{"config":"webdev","id":"arena-webdev","title":"Web development","category":"Coding and agents","metric":"Arena score","direction":"higher","precision":2,"publishedAt":"2026-10-28","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":[{"name":"GPT-5.3-Codex (Codex Harness)","entries":2,"reason":"The source publishes different results under this same name without a distinct variant identifier. All ambiguous entries are omitted."}],"rows":[{"name":"Claude Opus 5.5 (Max)","organization":"anthropic","score":1809.8391605525123,"low":1797.0047852622824,"high":1822.673535842742,"observations":3473,"sourceRank":1,"publishedAt":"2026-10-28","rank":1},{"name":"GPT-6 Astra (Max)","organization":"openai","score":1773.3545606290113,"low":1763.8328470745705,"high":1782.876274183452,"observations":7210,"sourceRank":2,"publishedAt":"2026-10-28","rank":2},{"name":"Claude Sonnet 5.5 (xHigh)","organization":"anthropic","score":1769.7283971913196,"low":1758.4502972988341,"high":1781.006497083805,"observations":4469,"sourceRank":3,"publishedAt":"2026-10-28","rank":2},{"name":"Gemini 4 Carbon (High)","organization":"google","score":1768.1522310766236,"low":1753.1512248464587,"high":1783.1532373067887,"observations":2230,"sourceRank":4,"publishedAt":"2026-10-28","rank":2},{"name":"GPT-6.1 Sol (Max)","organization":"openai","score":1750.568215754016,"low":1739.1403199480676,"high":1761.9961115599644,"observations":4092,"sourceRank":5,"publishedAt":"2026-10-28","rank":3},{"name":"Claude Fable 5.1 (Max)","organization":"anthropic","score":1745.8518267992542,"low":1737.2976889065808,"high":1754.405964691928,"observations":8614,"sourceRank":6,"publishedAt":"2026-10-28","rank":4},{"name":"Muse Wonder Full (Max)","organization":"meta","score":1725.3158378428036,"low":1711.4583620962712,"high":1739.173313589336,"observations":2248,"sourceRank":7,"publishedAt":"2026-10-28","rank":5},{"name":"Claude Sonnet 5.5 (High)","organization":"anthropic","score":1710.5864353676154,"low":1701.3939622012724,"high":1719.7789085339584,"observations":6371,"sourceRank":8,"publishedAt":"2026-10-28","rank":7},{"name":"Kimi K3.1 Pro (Max)","organization":"moonshot","score":1694.582449167362,"low":1681.6236547546387,"high":1707.5412435800854,"observations":2671,"sourceRank":9,"publishedAt":"2026-10-28","rank":8},{"name":"Claude Opus 5 (Max)","organization":"anthropic","score":1690.5239169555273,"low":1684.4223558772017,"high":1696.625478033853,"observations":19641,"sourceRank":10,"publishedAt":"2026-10-28","rank":9},{"name":"Gemini 4 Argon (High)","organization":"google","score":1679.2118291253184,"low":1667.7836721812448,"high":1690.639986069392,"observations":3437,"sourceRank":11,"publishedAt":"2026-10-28","rank":9},{"name":"GPT-6 Sol (Max)","organization":"openai","score":1678.189584003976,"low":1668.8001662896868,"high":1687.5790017182655,"observations":5714,"sourceRank":12,"publishedAt":"2026-10-28","rank":9},{"name":"Qwen3.8-Max (0902)","organization":"alibaba","score":1675.9355584770149,"low":1669.264050116608,"high":1682.6070668374218,"observations":17936,"sourceRank":13,"publishedAt":"2026-10-28","rank":10},{"name":"GPT-6.1 Terra (Max)","organization":"openai","score":1672.6547058209349,"low":1657.3346917882454,"high":1687.9747198536243,"observations":1821,"sourceRank":14,"publishedAt":"2026-10-28","rank":9},{"name":"Qwen3.8-Max","organization":"alibaba","score":1671.885286248237,"low":1659.8180632666053,"high":1683.9525092298686,"observations":3406,"sourceRank":15,"publishedAt":"2026-10-28","rank":10},{"name":"DeepSeek-V4.1-Flash-20261017 (Max)","organization":"deepseek","score":1665.040445245608,"low":1657.02755320211,"high":1673.0533372891057,"observations":7842,"sourceRank":16,"publishedAt":"2026-10-28","rank":11},{"name":"Claude Opus 5 (High)","organization":"anthropic","score":1658.189754773115,"low":1652.922757292659,"high":1663.456752253571,"observations":26887,"sourceRank":17,"publishedAt":"2026-10-28","rank":14},{"name":"Kimi