f99.json","count":48},{"label":"video_edit · overall · 2026-08-27","file":"arena-group-e92913eff35cfb08.json","count":10},{"label":"image_edit · multi_image_edit · 2026-07-28","file":"arena-group-8e6d0beaa087b42a.json","count":40},{"label":"vision_style_control · creative_writing · 2026-01-09","file":"arena-group-fdd9fe19cd477d90.json","count":34},{"label":"vision · captioning · 2026-08-27","file":"arena-group-d3fd5781f352dcbe.json","count":32},{"label":"text_to_video · overall · 2026-08-27","file":"arena-group-1c2969c25b141104.json","count":46},{"label":"text_to_image · english · 2025-02-11","file":"arena-group-f7e5f426ec7e8f24.json","count":8},{"label":"search_style_control · overall · 2026-08-24","file":"arena-group-8022884c2d552c17.json","count":34}],"recordCount":28315,"groupCount":141,"lastSuccess":"2026-09-05T10:23:38.657Z","status":"ok","error":null,"contentHash":"96db3fe5fcf91ba4c4bef94afdf686774d168ec0175d71e7864eeac5376f658e","added":0,"changed":false},{"id":"livebench","name":"LiveBench","kind":"benchmark","url":"https://livebench.ai","endpoint":"https://api.github.com/repos/LiveBench/livebench.github.io/git/trees/main?recursive=1","note":"Newest published release. Raw subtask scores are retained and category averages require complete results. Different releases must not be pooled.","noteKo":"가장 최근 공개된 평가 버전입니다. 원래 과제 점수를 보존하고 모든 결과가 있을 때만 평균을 계산합니다. 다른 버전의 점수를 섞지 마세요.","license":"Upstream terms apply","licenseUrl":"https://livebench.ai","refreshHours":24,"enabled":true,"checkedAt":"2026-09-05T10:23:26.581Z","file":"livebench-8ebeb8ffa474ee21.json","groupFiles":[{"label":"LiveBench 2026_06_25 · Language / connections","file":"livebench-group-c2eea148fce8f9e8.json","count":28},{"label":"LiveBench 2026_06_25 · IF / paraphrase","file":"livebench-group-5c25021218dc5bf5.json","count":28},{"label":"LiveBench 2026_06_25 · Agentic Coding / javascript","file":"livebench-group-cded47f9e842592d.json","count":28},{"label":"LiveBench 2026_06_25 · Agentic Coding / typescript","file":"livebench-group-259d90169538dc97.json","count":28},{"label":"LiveBench 2026_06_25 · Mathematics / AMPS_Hard","file":"livebench-group-e01f1f85706d408b.json","count":28},{"label":"LiveBench 2026_06_25 · Overall","file":"livebench-group-bba679be47f81a46.json","count":28},{"label":"LiveBench 2026_06_25 · Language","file":"livebench-group-49e8383434c46f0a.json","count":28},{"label":"LiveBench 2026_06_25 · Language / typos","file":"livebench-group-999d00eb4c131adf.json","count":28},{"label":"LiveBench 2026_06_25 · Agentic Coding / python","file":"livebench-group-b156f56f8c1c17f6.json","count":28},{"label":"LiveBench 2026_06_25 · Reasoning / zebra_puzzle","file":"livebench-group-26fdb617e1e4144c.json","count":28},{"label":"LiveBench 2026_06_25 · Reasoning","file":"livebench-group-1fa2a61f21d20917.json","count":28},{"label":"LiveBench 2026_06_25 · Agentic Coding","file":"livebench-group-142cc86766c98440.json","count":28},{"label":"LiveBench 2026_06_25 · Mathematics / olympiad","file":"livebench-group-7e31b9cbcea838dd.json","count":28},{"label":"LiveBench 2026_06_25 · Data Analysis / tablereformat","file":"livebench-group-4ca91b8847275104.json","count":28},{"label":"LiveBench 2026_06_25 · Mathematics","file":"livebench-group-37eaab992187f73a.json","count":28},{"label":"LiveBench 2026_06_25 · IF","file":"livebench-group-25e9fff51cf70d17.json","count":28},{"label":"LiveBench 2026_06_25 · Data Analysis / consecutive_events","file":"livebench-group-017bb9e31abbd29d.json","count":28},{"label":"LiveBench 2026_06_25 · Coding / code_completion","file":"livebench-group-b57ae7be920ad1a1.json","count":28},{"label":"LiveBench 2026_06_25 · IF / simplify","file":"livebench-group-3a0a962015eeed99.json","count":28},{"label":"LiveBench 2026_06_25 · Data Analysis","file":"livebench-group-1a01bed913f1b44f.json","count":28},{"label":"LiveBench 2026_06_25 · Data Analysis / tablejoin","file":"livebench-group-4b79bd7f751df342.json","count":28},{"label":"LiveBench 2026_06_25 · Coding","file":"livebench-group-ff092b9ac04b0854.json","count":28},{"label":"LiveBench 2026_06_25 · Reasoning / theory_of_mind","file":"livebench-group-16988539e21487c1.json","count":28},{"label":"LiveBench 2026_06_25 · Reasoning / spatial","file":"livebench-group-5cf774af3bed4914.json","count":28},{"label":"LiveBench 2026_06_25 · IF / summarize","file":"livebench-group-52385e4b9ca6c678.json","count":28},{"label":"LiveBench 2026_06_25 · Mathematics / integrals_with_game","file":"livebench-group-538e1bbed8b38fc6.json","count":28},{"label":"LiveBench 2026_06_25 · Reasoning / logic_with_navigation","file":"livebench-group-e6e6dd1a8aa041e3.json","count":28},{"label":"LiveBench 