{"config":"document","id":"arena-document","title":"Documents","category":"Search and documents","metric":"Arena score","direction":"higher","precision":2,"publishedAt":"2026-09-13","interval":"95% confidence interval","observationLabel":"Votes","description":"Human preference ratings for the overall category of this Arena task. Scores from different boards are not interchangeable.","limitations":["The population is the models in this source board, including variants and models without an available API price.","Ranks use the published confidence bounds: one plus the number of models whose lower bound exceeds this model’s upper bound. Shared ranks are not proof of equal performance."],"omissions":[],"rows":[{"name":"claude-opus-5-high","organization":"anthropic","score":1516.2663910026604,"low":1509.2451253325603,"high":1523.287656672761,"observations":8794,"sourceRank":1,"publishedAt":"2026-09-13","rank":1},{"name":"claude-fable-5.1-max","organization":"anthropic","score":1512.5843185623094,"low":1497.4036473193169,"high":1527.7649898053014,"observations":1403,"sourceRank":2,"publishedAt":"2026-09-13","rank":1},{"name":"claude-opus-4-6-high","organization":"anthropic","score":1507.3187845894272,"low":1500.8950241462112,"high":1513.7425450326432,"observations":27929,"sourceRank":3,"publishedAt":"2026-09-13","rank":1},{"name":"claude-opus-4-6","organization":"anthropic","score":1507.0536318152122,"low":1501.1833603686346,"high":1512.9239032617897,"observations":41260,"sourceRank":4,"publishedAt":"2026-09-13","rank":1},{"name":"claude-fable-5","organization":"anthropic","score":1496.0822362465265,"low":1488.2213598981848,"high":1503.9431125948686,"observations":8497,"sourceRank":5,"publishedAt":"2026-09-13","rank":2},{"name":"claude-opus-4-7","organization":"anthropic","score":1495.0390463625913,"low":1488.6649626402418,"high":1501.4131300849403,"observations":22192,"sourceRank":6,"publishedAt":"2026-09-13","rank":2},{"name":"claude-opus-4-7-high","organization":"anthropic","score":1494.7129469858314,"low":1488.207103833398,"high":1501.218790138265,"observations":21957,"sourceRank":7,"publishedAt":"2026-09-13","rank":2},{"name":"gpt-5.5","organization":"openai","score":1485.7193136054452,"low":1479.482455779253,"high":1491.956171431637,"observations":21279,"sourceRank":8,"publishedAt":"2026-09-13","rank":5},{"name":"gpt-5.5-high","organization":"openai","score":1484.4780269046255,"low":1478.100083800281,"high":1490.8559700089704,"observations":20944,"sourceRank":9,"publishedAt":"2026-09-13","rank":5},{"name":"gpt-5.6-sol-xhigh","organization":"openai","score":1482.7123255544448,"low":1473.9108602606393,"high":1491.5137908482507,"observations":4818,"sourceRank":10,"publishedAt":"2026-09-13","rank":5},{"name":"claude-sonnet-4-6","organization":"anthropic","score":1482.23522561877,"low":1476.3642726494068,"high":1488.1061785881338,"observations":57813,"sourceRank":11,"publishedAt":"2026-09-13","rank":8},{"name":"claude-opus-4-8-high","organization":"anthropic","score":1474.788449846873,"low":1467.8852931624647,"high":1481.6916065312812,"observations":11551,"sourceRank":12,"publishedAt":"2026-09-13","rank":8},{"name":"gpt-5.6-terra-xhigh","organization":"openai","score":1471.5811447461108,"low":1463.3117929827959,"high":1479.8504965094257,"observations":5787,"sourceRank":13,"publishedAt":"2026-09-13","rank":8},{"name":"gpt-5.4","organization":"openai","score":1471.0043734130195,"low":1464.9684178206312,"high":1477.0403290054078,"observations":33331,"sourceRank":14,"publishedAt":"2026-09-13","rank":10},{"name":"muse-spark-1.3-max","organization":"meta","score":1470.6564935613937,"low":1452.365