K3 (Max)","organization":"moonshot","score":1656.390908396489,"low":1650.5567373388326,"high":1662.2250794541453,"observations":21281,"sourceRank":18,"publishedAt":"2026-10-28","rank":14},{"name":"Muse Spark 1.3 (Max)","organization":"meta","score":1656.2348593321256,"low":1648.7775363232556,"high":1663.6921823409955,"observations":10796,"sourceRank":19,"publishedAt":"2026-10-28","rank":14},{"name":"Muse Wonder (Max)","organization":"meta","score":1652.0939667524244,"low":1641.0173070157305,"high":1663.1706264891186,"observations":3724,"sourceRank":20,"publishedAt":"2026-10-28","rank":14},{"name":"Grok 4.7 (xHigh)","organization":"xai","score":1637.4572057581888,"low":1628.702398350564,"high":1646.2120131658135,"observations":6572,"sourceRank":21,"publishedAt":"2026-10-28","rank":20},{"name":"MiMo-V2.6-Flash","organization":"xiaomi","score":1637.1737027632755,"low":1628.7251695184052,"high":1645.6222360081458,"observations":7068,"sourceRank":22,"publishedAt":"2026-10-28","rank":20},{"name":"Hy4 preview","organization":"tencent","score":1631.1069363530096,"low":1621.4556290278233,"high":1640.7582436781959,"observations":4765,"sourceRank":23,"publishedAt":"2026-10-28","rank":21},{"name":"Qwen3.8-Flash-Next","organization":"alibaba","score":1628.3220907822047,"low":1620.7152592990487,"high":1635.9289222653608,"observations":9703,"sourceRank":24,"publishedAt":"2026-10-28","rank":21},{"name":"MiMo-V2.6-Pro","organization":"xiaomi","score":1625.417548626546,"low":1617.0147664248568,"high":1633.820330828235,"observations":6820,"sourceRank":25,"publishedAt":"2026-10-28","rank":21},{"name":"Claude Fable 5 (High)","organization":"anthropic","score":1624.082589402146,"low":1618.1078673431737,"high":1630.0573114611184,"observations":16951,"sourceRank":26,"publishedAt":"2026-10-28","rank":21},{"name":"GLM-5.3 (Max)","organization":"zai","score":1622.8098625429598,"low":1615.5595486077714,"high":1630.0601764781482,"observations":11150,"sourceRank":27,"publishedAt":"2026-10-28","rank":21},{"name":"Muse Spark 1.3 (xHigh)","organization":"meta","score":1620.064431270458,"low":1612.6710367801993,"high":1627.4578257607166,"observations":10243,"sourceRank":28,"publishedAt":"2026-10-28","rank":23},{"name":"DeepSeek-V4.1-Flash-20260910 (Max)","organization":"deepseek","score":1619.1588129696818,"low":1608.1963653871228,"high":1630.1212605522408,"observations":3510,"sourceRank":29,"publishedAt":"2026-10-28","rank":21},{"name":"Grok 4.6 (High)","organization":"xai","score":1616.3867226095672,"low":1609.3897320040517,"high":1623.3837132150825,"observations":11966,"sourceRank":30,"publishedAt":"2026-10-28","rank":23},{"name":"GPT-5.6 Sol (xHigh, Codex Harness)","organization":"openai","score":1615.7849726003753,"low":1610.0332231565444,"high":1621.5367220442063,"observations":18884,"sourceRank":31,"publishedAt":"2026-10-28","rank":23},{"name":"GLM-5.3-Flash","organization":"zai","score":1606.6486731495352,"low":1600.3145985111457,"high":1612.9827477879248,"observations":21587,"sourceRank":32,"publishedAt":"2026-10-28","rank":28},{"name":"GLM-5.2 (Max)","organization":"zai","score":1605.639209438289,"low":1599.7439785073198,"high":1611.5344403692586,"observations":17817,"sourceRank":33,"publishedAt":"2026-10-28","rank":29},{"name":"Qwen3.8-27B","organization":"alibaba","score":1589.782268834193,"low":1583.5192465442685,"high":1596.0452911241173,"observations":18752,"sourceRank":34,"publishedAt":"2026-10-28","rank":34},{"name":"Gemini 3.7 Flash (High)","organization":"google","score":1589.6728568868868,"low":1583.1771976253099,"high":1596.168516148464,"observations":14473,"sourceRank":35,"publishedAt":"2026-10-28","rank":34},{"name":"Claude Haiku 5.5 (High)","organization":"anthropic","score":1588.8330617127986,"low":1579.1616933890941,"high":1598.504430036503,"observations":4758,"sourceRank":36,"publishedAt":"2026-10-28","rank":34},{"name":"Gemini 3.8 Flash (High)","organization":"google","score":1583.2994176433617,"low":1576.2679678193863,"high":1590.330867467337,"observations":12342,"sourceRank":37,"publishedAt":"2026-10-28","rank":34},{"name":"MiniMax-M3.1-Flash","organization":"minimax","score":1582.4578204140666,"low":1570.927739058925,"high":1593.987901769208,"observations":3062,"sourceRank":38,"publishedAt":"2026-10-28","rank":34},{"name":"DeepSeek-V4-Pro (High, 20260813)","organization":"deepseek","score":1581.8580682830898,"low":1572.3901175318756,"high":1591.3260190343042,"observations":4676,"sourceRank":39,"publishedAt":"2026-10-28","rank":34},{"name":"DeepSeek-V4-Flash (High)","organization":"deepseek","score":1581.8380356617101,"low":1572.5418571503953,"high":1591.134214173025,"observations":4927,"sourceRank":40,"publishedAt":"2026-10-28","rank":34},{"name":"GPT-6 Luna (Max)","organization":"openai","score":1579.4041580064886,"low":1573.5972848414442,"high":1585.2110311715333,"observations":27808,"sourceRank":41,"publishedAt":"2026-10-28","rank":34},{"name":"Step 5 Preview (High)","organization":"stepfun","score":1571.03868087871,"low":1562.098162591625,"high":1579.979199165795,"observations":5966,"sourceRank":42,"publishedAt":"2026-10-28","rank":36},{"name":"Claude Opus 4.7 (High)","organization":"anthropic","score":1557.537773306169,"low":1551.7855280776807,"high":1563.290018534657,"observations":17859,"sourceRank":43,"publishedAt":"2026-10-28","rank":42},{"name":"Claude Opus 4.8 (High)","organization":"anthropic","score":1555.8263524171814,"low":1550.0654597594967,"high":1561.5872450748664,"observations":18408,"sourceRank":44,"publishedAt":"2026-10-28","rank":43},{"name":"Claude Opus 4.7","organization":"anthropic","score":1555.4286270187122,"low":1549.8059793570835,"high":1561.0512746803408,"observations":18167,"sourceRank":45,"publishedAt":"2026-10-28","rank":43},{"name":"Grok 4.5","organization":"xai","score":1553.032541111338,"low":1546.3518706108093,"high":1559.7132116118669,"observations":11018,"sourceRank":46,"publishedAt":"2026-10-28","rank":43},{"name":"Claude Opus 4.6 (High)","organization":"anthropic","score":1546.235576890829,"low":1540.7643430161768,"high":1551.7068107654811,"observations":19316,"sourceRank":47,"publishedAt":"2026-10-28","rank":44},{"name":"Mistral Large 4","organization":"mistral","score":1544.3103315032786,"low":1533.756929898643,"high":1554.8637331079142,"observations":4068,"sourceRank":48,"publishedAt":"2026-10-28","rank":43},{"name":"Muse Spark 1.1","organization":"meta","score":1542.4822191942499,"low":1534.8531724948775,"high":1550.1112658936222,"observations":7935,"sourceRank":49,"publishedAt":"2026-10-28","rank":44},{"name":"Claude Sonnet 5 (High)","organization":"anthropic","score":1540.090043634944,"low":1534.2660535559125,"high":1545.9140337139759,"observations":16832,"sourceRank":50,"publishedAt":"2026-10-28","rank":47},{"name":"Gemini 3.6 Flash (High)","organization":"google","score":1537.5456409227427,"low":1530.050356740605,"high":1545.0409251048804,"observations":8722,"sourceRank":51,"publishedAt":"2026-10-28","rank":47},{"name":"Claude Opus 4.6","organization":"anthropic","score":1537.008164689128,"low":1531.653163253918,"high":1542.3631661243385,"observations":20576,"sourceRank":52,"publishedAt":"2026-10-28","rank":47},{"name":"Claude Opus 4.8","organization":"anthropic","score":1535.9780359669865,"low":1530.2787318649582,"high":1541.6773400690145,"observations":17323,"sourceRank":53,"publishedAt":"2026-10-28","rank":47},{"name":"Muse Spark 1.2 (xHigh)","organization":"meta","score":1533.6689783572438,"low":1520.0044115132641,"high":1547.3335452012234,"observations":2155,"sourceRank":54,"publishedAt":"2026-10-28","rank":46},{"name":"Muse Spark Open (Max)","organization":"meta","score":1526.2373165722156,"low":1510.944606608046,"high":1541.5300265363855,"observations":1721,"sourceRank":55,"publishedAt":"2026-10-28","rank":47},{"name":"Claude Sonnet 