2026_06_25 · Language / plot_unscrambling","file":"livebench-group-d21ab9dafafacf49.json","count":28},{"label":"LiveBench 2026_06_25 · Mathematics / math_comp","file":"livebench-group-d608c6094c85afe5.json","count":28},{"label":"LiveBench 2026_06_25 · IF / story_generation","file":"livebench-group-e800d85929364412.json","count":28},{"label":"LiveBench 2026_06_25 · Coding / code_generation","file":"livebench-group-43bf6a52e5a5ed52.json","count":28}],"recordCount":868,"groupCount":31,"lastSuccess":"2026-09-05T10:23:27.450Z","status":"ok","error":null,"contentHash":"c385118efce74980ebbee9400933b2207ad44f6b22552018347ff41d313e6328","added":0,"changed":false},{"id":"livecodebench","name":"LiveCodeBench","kind":"benchmark","url":"https://livecodebench.github.io","endpoint":"https://livecodebench.github.io/performances_generation.json","note":"Public code-generation results grouped by the exact test window. The public feed may lag the latest models.","noteKo":"공개 코드 생성 평가를 문제 기간·문제 집합별로 구분합니다. 공개 피드에 최신 모델 결과가 없을 수 있습니다.","license":"Upstream terms apply","licenseUrl":"https://livecodebench.github.io","refreshHours":24,"enabled":true,"checkedAt":"2026-09-05T10:23:26.581Z","file":"livecodebench-3fe622acbec08c48.json","groupFiles":[{"label":"LiveCodeBench · 2023-12 · 40 tasks · 5cd80f19fca6","file":"livecodebench-group-b3fd1434fe58ab1c.json","count":28},{"label":"LiveCodeBench · 2023-07 · 54 tasks · d229dc31aa24","file":"livecodebench-group-37c70785f1653f32.json","count":28},{"label":"LiveCodeBench · 2023-05 · 34 tasks · b19af162b8e1","file":"livecodebench-group-d414cf4f2f390ba2.json","count":28},{"label":"LiveCodeBench · 2024-07 · 48 tasks · d9dd5ac04318","file":"livecodebench-group-6c85ea11b6286e26.json","count":28},{"label":"LiveCodeBench · 2025-01 · 51 tasks · fb4940e7808d","file":"livecodebench-group-4443f177770b2d87.json","count":28},{"label":"LiveCodeBench · 2024-01 · 36 tasks · 26e07264faa6","file":"livecodebench-group-2d7769c29fc3bae2.json","count":28},{"label":"LiveCodeBench · 2023-06 · 39 tasks · a01cd6d9ae51","file":"livecodebench-group-1a849accb034ed7c.json","count":28},{"label":"LiveCodeBench · 2024-09 · 61 tasks · 41f2966d90e9","file":"livecodebench-group-770bd7c628313a49.json","count":28},{"label":"LiveCodeBench · 2024-12 · 57 tasks · 6d85c495675c","file":"livecodebench-group-a4d13dbfd33e8377.json","count":28},{"label":"LiveCodeBench · 2024-03 · 45 tasks · 7da6344d102d","file":"livecodebench-group-2e963a5aef93c594.json","count":28},{"label":"LiveCodeBench · 2024-11 · 49 tasks · 67df66ce2ed7","file":"livecodebench-group-e9b0ea047cf0c875.json","count":28},{"label":"LiveCodeBench · 2024-04 · 37 tasks · 6e2a0fcc05e4","file":"livecodebench-group-2ab348cb5600afbf.json","count":28},{"label":"LiveCodeBench · 2024-06 · 41 tasks · 019dbf4b410a","file":"livecodebench-group-4722ca894ded7ce7.json","count":28},{"label":"LiveCodeBench · Full public feed · 1055 tasks · 412e1a43ae72","file":"livecodebench-group-960276a9f8ee2344.json","count":28},{"label":"LiveCodeBench · 2023-11 · 35 tasks · bcc52bc9abf1","file":"livecodebench-group-2478292b64ee6b1c.json","count":28},{"label":"LiveCodeBench · 2025-03 · 68 tasks · 4dd09548f05a","file":"livecodebench-group-a760a5be76979312.json","count":28},{"label":"LiveCodeBench · 2025-04 · 12 tasks · 28a576276675","file":"livecodebench-group-5dd19c70bf14be27.json","count":28},{"label":"LiveCodeBench · 2024-08 · 52 tasks · e0d411141b9b","file":"livecodebench-group-cc116c04aabd0944.json","count":28},{"label":"LiveCodeBench · 2023-09 · 36 tasks · 452ecea7e902","file":"livecodebench-group-2bd64b2f2b5c9b15.json","count":28},{"label":"LiveCodeBench · 2025-02 · 51 tasks · ca761f72f26f","file":"livecodebench-group-e53855eeb00e8891.json","count":28},{"label":"LiveCodeBench · 2024-02 · 32 tasks · 9a752b60d9c0","file":"livecodebench-group-59e4398cfcf1cecc.json","count":28},{"label":"LiveCodeBench · 2024-10 · 53 tasks · 6d659747fcb9","file":"livecodebench-group-a3879c269b0692ed.json","count":28},{"label":"LiveCodeBench · 2023-10 · 52 tasks · b5b0627a476f","file":"livecodebench-group-960de5145010e83d.json","count":28},{"label":"LiveCodeBench · 2024-05 · 36 tasks · 4411c01be04b","file":"livecodebench-group-b5bc45fbb5baa6f8.json","count":28},{"label":"LiveCodeBench · 2023-08 · 36 tasks · 26b96d3d2942","file":"livecodebench-group-d047aae688a149e6.json","count":28}],"recordCount":700,"groupCount":25,"lastSuccess":"2026-09-05T10:23:27.777Z","status":"ok","error":null,"contentHash":"a9318a2459a87ed493de5218c4d344055293a684a783088eda369b66327bb7ed","added":0,"changed":false},{"id":"swebench","name":"SWE-bench","kind":"benchmark","url":"https://www.swebench.com","endpoint":"https://raw.githubusercontent.com/SWE-bench/swe-bench.github.io/master/data/leaderboards.json","note":"Verified, Lite, Test, Multilingual and Multimodal are separate suites. Each row is a model + agent submission; checked and self-reported results are distinguished.","noteKo":"Verified·Lite·Test·Multilingual·Multimodal은 서로 다른 평가입니다. 