050057403,"high":1488.9479370653844,"observations":1006,"sourceRank":15,"publishedAt":"2026-09-13","rank":5},{"name":"gpt-6-astra-max","organization":"openai","score":1467.5231106903996,"low":1453.2599533650027,"high":1481.7862680157964,"observations":1621,"sourceRank":16,"publishedAt":"2026-09-13","rank":8},{"name":"claude-sonnet-5-high","organization":"anthropic","score":1466.136518831971,"low":1458.4940745789263,"high":1473.7789630850154,"observations":7411,"sourceRank":17,"publishedAt":"2026-09-13","rank":12},{"name":"muse-spark-1.1","organization":"meta","score":1464.7005226650015,"low":1455.86175355964,"high":1473.539291770363,"observations":4885,"sourceRank":18,"publishedAt":"2026-09-13","rank":12},{"name":"claude-opus-4-8","organization":"anthropic","score":1464.0676818215188,"low":1457.1032033426409,"high":1471.0321603003968,"observations":12128,"sourceRank":19,"publishedAt":"2026-09-13","rank":12},{"name":"gemini-3.5-flash-medium","organization":"google","score":1463.2738281558122,"low":1455.404660409445,"high":1471.1429959021793,"observations":6500,"sourceRank":20,"publishedAt":"2026-09-13","rank":12},{"name":"claude-opus-4-5-20251101","organization":"anthropic","score":1462.1982192559744,"low":1451.7898857956338,"high":1472.6065527163155,"observations":7981,"sourceRank":21,"publishedAt":"2026-09-13","rank":12},{"name":"gemini-3.5-flash-high","organization":"google","score":1461.403811789994,"low":1452.1429772721058,"high":1470.6646463078823,"observations":4061,"sourceRank":22,"publishedAt":"2026-09-13","rank":12},{"name":"gpt-5.6-luna-xhigh","organization":"openai","score":1456.916653229613,"low":1448.7202925218398,"high":1465.1130139373859,"observations":5766,"sourceRank":23,"publishedAt":"2026-09-13","rank":13},{"name":"gemini-3.6-flash-high","organization":"google","score":1456.057486273054,"low":1445.2802300153544,"high":1466.8347425307538,"observations":2975,"sourceRank":24,"publishedAt":"2026-09-13","rank":13},{"name":"grok-4.6-high","organization":"xai","score":1452.3297871123095,"low":1440.3139973421785,"high":1464.3455768824406,"observations":2258,"sourceRank":25,"publishedAt":"2026-09-13","rank":14},{"name":"grok-4.5","organization":"xai","score":1451.9590443080492,"low":1443.2618284945743,"high":1460.6562601215242,"observations":4965,"sourceRank":26,"publishedAt":"2026-09-13","rank":15},{"name":"kimi-k2.6","organization":"moonshot","score":1450.7397099818368,"low":1443.104672618094,"high":1458.3747473455792,"observations":11291,"sourceRank":27,"publishedAt":"2026-09-13","rank":16},{"name":"claude-sonnet-4-5-20250929","organization":"anthropic","score":1449.8080646641465,"low":1443.6897264624088,"high":1455.926402865884,"observations":31455,"sourceRank":28,"publishedAt":"2026-09-13","rank":17},{"name":"muse-spark","organization":"meta","score":1444.188358957641,"low":1425.901100054967,"high":1462.4756178603152,"observations":1084,"sourceRank":29,"publishedAt":"2026-09-13","rank":15},{"name":"qwen3.7-plus","organization":"alibaba","score":1444.1444013632026,"low":1435.1230226738699,"high":1453.1657800525354,"observations":4591,"sourceRank":30,"publishedAt":"2026-09-13","rank":20},{"name":"gemini-3.1-pro-preview","organization":"google","score":1443.9187054358893,"low":1438.6941703898347,"high":1449.1432404819438,"observations":49457,"sourceRank":31,"publishedAt":"2026-09-13","rank":23},{"name":"minimax-m3","organization":"minimax","score":1434.7938037275746,"low":1426.532558045852,"high":1443.0550494092972,"observations":6314,"sourceRank":32,"publishedAt":"2026-09-13","rank":28},{"name":"gemini-3-pro","organization":"google","score":1434.086676148642,"low":1425.