4.6","organization":"anthropic","score":1522.6524947374642,"low":1517.4972604740078,"high":1527.8077290009207,"observations":22733,"sourceRank":56,"publishedAt":"2026-10-28","rank":54},{"name":"GPT-5.6 Terra (xHigh, Codex Harness)","organization":"openai","score":1520.1279670236868,"low":1514.0304659478788,"high":1526.2254680994945,"observations":15388,"sourceRank":57,"publishedAt":"2026-10-28","rank":54},{"name":"Seed2.1 Pro Preview","organization":"bytedance","score":1519.1039947604677,"low":1513.2976265847963,"high":1524.910362936139,"observations":16294,"sourceRank":58,"publishedAt":"2026-10-28","rank":54},{"name":"GPT-5.6 Luna (xHigh, Codex Harness)","organization":"openai","score":1518.9116265563573,"low":1512.4907283430762,"high":1525.3325247696382,"observations":12522,"sourceRank":59,"publishedAt":"2026-10-28","rank":54},{"name":"Qwen3.7-Max (20260517)","organization":"alibaba","score":1515.1361678106236,"low":1507.7628474030214,"high":1522.509488218226,"observations":8855,"sourceRank":60,"publishedAt":"2026-10-28","rank":54},{"name":"GPT-5.5 (xHigh, Codex Harness)","organization":"openai","score":1512.099404756151,"low":1506.1264837807623,"high":1518.0723257315399,"observations":15553,"sourceRank":61,"publishedAt":"2026-10-28","rank":55},{"name":"Kimi K2.6","organization":"moonshot","score":1509.2234110707893,"low":1501.981372868751,"high":1516.4654492728278,"observations":10119,"sourceRank":62,"publishedAt":"2026-10-28","rank":56},{"name":"GLM-5.1","organization":"zai","score":1507.854558177699,"low":1501.0707352459954,"high":1514.6383811094026,"observations":10647,"sourceRank":63,"publishedAt":"2026-10-28","rank":56},{"name":"Hy3","organization":"tencent","score":1505.4337074624896,"low":1497.333933783004,"high":1513.533481141975,"observations":6844,"sourceRank":64,"publishedAt":"2026-10-28","rank":57},{"name":"Gemini 3.5 Flash (High)","organization":"google","score":1499.2741854109668,"low":1492.007830289957,"high":1506.5405405319768,"observations":9331,"sourceRank":65,"publishedAt":"2026-10-28","rank":61},{"name":"Claude Opus 4.5 (High, 32K, 20251101)","organization":"anthropic","score":1493.6607664512705,"low":1485.3708764445084,"high":1501.9506564580329,"observations":10981,"sourceRank":66,"publishedAt":"2026-10-28","rank":63},{"name":"Gemini 3.5 Flash (Medium)","organization":"google","score":1490.6327257802702,"low":1483.9689702146968,"high":1497.2964813458436,"observations":12075,"sourceRank":67,"publishedAt":"2026-10-28","rank":65},{"name":"GPT-5.5 (High, Codex Harness)","organization":"openai","score":1486.7293325820726,"low":1480.8093335923602,"high":1492.6493315717853,"observations":17853,"sourceRank":68,"publishedAt":"2026-10-28","rank":65},{"name":"MiniMax-M3","organization":"minimax","score":1483.3051511403955,"low":1477.8997468513835,"high":1488.7105554294073,"observations":21032,"sourceRank":69,"publishedAt":"2026-10-28","rank":66},{"name":"Spark-X2.6","organization":"synlan","score":1481.9961109790227,"low":1463.0956335148933,"high":1500.896588443152,"observations":1210,"sourceRank":70,"publishedAt":"2026-10-28","rank":64},{"name":"Qwen3.6-Max-Preview","organization":"alibaba","score":1481.8179582284795,"low":1469.2986453665058,"high":1494.3372710904532,"observations":2700,"sourceRank":71,"publishedAt":"2026-10-28","rank":65},{"name":"MiMo-V2.5-Pro","organization":"xiaomi","score":1480.4355329379657,"low":1475.2165116902313,"high":1485.6545541857004,"observations":22604,"sourceRank":72,"publishedAt":"2026-10-28","rank":66},{"name":"Kimi K2.7 Code","organization":"moonshot","score":1473.5355204604502,"low":1464.1197387912318,"high":1482.9513021296689,"observations":4950,"sourceRank":73,"publishedAt":"2026-10-28","rank":68},{"name":"Claude Opus 4.5 (20251101)","organization":"anthropic","score":1469.2204625828695,"low":1462.0054781050226,"high":1476.4354470607166,"observations":13362,"sourceRank":74,"publishedAt":"2026-10-28","rank":70},{"name":"DeepSeek-V4-Pro Preview (High)","organization":"deepseek","score":1464.190999873057,"low":1457.871444656885,"high":1470.510555089229,"observations":13087,"sourceRank":75,"publishedAt":"2026-10-28","rank":71},{"name":"GPT-5.4 (High, Codex Harness)","organization":"openai","score":1463.4770483714215,"low":1444.604736788249,"high":1482.349359954594,"observations":1345,"sourceRank":76,"publishedAt":"2026-10-28","rank":68},{"name":"Qwen3.6-Plus","organization":"alibaba","score":1461.6254246112119,"low":1456.0389278050607,"high":1467.2119214173633,"observations":18511,"sourceRank":77,"publishedAt":"2026-10-28","rank":72},{"name":"GPT-5.5 (Codex Harness)","organization":"openai","score":1456.0796664601917,"low":1450.189624046008,"high":1461.969708874375,"observations":15811,"sourceRank":78,"publishedAt":"2026-10-28","rank":75},{"name":"DeepSeek-V4-Pro","organization":"deepseek","score":1447.1690797309973,"low":1440.832478058101,"high":1453.5056814038935,"observations":13931,"sourceRank":79,"publishedAt":"2026-10-28","rank":77},{"name":"Gemini 3.1 Pro Preview","organization":"google","score":1446.6498483953492,"low":1441.585927923699,"high":1451.713768866999,"observations":24129,"sourceRank":80,"publishedAt":"2026-10-28","rank":77},{"name":"GPT-5.4 (Medium, Codex Harness)","organization":"openai","score":1443.6136223052815,"low":1425.3264123246315,"high":1461.9008322859315,"observations":1374,"sourceRank":81,"publishedAt":"2026-10-28","rank":75},{"name":"Gemini 3 Flash","organization":"google","score":1440.1243208284204,"low":1431.5056581563315,"high":1448.7429835005091,"observations":10845,"sourceRank":82,"publishedAt":"2026-10-28","rank":78},{"name":"Gemini 3 Pro","organization":"google","score":1439.9733520268244,"low":1431.51521797956,"high":1448.431486074089,"observations":14054,"sourceRank":83,"publishedAt":"2026-10-28","rank":78},{"name":"MiMo-V2.5","organization":"xiaomi","score":1438.2678187561378,"low":1432.2437576057287,"high":1444.291879906547,"observations":14837,"sourceRank":84,"publishedAt":"2026-10-28","rank":79},{"name":"Kimi K2.5 (Thinking)","organization":"moonshot","score":1436.2450288272603,"low":1431.0298121307376,"high":1441.460245523783,"observations":20008,"sourceRank":85,"publishedAt":"2026-10-28","rank":80},{"name":"Beam 1.0 501B A23B","organization":"reflection","score":1436.0479044399463,"low":1423.2717321812627,"high":1448.8240766986298,"observations":2932,"sourceRank":86,"publishedAt":"2026-10-28","rank":78},{"name":"GLM-5","organization":"zai","score":1435.569438296295,"low":1427.408439056557,"high":1443.730437536033,"observations":7465,"sourceRank":87,"publishedAt":"2026-10-28","rank":79},{"name":"GLM-4.7","organization":"zai","score":1435.1854984949694,"low":1423.1124773248948,"high":1447.258519665044,"observations":3948,"sourceRank":88,"publishedAt":"2026-10-28","rank":78},{"name":"MiMo-V2-Pro","organization":"xiaomi","score":1434.1505957574632,"low":1426.002251111771,"high":1442.2989404031553,"observations":7225,"sourceRank":89,"publishedAt":"2026-10-28","rank":79},{"name":"Gemini 3.5 Flash-Lite","organization":"google","score":1434.0835335612885,"low":1393.0705102632426,"high":1475.0965568593347,"observations":236,"sourceRank":90,"publishedAt":"2026-10-28","rank":71},{"name":"DeepSeek-V4-Flash Preview (High)","organization":"deepseek","score":1430.4821164472921,"low":1423.5158830659445,"high":1437.44834982864,"observations":10074,"sourceRank":91,"publishedAt":"2026-10-28","rank":81},{"name":"GPT-5 (Medium)","organization":"openai","score":1417.276921350425,"low":1401.6815134635042,"high":1432.8723292373459,"observations":3089,"sourceRank":92,"publishedAt":"2026-10-28","rank":81},{"name":"GPT-5.2","organization":"openai","score":1416.424922259506,"low":1393.8333216470496,"high":1439.0165228719625,"observations":1082,"sourceRank":93,"publishedAt":"2026-10-28","rank":81},{"name":"Inkling","organization":"thinky","score":1415.192007852744,"low":1409.1942877491174,"high":1421.1897279563705,"observations":17073,"sourceRank":94,"publishedAt":"2026-10-28","rank":91},{"name":"Inkling-Small","organization":"thinky","score":1409.1376517895078,"low":1400.0318311791993,"high":1418.2434723998163,"observations":5295,"sourceRank":95,"publishedAt":"2026-10-28","rank":91},{"name":"Kimi