각 행은 모델+에이전트 제출 결과이며 검증 여부를 함께 표시합니다.","license":"Upstream terms apply","licenseUrl":"https://www.swebench.com","refreshHours":24,"enabled":true,"checkedAt":"2026-09-05T10:23:26.581Z","file":"swebench-afef571af1c0960d.json","groupFiles":[{"label":"SWE-bench Verified","file":"swebench-group-8f95dc31b846a0f7.json","count":180},{"label":"SWE-bench Test","file":"swebench-group-820a03236cedc3b7.json","count":24},{"label":"SWE-bench Lite","file":"swebench-group-5a1a40cd79ac2d25.json","count":84},{"label":"SWE-bench Multilingual","file":"swebench-group-13cecbbbf4881cb3.json","count":13},{"label":"SWE-bench Multimodal","file":"swebench-group-d9fced0c920a2573.json","count":22}],"recordCount":323,"groupCount":5,"lastSuccess":"2026-09-05T10:23:27.520Z","status":"ok","error":null,"contentHash":"d9289bc0acabd81a1e00106e6d98c8d4a36cc91cbc1bc9151fd3c1b4d032117d","added":0,"changed":false},{"id":"aider","name":"Aider Polyglot","kind":"benchmark","url":"https://aider.chat/docs/leaderboards/","endpoint":"https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml","note":"First-pass and two-attempt success rates are separate. Edit format, Aider version, test count and run cost are retained.","noteKo":"첫 시도와 두 번 시도한 성공률을 분리합니다. 편집 형식, Aider 버전, 테스트 수, 실행 비용을 보존합니다.","license":"Apache-2.0","licenseUrl":"https://github.com/Aider-AI/aider/blob/main/LICENSE.txt","refreshHours":24,"enabled":true,"checkedAt":"2026-09-05T10:23:26.581Z","file":"aider-16bf94aa96444ee9.json","groupFiles":[{"label":"Aider Polyglot · 224 tasks · pass@1","file":"aider-group-b0a66f20dec71183.json","count":5},{"label":"Aider Polyglot · 225 tasks · pass@1","file":"aider-group-23396d1156292187.json","count":63},{"label":"Aider Polyglot · 225 tasks · pass@2","file":"aider-group-c4df46181941bc31.json","count":63},{"label":"Aider Polyglot · 223 tasks · pass@1","file":"aider-group-ca878b59a9ee9074.json","count":1},{"label":"Aider Polyglot · 224 tasks · pass@2","file":"aider-group-c97fba03d82be113.json","count":5},{"label":"Aider Polyglot · 223 tasks · pass@2","file":"aider-group-86ff8720b123e4f4.json","count":1}],"recordCount":138,"groupCount":6,"lastSuccess":"2026-09-05T10:23:27.555Z","status":"ok","error":null,"contentHash":"2b989cab9c1a804ac41334f078054c7abee41d722d25395be2f6beec2654c5fb","added":0,"changed":false},{"id":"evalplus","name":"EvalPlus","kind":"benchmark","url":"https://evalplus.github.io/leaderboard.html","endpoint":"https://evalplus.github.io/results.json","note":"HumanEval, HumanEval+, MBPP and MBPP+ pass@1 scores. The feed does not specify a publication date; retrieval time is not evaluation time.","noteKo":"HumanEval·HumanEval+·MBPP·MBPP+의 pass@1 결과입니다. 원본에 발표일이 없어 미공개로 표시합니다.","license":"Upstream terms apply","licenseUrl":"https://evalplus.github.io/leaderboard.html","refreshHours":24,"enabled":true,"checkedAt":"2026-09-05T10:23:26.581Z","file":"evalplus-1e83ac48ff8a5e20.json","groupFiles":[{"label":"EvalPlus · mbpp+","file":"evalplus-group-a7def0f2e94d85fa.json","count":89},{"label":"EvalPlus · humaneval+","file":"evalplus-group-faf84765d35df0fa.json","count":125},{"label":"EvalPlus · mbpp","file":"evalplus-group-8e04a4d4ca4d742c.json","count":89},{"label":"EvalPlus · humaneval","file":"evalplus-group-a23c7d080fedaf0f.json","count":125}],"recordCount":428,"groupCount":4,"lastSuccess":"2026-09-05T10:23:27.804Z","status":"ok","error":null,"contentHash":"6b584bf1f8db724cd7ca81bf86b122ce653e0b7912c0ffcf5f183295892c2895","added":0,"changed":false},{"id":"bfcl","name":"Berkeley Function Calling","kind":"benchmark","url":"https://gorilla.cs.berkeley.edu/leaderboard.html","endpoint":"https://gorilla.cs.berkeley.edu/data_overall.csv","note":"BFCL version is checked against the official page on each refresh. Function-calling vs prompted configurations, multi-turn, memory, search, cost and latency remain separate.","noteKo":"갱신할 때 공식 페이지에서 BFCL 버전을 확인합니다. 