1751950666285,"high":1442.9981572306556,"observations":10769,"sourceRank":33,"publishedAt":"2026-09-13","rank":28},{"name":"kimi-k2.5-thinking","organization":"moonshot","score":1430.0950562216417,"low":1423.3702786608987,"high":1436.8198337823842,"observations":21569,"sourceRank":34,"publishedAt":"2026-09-13","rank":30},{"name":"gemma-4-31b","organization":"google","score":1424.5122273663578,"low":1416.7115901161187,"high":1432.3128646165972,"observations":12326,"sourceRank":35,"publishedAt":"2026-09-13","rank":31},{"name":"gemini-2.5-pro","organization":"google","score":1421.2344901606084,"low":1414.9807289534765,"high":1427.4882513677403,"observations":25110,"sourceRank":36,"publishedAt":"2026-09-13","rank":31},{"name":"claude-haiku-4-5-20251001","organization":"anthropic","score":1419.965425258912,"low":1414.0957997204337,"high":1425.835050797391,"observations":34677,"sourceRank":37,"publishedAt":"2026-09-13","rank":33},{"name":"grok-4.20-beta-0309-reasoning","organization":"xai","score":1416.182698525337,"low":1409.2125718945827,"high":1423.1528251560912,"observations":20948,"sourceRank":38,"publishedAt":"2026-09-13","rank":35},{"name":"glm-5v-turbo","organization":"zai","score":1415.5933758703818,"low":1407.3774330081324,"high":1423.8093187326313,"observations":6995,"sourceRank":39,"publishedAt":"2026-09-13","rank":34},{"name":"gemini-3-flash","organization":"google","score":1412.994825179088,"low":1403.5869499778219,"high":1422.402700380354,"observations":7158,"sourceRank":40,"publishedAt":"2026-09-13","rank":35},{"name":"gpt-5.2-high","organization":"openai","score":1404.5908350822938,"low":1395.0895621592772,"high":1414.0921080053104,"observations":7108,"sourceRank":41,"publishedAt":"2026-09-13","rank":38},{"name":"gpt-5.1","organization":"openai","score":1403.1671458960845,"low":1393.828862006449,"high":1412.5054297857205,"observations":8244,"sourceRank":42,"publishedAt":"2026-09-13","rank":38},{"name":"gpt-5.5-instant","organization":"openai","score":1402.9457548508221,"low":1395.0162313510828,"high":1410.875278350561,"observations":8497,"sourceRank":43,"publishedAt":"2026-09-13","rank":38},{"name":"gpt-5.2","organization":"openai","score":1401.1156108695666,"low":1395.1950812046412,"high":1407.036140534492,"observations":28212,"sourceRank":44,"publishedAt":"2026-09-13","rank":40}],"source":{"id":"arena","publisher":"Arena (lmarena-ai)","href":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","licence":"CC-BY-4.0","licenceUrl":"https://creativecommons.org/licenses/by/4.0/","revision":"8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53","fetchedAt":"2026-11-05T06:35:05.520Z","evidence":[{"file":"a7a159f557a1e594a5d41218fe8d53c63c63daa39b655e51d6fc5b482a17d059.json","sha256":"a7a159f557a1e594a5d41218fe8d53c63c63daa39b655e51d6fc5b482a17d059","url":"https://huggingface.co/api/datasets/lmarena-ai/leaderboard-dataset","revision":null,"role":"metadata"},{"file":"88a46d472f35274fb6b7a852c3d16c8ee8007d51b37f290161537bec26895ee4.txt","sha256":"88a46d472f35274fb6b7a852c3d16c8ee8007d51b37f290161537bec26895ee4","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/raw/8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53/README.md","revision":"8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53","role":"licence"},{"file":"5fddd9f56aa810f58b49a4463d2d400129c814bd7d76e908120956f86ae5540d.parquet","sha256":"5fddd9f56aa810f58b49a4463d2d400129c814bd7d76e908120956f86ae5540d","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53/document/latest-00000-of-00001.parquet","revision":"8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53","role":"rows"}]},"status":"fresh"}