K2.5 (Instant)","organization":"moonshot","score":1405.5661928557854,"low":1393.4891166711952,"high":1417.6432690403758,"observations":3246,"sourceRank":97,"publishedAt":"2026-10-28","rank":91},{"name":"GPT-5.4","organization":"openai","score":1401.0886143328514,"low":1391.1326896098626,"high":1411.04453905584,"observations":4499,"sourceRank":98,"publishedAt":"2026-10-28","rank":91},{"name":"GLM-5V-Turbo","organization":"zai","score":1400.9863808273662,"low":1387.7419997351728,"high":1414.2307619195599,"observations":2394,"sourceRank":99,"publishedAt":"2026-10-28","rank":91},{"name":"Qwen3.5-397B-A17B","organization":"alibaba","score":1400.2208309279806,"low":1395.0902358908133,"high":1405.3514259651479,"observations":21096,"sourceRank":100,"publishedAt":"2026-10-28","rank":92},{"name":"NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)","organization":"nvidia","score":1399.1848270977043,"low":1386.2821677480115,"high":1412.0874864473972,"observations":3193,"sourceRank":101,"publishedAt":"2026-10-28","rank":91},{"name":"MiniMax-M2.7","organization":"minimax","score":1398.1916538931569,"low":1392.398609089781,"high":1403.9846986965326,"observations":15890,"sourceRank":102,"publishedAt":"2026-10-28","rank":92},{"name":"GPT-5.4 mini (High)","organization":"openai","score":1397.299194720604,"low":1390.7573592264957,"high":1403.841030214712,"observations":11893,"sourceRank":103,"publishedAt":"2026-10-28","rank":92},{"name":"GPT-5.1 (Medium)","organization":"openai","score":1395.6212231615589,"low":1384.0838346652645,"high":1407.1586116578533,"observations":4891,"sourceRank":104,"publishedAt":"2026-10-28","rank":92},{"name":"Claude Sonnet 4.5 (High, 32K, 20250929)","organization":"anthropic","score":1393.5404164128754,"low":1385.820265198625,"high":1401.260567627126,"observations":13213,"sourceRank":105,"publishedAt":"2026-10-28","rank":93},{"name":"Claude Opus 4.1 (20250805)","organization":"anthropic","score":1390.1558311618264,"low":1379.414439455257,"high":1400.8972228683956,"observations":6904,"sourceRank":106,"publishedAt":"2026-10-28","rank":93},{"name":"MiniMax-M2.5","organization":"minimax","score":1386.1630928790391,"low":1377.8157999917726,"high":1394.510385766306,"observations":7594,"sourceRank":107,"publishedAt":"2026-10-28","rank":95},{"name":"Claude Sonnet 4.5 (20250929)","organization":"anthropic","score":1384.9137217755942,"low":1377.6286711293574,"high":1392.198772421831,"observations":15679,"sourceRank":108,"publishedAt":"2026-10-28","rank":99},{"name":"Gemini 3 Flash (Minimal)","organization":"google","score":1384.4938378264999,"low":1379.2700924573223,"high":1389.7175831956777,"observations":22080,"sourceRank":109,"publishedAt":"2026-10-28","rank":101},{"name":"MiniMax-M2.1 Preview","organization":"minimax","score":1383.9795871670053,"low":1374.4203407549771,"high":1393.5388335790337,"observations":7573,"sourceRank":110,"publishedAt":"2026-10-28","rank":96},{"name":"Grok 4.20 Beta (Reasoning, 0309)","organization":"xai","score":1375.4624441703345,"low":1369.3760049499185,"high":1381.5488833907505,"observations":15404,"sourceRank":111,"publishedAt":"2026-10-28","rank":105},{"name":"Solar Pro 4","organization":"upstage","score":1370.181401834313,"low":1359.8203326464848,"high":1380.5424710221412,"observations":4630,"sourceRank":113,"publishedAt":"2026-10-28","rank":105},{"name":"Gemma 4 31B","organization":"google","score":1368.6624108190852,"low":1362.5336185244823,"high":1374.7912031136882,"observations":15489,"sourceRank":114,"publishedAt":"2026-10-28","rank":109},{"name":"DeepSeek-V3.2 (Thinking)","organization":"deepseek","score":1362.5238258167278,"low":1353.411037219597,"high":1371.6366144138588,"observations":6860,"sourceRank":115,"publishedAt":"2026-10-28","rank":110},{"name":"Qwen3.5-122B-A10B","organization":"alibaba","score":1360.3815376302985,"low":1352.7174219411397,"high":1368.045653319457,"observations":8210,"sourceRank":116,"publishedAt":"2026-10-28","rank":111},{"name":"Gemma 4 26B A4B","organization":"google","score":1358.776588697436,"low":1341.8297253816463,"high":1375.7234520132256,"observations":1494,"sourceRank":117,"publishedAt":"2026-10-28","rank":109},{"name":"Qwen3.5-27B","organization":"alibaba","score":1358.3092755979856,"low":1350.2630402629318,"high":1366.3555109330396,"observations":7767,"sourceRank":118,"publishedAt":"2026-10-28","rank":111},{"name":"Grok 4.3","organization":"xai","score":1357.5695879962777,"low":1351.3313825067055,"high":1363.8077934858497,"observations":14906,"sourceRank":119,"publishedAt":"2026-10-28","rank":111},{"name":"Hy3 preview","organization":"tencent","score":1356.9153594827778,"low":1339.5472368462038,"high":1374.2834821193517,"observations":1444,"sourceRank":120,"publishedAt":"2026-10-28","rank":110},{"name":"Muse Glimmer","organization":"meta","score":1355.0649278889712,"low":1339.4208965245302,"high":1370.7089592534119,"observations":1632,"sourceRank":121,"publishedAt":"2026-10-28","rank":110},{"name":"Laguna M.1","organization":"poolside","score":1349.1775253684623,"low":1339.878910589451,"high":1358.4761401474734,"observations":5359,"sourceRank":122,"publishedAt":"2026-10-28","rank":113},{"name":"GPT-5.1","organization":"openai","score":1341.3437443111054,"low":1332.8565815834122,"high":1349.8309070387988,"observations":10675,"sourceRank":123,"publishedAt":"2026-10-28","rank":117},{"name":"GLM-4.6","organization":"zai","score":1341.1518521405144,"low":1330.338269503539,"high":1351.9654347774897,"observations":6755,"sourceRank":124,"publishedAt":"2026-10-28","rank":115},{"name":"GPT-5.2-Codex","organization":"openai","score":1338.6655694153849,"low":1329.7276823301117,"high":1347.6034565006578,"observations":6705,"sourceRank":125,"publishedAt":"2026-10-28","rank":117},{"name":"GPT-5.1-Codex","organization":"openai","score":1337.1172107840903,"low":1325.5363533865643,"high":1348.6980681816165,"observations":4981,"sourceRank":126,"publishedAt":"2026-10-28","rank":117},{"name":"MiMo-V2-Flash (Non-Thinking)","organization":"xiaomi","score":1330.6239040787611,"low":1320.8578297960016,"high":1340.3899783615207,"observations":5645,"sourceRank":127,"publishedAt":"2026-10-28","rank":118},{"name":"Claude Haiku 4.5 (20251001)","organization":"anthropic","score":1330.3720212251565,"low":1325.4410256175365,"high":1335.3030168327762,"observations":28961,"sourceRank":128,"publishedAt":"2026-10-28","rank":121},{"name":"DeepSeek-V3.2","organization":"deepseek","score":1325.750670059786,"low":1317.7705038556032,"high":1333.7308362639687,"observations":9327,"sourceRank":129,"publishedAt":"2026-10-28","rank":121},{"name":"Kimi K2 Thinking Turbo","organization":"moonshot","score":1321.9150315480917,"low":1314.4529699578302,"high":1329.377093138353,"observations":13045,"sourceRank":130,"publishedAt":"2026-10-28","rank":124},{"name":"Laguna XS.2","organization":"poolside","score":1302.434909213999,"low":1291.6948070810108,"high":1313.1750113469868,"observations":4204,"sourceRank":131,"publishedAt":"2026-10-28","rank":129},{"name":"MiniMax-M2","organization":"minimax","score":1297.1093946778446,"low":1286.1686608007733,"high":1308.050128554916,"observations":6683,"sourceRank":132,"publishedAt":"2026-10-28","rank":129},{"name":"MiMo-V2-Flash (Thinking)","organization":"xiaomi","score":1291.6958938048085,"low":1275.213608944174,"high":1308.1781786654433,"observations":1681,"sourceRank":133,"publishedAt":"2026-10-28","rank":129},{"name":"Qwen3-Coder-480B-A35B-Instruct","organization":"alibaba","score":1274.7527065636266,"low":1266.9566141042742,"high":1282.5487990229792,"observations":12675,"sourceRank":134,"publishedAt":"2026-10-28","rank":131},{"name":"DeepSeek-V3.2-Exp","organization":"deepseek","score":1271.4406409272704,"low":1257.9271142352582,"high":1284.9541676192828,"observations":3968,"sourceRank":135,"publishedAt":"2026-10-28","rank":131},{"name":"Mistral