함수 호출과 프롬프트 방식, 멀티턴·메모리·검색·비용·지연을 구분합니다.","license":"Upstream terms apply","licenseUrl":"https://gorilla.cs.berkeley.edu/leaderboard.html","refreshHours":24,"enabled":true,"checkedAt":"2026-09-05T10:23:26.581Z","file":"bfcl-bc101bca79176383.json","groupFiles":[{"label":"BFCL V4 · Latency Standard Deviation (s)","file":"bfcl-group-cc96b4417dcf861d.json","count":109},{"label":"BFCL V4 · Memory Recursive Summarization","file":"bfcl-group-97866cbf99e24a4f.json","count":109},{"label":"BFCL V4 · Multi Turn Miss Func","file":"bfcl-group-36f5d14eb785f7b7.json","count":109},{"label":"BFCL V4 · Multi Turn Base","file":"bfcl-group-4ccf39e3f762e205.json","count":109},{"label":"BFCL V4 · Memory Acc","file":"bfcl-group-db80b79a1ea8869b.json","count":109},{"label":"BFCL V4 · Live Multiple AST","file":"bfcl-group-70b78a0420b2ac93.json","count":109},{"label":"BFCL V4 · Overall Acc","file":"bfcl-group-5fad17199593847a.json","count":109},{"label":"BFCL V4 · Non-Live Parallel AST","file":"bfcl-group-f25cb26f091a0678.json","count":109},{"label":"BFCL V4 · Live Simple AST","file":"bfcl-group-cc930f11fcd1b70d.json","count":109},{"label":"BFCL V4 · Web Search No Snippet","file":"bfcl-group-abb1592506200aea.json","count":109},{"label":"BFCL V4 · Live Acc","file":"bfcl-group-2c0af1fac8f62e3f.json","count":109},{"label":"BFCL V4 · Live Parallel Multiple AST","file":"bfcl-group-cd9d8862b56d08df.json","count":109},{"label":"BFCL V4 · Live Parallel AST","file":"bfcl-group-a5568e1e0d53e6f2.json","count":109},{"label":"BFCL V4 · Web Search Acc","file":"bfcl-group-36913618035d99b0.json","count":109},{"label":"BFCL V4 · Latency 95th Percentile (s)","file":"bfcl-group-6e285c63fd1b25c0.json","count":109},{"label":"BFCL V4 · Non-Live Parallel Multiple AST","file":"bfcl-group-ac47552eb7598e21.json","count":109},{"label":"BFCL V4 · Format Sensitivity Standard Deviation","file":"bfcl-group-42ecc8be36763fbc.json","count":40},{"label":"BFCL V4 · Multi Turn Long Context","file":"bfcl-group-769e3bbc06c3a971.json","count":109},{"label":"BFCL V4 · Latency Mean (s)","file":"bfcl-group-52ceac76d19a2dec.json","count":109},{"label":"BFCL V4 · Irrelevance Detection","file":"bfcl-group-b78957ab5547b998.json","count":109},{"label":"BFCL V4 · Memory Vector","file":"bfcl-group-a718e246273497ba.json","count":109},{"label":"BFCL V4 · Multi Turn Miss Param","file":"bfcl-group-d64460acfd250bf0.json","count":109},{"label":"BFCL V4 · Format Sensitivity Max Delta","file":"bfcl-group-82e7c4cf80b1459c.json","count":40},{"label":"BFCL V4 · Non-Live Multiple AST","file":"bfcl-group-997135743761157c.json","count":109},{"label":"BFCL V4 · Relevance Detection","file":"bfcl-group-a9c75fb47240e104.json","count":109},{"label":"BFCL V4 · Non-Live Simple AST","file":"bfcl-group-e7fa54f6aa75a228.json","count":109},{"label":"BFCL V4 · Memory KV","file":"bfcl-group-1438d94dcadc292f.json","count":109},{"label":"BFCL V4 · Web Search Base","file":"bfcl-group-bf73f21ded7206b9.json","count":109},{"label":"BFCL V4 · Multi Turn Acc","file":"bfcl-group-4f2742061dda2a92.json","count":109},{"label":"BFCL V4 · Non-Live AST Acc","file":"bfcl-group-6a07a47386ea715a.json","count":109}],"recordCount":3132,"groupCount":30,"lastSuccess":"2026-09-05T10:23:28.087Z","status":"ok","error":null,"contentHash":"6fc1074bebbf225a9829fde0315b76d808ef0e0193bd2e71f7c64331c3802e6e","added":0,"changed":false},{"id":"arc","name":"ARC Prize","kind":"benchmark","url":"https://arcprize.org/leaderboard","endpoint":"https://arcprize.org/media/data/evaluations.json","note":"ARC-AGI versions and public/semi-private sets are separate. Standard and provider-adapter harnesses, reasoning effort and cost units are preserved.","noteKo":"ARC-AGI 버전과 public/semi-private 세트를 구분합니다. 하네스, 추론 설정, 비용 단위를 보존합니다.","license":"Upstream terms apply","licenseUrl":"https://arcprize.org/leaderboard","refreshHours":24,"enabled":true,"checkedAt":"2026-09-05T10:23:26.581Z","file":"arc-19f42aa9ab2726f9.json","groupFiles":[{"label":"ARC-AGI · v2_Semi_Private · Published configuration","file":"arc-group-5ab3e9abb30ce100.json","count":223},{"label":"ARC-AGI · v2_Public_Eval · Published configuration","file":"arc-group-d0675e988d605ace.json","count":212},{"label":"ARC-AGI · v3_Semi_Private · Published configuration","file":"arc-group-3bc3d58ce5a0ec4d.json","count":33},{"label":"ARC-AGI · v3_Semi_Private · Provider Adapter","file":"arc-group-042f904d24dd4c30.json","count":6},{"label":"ARC-AGI · v1_Public_Eval · Published configuration","file":"arc-group-32db5267d1797daf.json","count":202},{"label":"ARC-AGI · v1_Semi_Private · Published configuration","file":"arc-group-5c74b0319f0542e3.json","count":222},{"label":"ARC-AGI · v2_Private_Eval · Published configuration","file":"arc-group-a0033e57ad91b37d.json","count":2}],"recordCount":900,"groupCount":7,"lastSuccess":"2026-09-05T10:23:28.616Z","status":"ok","error":null,"contentHash":"b3c7f31efc45cedcc7bc97ec70e135e93a809f8987934f8da9e442f29b77de8c","added":0,"changed":false},{"id":"artificialanalysis","name":"Artificial Analysis","kind":"benchmark","url":"https://artificialanalysis.ai","endpoint":"https://artificialanalysis.ai/api/v2/data/llms/models","note":"Independent evaluations, intelligence indexes, throughput and latency. Every effort variant is retained. API key is read only by the local updater.","noteKo":"독립 벤치마크와 지능 지수·출력 속도·응답 지연입니다. 추론 설정별 결과를 보존하며 API 키는 수집기에서만 사용합니다.","license":"Artificial Analysis API attribution terms","licenseUrl":"https://artificialanalysis.ai/api-reference","refreshHours":24,"enabled":true,"authEnv":"AA_API_KEY","checkedAt":"2026-09-05T10:23:26.581Z","file":"artificialanalysis-93a1400688991c32.json","groupFiles":[{"label":"Artificial Analysis · tau_banking","file":"artificialanalysis-group-aad9fc12d5a879c4.json","count":203},{"label":"Artificial Analysis · tau2","file":"artificialanalysis-group-8b8b5a0aa8a49380.json","count":440},{"label":"Artificial Analysis · lcr","file":"artificialanalysis-group-b82a066ba49065b3.json","count":509},{"label":"Artificial Analysis · artificial_analysis_intelligence_index","file":"artificialanalysis-group-f787ceec8dfa7f06.json","count":630},{"label":"Artificial Analysis · artificial_analysis_math_index","file":"artificialanalysis-group-13c8c7f1c4f30833.json","count":270},{"label":"Artificial Analysis · gpqa","file":"artificialanalysis-group-3a7922f0aa33418c.json","count":611},{"label":"Artificial Analysis · aime","file":"artificialanalysis-group-2ced0a873cf6f9a8.json","count":194},{"label":"Artificial Analysis · median_time_to_first_answer_token","file":"artificialanalysis-group-42315cb11f2c40c1.json","count":193},{"label":"Artificial Analysis · terminalbench_v2_1","file":"artificialanalysis-group-71e0e1fa9b15aefe.json","count":235},{"label":"Artificial Analysis · ifbench","file":"artificialanalysis-group-3877438e200e6899.json","count":450},{"label":"Artificial Analysis · median_time_to_first_token_seconds","file":"artificialanalysis-group-99b200cf1209a5b2.json","count":193},{"label":"Artificial Analysis · hle","file":"artificialanalysis-group-64954cd0f8bf8a74.json","count":602},{"label":"Artificial Analysis · terminalbench_hard","file":"artificialanalysis-group-a22296f3aa811241.json","count":432},{"label":"Artificial Analysis · median_output_tokens_per_second","file":"artificialanalysis-group-bbaa39d708c68e78.json","count":193},{"label":"Artificial Analysis · scicode","file":"artificialanalysis-group-4b63da2bf4d1b92f.json","count":88},{"label":"Artificial Analysis · livecodebench","file":"artificialanalysis-group-231a46a943492f6c.json","count":343},{"label":"Artificial Analysis · mmlu_pro","file":"artificialanalysis-group-1ba94527a89159e4.json","count":349},{"label":"Artificial Analysis · aime_25","file":"artificialanalysis-group-5e5aae327cbe13b6.json","count":270},{"label":"Artificial Analysis · math_500","file":"artificialanalysis-group-e4fb9200bdc044bd.json","count":202},{"label":"Artificial Analysis · artificial_analysis_coding_index","file":"artificialanalysis-group-d49b3298b9dedb6c.json","count":255}],"recordCount":6662,"groupCount":20,"lastSuccess":"2026-09-05T10:19:01.947Z","status":"stale","error":"HTTP 401: https://artificialanalysis.ai/api/v2/data/llms/models"},{"id":"aa-text-to-image","name":"Artificial Analysis · text-to-image","kind":"benchmark","url":"https://artificialanalysis.ai","endpoint":"https://artificialanalysis.ai/api/v2/data/media/text-to-image?include_categories=true","note":"Media preference ratings. Quality settings, category breakdowns, appearances and reported confidence intervals are preserved.","noteKo":"미디어 선호도 평가입니다. 화질 설정, 카테고리별 결과, 평가 표본 수와 보고된 신뢰구간을 보존합니다.","license":"Artificial Analysis API attribution terms","licenseUrl":"https://artificialanalysis.ai/api-reference","refreshHours":24,"enabled":true,"authEnv":"AA_API_KEY","checkedAt":"2026-09-05T10:23:26.581Z","file":"aa-text-to-image-c1431f5caabd8330.json","groupFiles":[{"label":"Artificial Analysis · text-to-image · Physical Spaces","file":"aa-text-to-image-group-9fd2016ff37f74e0.json","count":92},{"label":"Artificial Analysis · text-to-image · Futuristic & Sci-Fi","file":"aa-text-to-image-group-1f6237be8e439024.json","count":97},{"label":"Artificial Analysis · text-to-image · Traditional Art","file":"aa-text-to-image-group-c6b38f688528ec9a.json","count":48},{"label":"Artificial Analysis · text-to-image · UI/UX Design","file":"aa-text-to-image-group-b24e025656eeed27.json","count":71},{"label":"Artificial Analysis · text-to-image · overall","file":"aa-text-to-image-group-e6cfd5bccb059eb0.json","count":157},{"label":"Artificial Analysis · text-to-image · People: Groups & Activities","file":"aa-text-to-image-group-1df113e76db6aaed.json","count":87},{"label":"Artificial Analysis · text-to-image · Fantasy & Mythical","file":"aa-text-to-image-group-1ee67ba192ec8972.json","count":104},{"label":"Artificial Analysis · text-to-image · Graphic Design & Digital Rendering","file":"aa-text-to-image-group-d93a19747c0e477a.json","count":89},{"label":"Artificial Analysis · text-to-image · Anime","file":"aa-text-to-image-group-fce6b10f52415cdd.json","count":96},{"label":"Artificial Analysis · text-to-image · People: Portraits","file":"aa-text-to-image-group-7b349faa2337db61.json","count":88},{"label":"Artificial Analysis · text-to-image · Cartoon & Illustration","file":"aa-text-to-image-group-0f2710e94ab85870.json","count":77},{"label":"Artificial Analysis · text-to-image · Vintage & Retro","file":"aa-text-to-image-group-84538c7541ffbb82.json","count":15},{"label":"Artificial Analysis · text-to-image · Commercial","file":"aa-text-to-image-group-1e9e91012cf87170.json","count":88},{"label":"Artificial Analysis · text-to-image · General & Photorealistic","file":"aa-text-to-image-group-4642a65446e54610.json","count":89},{"label":"Artificial Analysis · text-to-image · Nature & Landscapes","file":"aa-text-to-image-group-3f1d7be2b6a70de6.json","count":87},{"label":"Artificial Analysis · text-to-image · Text & Typography","file":"aa-text-to-image-group-87601da8ece238d4.json","count":77}],"recordCount":1362,"groupCount":16,"lastSuccess":"2026-09-05T10:19:02.421Z","status":"stale","error":"HTTP 401: https://artificialanalysis.ai/api/v2/data/media/text-to-image?include_categories=true"},{"id":"aa-image-editing","name":"Artificial Analysis · image-editing","kind":"benchmark","url":"https://artificialanalysis.ai","endpoint":"https://artificialanalysis.ai/api/v2/data/media/image-editing?include_categories=true","note":"Media preference ratings. Quality settings, category breakdowns, appearances and reported confidence intervals are preserved.","noteKo":"미디어 선호도 평가입니다. 화질 설정, 카테고리별 결과, 평가 표본 수와 보고된 신뢰구간을 보존합니다.","license":"Artificial Analysis API attribution terms","licenseUrl":"https://artificialanalysis.ai/api-reference","refreshHours":24,"enabled":true,"authEnv":"AA_API_KEY","checkedAt":"2026-09-05T10:23:26.581Z","file":"aa-image-editing-fea4b2ca0f5f06f6.json","groupFiles":[{"label":"Artificial Analysis · image-editing · overall","file":"aa-image-editing-group-532210d395273883.json","count":74}],"recordCount":74,"groupCount":1,"lastSuccess":"2026-09-05T10:19:02.460Z","status":"stale","error":"HTTP 401: https://artificialanalysis.ai/api/v2/data/media/image-editing?include_categories=true"},{"id":"aa-text-to-speech","name":"Artificial Analysis · text-to-speech","kind":"benchmark","url":"https://artificialanalysis.ai","endpoint":"https://artificialanalysis.ai/api/v2/data/media/text-to-speech?include_categories=true","note":"Media preference ratings. Quality settings, category breakdowns, appearances and reported confidence intervals are preserved.","noteKo":"미디어 선호도 평가입니다. 화질 설정, 카테고리별 결과, 평가 표본 수와 보고된 신뢰구간을 보존합니다.","license":"Artificial Analysis API attribution terms","licenseUrl":"https://artificialanalysis.ai/api-reference","refreshHours":24,"enabled":true,"authEnv":"AA_API_KEY","checkedAt":"2026-09-05T10:23:26.581Z","file":"aa-text-to-speech-24dfb4bab7502bb7.json","groupFiles":[{"label":"Artificial Analysis · text-to-speech · overall","file":"aa-text-to-speech-group-e4920fd1f96c5ed0.json","count":97}],"recordCount":97,"groupCount":1,"lastSuccess":"2026-09-05T10:19:02.739Z","status":"stale","error":"HTTP 401: https://artificialanalysis.ai/api/v2/data/media/text-to-speech?include_categories=true"},{"id":"aa-text-to-video","name":"Artificial Analysis · text-to-video","kind":"benchmark","url":"https://artificialanalysis.ai","endpoint":"https://artificialanalysis.ai/api/v2/data/media/text-to-video?include_categories=true","note":"Media preference ratings. Quality settings, category breakdowns, appearances and reported confidence intervals are preserved.","noteKo":"미디어 선호도 평가입니다. 화질 설정, 카테고리별 결과, 평가 표본 수와 보고된 신뢰구간을 보존합니다.","license":"Artificial Analysis API attribution terms","licenseUrl":"https://artificialanalysis.ai/api-reference","refreshHours":24,"enabled":true,"authEnv":"AA_API_KEY","checkedAt":"2026-09-05T10:23:26.581Z","file":"aa-text-to-video-4f2d715686aab915.json","groupFiles":[{"label":"Artificial Analysis · text-to-video · Buildings","file":"aa-text-to-video-group-50d17612f85d346d.json","count":81},{"label":"Artificial Analysis · text-to-video · Photorealistic","file":"aa-text-to-video-group-54c1a56eb44118d9.json","count":68},{"label":"Artificial Analysis · text-to-video · Sci Fi","file":"aa-text-to-video-group-675cfab103692662.json","count":81},{"label":"Artificial Analysis · text-to-video · Transport","file":"aa-text-to-video-group-b86695c4dd096092.json","count":81},{"label":"Artificial Analysis · text-to-video · Text","file":"aa-text-to-video-group-cdf0ff8dea9d6ed0.json","count":81},{"label":"Artificial Analysis · text-to-video · Food","file":"aa-text-to-video-group-fc21f70e8eea7b1e.json","count":79},{"label":"Artificial Analysis · text-to-video · Specific location or era","file":"aa-text-to-video-group-0295d8a7fbc795ab.json","count":81},{"label":"Artificial Analysis · text-to-video · Indoor","file":"aa-text-to-video-group-68a8a2d9d2a3a130.json","count":81},{"label":"Artificial Analysis · text-to-video · Specific lighting","file":"aa-text-to-video-group-6f3f4efb19c8ac0e.json","count":81},{"label":"Artificial Analysis · text-to-video · Fashion","file":"aa-text-to-video-group-a6bc87f5abf66d51.json","count":81},{"label":"Artificial Analysis · text-to-video · Weather and effects","file":"aa-text-to-video-group-fee45ef616a44edb.json","count":81},{"label":"Artificial Analysis · text-to-video · Fantasy","file":"aa-text-to-video-group-0ccca36ca5a3b2fc.json","count":78},{"label":"Artificial Analysis · text-to-video · Screens","file":"aa-text-to-video-group-87269cd34ae64f67.json","count":76},{"label":"Artificial Analysis · text-to-video · Nature","file":"aa-text-to-video-group-94e73573391f527a.json","count":81},{"label":"Artificial Analysis · text-to-video · overall","file":"aa-text-to-video-group-b665d7b8ad424f81.json","count":81},{"label":"Artificial Analysis · text-to-video · Short prompt","file":"aa-text-to-video-group-9e622df9ff8e0474.json","count":81},{"label":"Artificial Analysis · text-to-video · Physics","file":"aa-text-to-video-group-da0e31d1ef07f26a.json","count":81},{"label":"Artificial Analysis · text-to-video · Sports","file":"aa-text-to-video-group-c89b8fd811d4b002.json","count":81},{"label":"Artificial Analysis · text-to-video · Abstract","file":"aa-text-to-video-group-81b1e41ef5f1c64c.json","count":70},{"label":"Artificial Analysis · text-to-video · Cartoon and anime","file":"aa-text-to-video-group-aff9e7852c722634.json","count":81},{"label":"Artificial Analysis · text-to-video · Multi-scene","file":"aa-text-to-video-group-f984c4d34abf3470.json","count":79},{"label":"Artificial Analysis · text-to-video · Animals","file":"aa-text-to-video-group-477753487b26a657.json","count":81},{"label":"Artificial Analysis · text-to-video · Moving camera","file":"aa-text-to-video-group-cdedd3e0b6fee829.json","count":81},{"label":"Artificial Analysis · text-to-video · 3D animation","file":"aa-text-to-video-group-20e7461b89125b8e.json","count":66},{"label":"Artificial Analysis · text-to-video · Action","file":"aa-text-to-video-group-3471b0f2defe6900.json","count":81},{"label":"Artificial Analysis · text-to-video · Long prompt","file":"aa-text-to-video-group-285e45153faac003.json","count":81},{"label":"Artificial Analysis · text-to-video · Outdoor","file":"aa-text-to-video-group-cfc002cedc5a3f45.json","count":81},{"label":"Artificial Analysis · text-to-video · People","file":"aa-text-to-video-group-8372ae1e27782aa9.json","count":81},{"label":"Artificial Analysis · text-to-video · Water","file":"aa-text-to-video-group-b0df88436297fe93.json","count":81},{"label":"Artificial Analysis · text-to-video · Technology","file":"aa-text-to-video-group-4cf43bfac71a82dc.json","count":81}],"recordCount":2379,"groupCount":30,"lastSuccess":"2026-09-05T10:19:03.121Z","status":"stale","error":"HTTP 401: https://artificialanalysis.ai/api/v2/data/media/text-to-video?include_categories=true"},{"id":"aa-image-to-video","name":"Artificial Analysis · image-to-video","kind":"benchmark","url":"https://artificialanalysis.ai","endpoint":"https://artificialanalysis.ai/api/v2/data/media/image-to-video?include_categories=true","note":"Media preference ratings. Quality settings, category breakdowns, appearances and reported confidence intervals are preserved.","noteKo":"미디어 선호도 평가입니다. 화질 설정, 카테고리별 결과, 평가 표본 수와 보고된 신뢰구간을 보존합니다.","license":"Artificial Analysis API attribution terms","licenseUrl":"https://artificialanalysis.ai/api-reference","refreshHours":24,"enabled":true,"authEnv":"AA_API_KEY","checkedAt":"2026-09-05T10:23:26.581Z","file":"aa-image-to-video-c9f11354e618d593.json","groupFiles":[{"label":"Artificial Analysis · image-to-video · Specific lighting","file":"aa-image-to-video-group-aae1af9b0d021f89.json","count":75},{"label":"Artificial Analysis · image-to-video · Outdoor","file":"aa-image-to-video-group-efaa4534e6ac59bf.json","count":75},{"label":"Artificial Analysis · image-to-video · Buildings","file":"aa-image-to-video-group-cd1aa02a7965cea9.json","count":75},{"label":"Artificial Analysis · image-to-video · Screens","file":"aa-image-to-video-group-bf902bd0f45c786b.json","count":72},{"label":"Artificial Analysis · image-to-video · Water","file":"aa-image-to-video-group-9c813b1644d94b21.json","count":75},{"label":"Artificial Analysis · image-to-video · Long prompt","file":"aa-image-to-video-group-ca0f74871d55b52f.json","count":46},{"label":"Artificial Analysis · image-to-video · Moving camera","file":"aa-image-to-video-group-7a582ffba0e765c2.json","count":75},{"label":"Artificial Analysis · image-to-video · Indoor","file":"aa-image-to-video-group-c8b64f0acb93c68e.json","count":75},{"label":"Artificial Analysis · image-to-video · Animals","file":"aa-image-to-video-group-5d8403be342571aa.json","count":75},{"label":"Artificial Analysis · image-to-video · Transport","file":"aa-image-to-video-group-9585b0205f5e6aae.json","count":75},{"label":"Artificial Analysis · image-to-video · Food","file":"aa-image-to-video-group-18fd1915af8d4c84.json","count":75},{"label":"Artificial Analysis · image-to-video · Fantasy","file":"aa-image-to-video-group-bd8ca6659cf340e8.json","count":72},{"label":"Artificial Analysis · image-to-video · Technology","file":"aa-image-to-video-group-0c4345ec93ec308f.json","count":75},{"label":"Artificial Analysis · image-to-video · Nature","file":"aa-image-to-video-group-5dccc809e66e9a84.json","count":75},{"label":"Artificial Analysis · image-to-video · Sports","file":"aa-image-to-video-group-e5e884d0b3ed1c9f.json","count":75},{"label":"Artificial Analysis · image-to-video · Abstract","file":"aa-image-to-video-group-480385b560eefb04.json","count":72},{"label":"Artificial Analysis · image-to-video · Photorealistic","file":"aa-image-to-video-group-8709f7d177a2b07b.json","count":75},{"label":"Artificial Analysis · image-to-video · Multi-scene","file":"aa-image-to-video-group-e9e253eb791c7be9.json","count":45},{"label":"Artificial Analysis · image-to-video · Fashion","file":"aa-image-to-video-group-156673ce30401736.json","count":75},{"label":"Artificial Analysis · image-to-video · Cartoon and anime","file":"aa-image-to-video-group-cb0b80bc122c916e.json","count":70},{"label":"Artificial Analysis · image-to-video · People","file":"aa-image-to-video-group-c3dc6fe2a03a8191.json","count":75},{"label":"Artificial Analysis · image-to-video · Short prompt","file":"aa-image-to-video-group-a3c7d8831750fd40.json","count":75},{"label":"Artificial Analysis · image-to-video · Action","file":"aa-image-to-video-group-695fb28b4dabf5d3.json","count":75},{"label":"Artificial Analysis · image-to-video · overall","file":"aa-image-to-video-group-cce28655b4fa47ee.json","count":75},{"label":"Artificial Analysis · image-to-video · Text","file":"aa-image-to-video-group-7e30c6955b8ea1a8.json","count":75},{"label":"Artificial Analysis · image-to-video · 3D animation","file":"aa-image-to-video-group-70289984f060da67.json","count":74},{"label":"Artificial Analysis · image-to-video · Physics","file":"aa-image-to-video-group-91db70d747960612.json","count":75},{"label":"Artificial Analysis · image-to-video · Weather and effects","file":"aa-image-to-video-group-8a2fbd0f2a3dbabe.json","count":75},{"label":"Artificial Analysis · image-to-video · Sci Fi","file":"aa-image-to-video-group-1795c5318628c8c3.json","count":47},{"label":"Artificial Analysis · image-to-video · Specific location or era","file":"aa-image-to-video-group-80b2e42a9969124b.json","count":2}],"recordCount":2075,"groupCount":30,"lastSuccess":"2026-09-05T10:19:03.210Z","status":"stale","error":"HTTP 401: https://artificialanalysis.ai/api/v2/data/media/image-to-video?include_categories=true"}],"candidates":[{"name":"MTEB / MMTEB","url":"https://huggingface.co/spaces/mteb/leaderboard","reason":"Embedding evaluations need benchmark version, task set, language, pooling and embedding dimension. A stable aggregate feed has not yet been validated."},{"name":"Terminal-Bench","url":"https://www.tbench.ai/leaderboard","reason":"Terminal agents require the exact benchmark version, harness and uncertainty. A stable public result feed has not yet been validated."},{"name":"HELM","url":"https://crfm.stanford.edu/helm/","reason":"Import individual suites with their scenario and metric definitions; do not combine unrelated suite averages."},{"name":"KMMLU / KoBEST / KUDGE","url":"https://huggingface.co/datasets/HAERAE-HUB/KMMLU","reason":"Korean-language coverage is valuable. Public question datasets alone are not verified model result tables; reproducible evaluations are needed."}]}