Medium 3.5","organization":"mistral","score":1264.0086408699274,"low":1249.1955815076813,"high":1278.8217002321735,"observations":2299,"sourceRank":136,"publishedAt":"2026-10-28","rank":131},{"name":"Gemini 3.1 Flash-Lite Preview","organization":"google","score":1256.2629544827098,"low":1249.4264821740428,"high":1263.099426791377,"observations":14350,"sourceRank":137,"publishedAt":"2026-10-28","rank":133},{"name":"KAT-Coder-Pro V1","organization":"","score":1255.828952682332,"low":1236.3256198112356,"high":1275.3322855534284,"observations":1503,"sourceRank":138,"publishedAt":"2026-10-28","rank":131},{"name":"Qwen3.5-35B-A3B","organization":"alibaba","score":1254.1583882182388,"low":1236.6992534235849,"high":1271.6175230128924,"observations":1612,"sourceRank":139,"publishedAt":"2026-10-28","rank":132},{"name":"Qwen3.5-Flash","organization":"alibaba","score":1243.693201316261,"low":1224.0257374804935,"high":1263.3606651520286,"observations":1321,"sourceRank":140,"publishedAt":"2026-10-28","rank":133},{"name":"GPT-5.1-Codex-Mini","organization":"openai","score":1243.5470502084045,"low":1221.4993984431512,"high":1265.594701973658,"observations":1154,"sourceRank":141,"publishedAt":"2026-10-28","rank":133},{"name":"Grok 4.1 Fast (Reasoning)","organization":"xai","score":1242.0822790398674,"low":1230.9705942346325,"high":1253.1939638451022,"observations":5473,"sourceRank":142,"publishedAt":"2026-10-28","rank":134},{"name":"Trinity Large Thinking","organization":"","score":1238.030861835541,"low":1218.00968290574,"high":1258.0520407653419,"observations":1352,"sourceRank":143,"publishedAt":"2026-10-28","rank":133},{"name":"Mistral Large 3","organization":"mistral","score":1232.601739542315,"low":1207.1431395008944,"high":1258.0603395837356,"observations":838,"sourceRank":144,"publishedAt":"2026-10-28","rank":133},{"name":"Gemini 2.5 Pro","organization":"google","score":1226.0977652196555,"low":1210.2149916414273,"high":1241.9805387978838,"observations":2724,"sourceRank":145,"publishedAt":"2026-10-28","rank":136},{"name":"Grok 4.1 (Thinking)","organization":"xai","score":1214.468784837361,"low":1189.5875011116016,"high":1239.3500685631204,"observations":961,"sourceRank":146,"publishedAt":"2026-10-28","rank":136},{"name":"Devstral 2","organization":"mistral","score":1197.1289143313095,"low":1176.3948065790933,"high":1217.8630220835257,"observations":1182,"sourceRank":147,"publishedAt":"2026-10-28","rank":142},{"name":"Granite 4.1 8B","organization":"ibm","score":1192.480962451842,"low":1174.0120238461566,"high":1210.9499010575275,"observations":1766,"sourceRank":148,"publishedAt":"2026-10-28","rank":142},{"name":"Mercury 2","organization":"inception-ai","score":1170.3786757696055,"low":1145.8440301608161,"high":1194.9133213783946,"observations":954,"sourceRank":149,"publishedAt":"2026-10-28","rank":144},{"name":"Grok Code Fast 1","organization":"xai","score":1166.345338592527,"low":1138.0838432744106,"high":1194.6068339106434,"observations":789,"sourceRank":150,"publishedAt":"2026-10-28","rank":144},{"name":"Grok 4 Fast (Reasoning)","organization":"xai","score":1159.112594881782,"low":1131.691085348264,"high":1186.5341044152997,"observations":742,"sourceRank":151,"publishedAt":"2026-10-28","rank":145},{"name":"Devstral Medium (2507)","organization":"mistral","score":1071.3821988348811,"low":1040.7727964860776,"high":1101.9916011836847,"observations":842,"sourceRank":152,"publishedAt":"2026-10-28","rank":150}],"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":"e2a18304ba61c943d7bb243730005c2b17fa67bdc3fb450d0e219ee4bf263abd.parquet","sha256":"e2a18304ba61c943d7bb243730005c2b17fa67bdc3fb450d0e219ee4bf263abd","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53/webdev/latest-00000-of-00001.parquet","revision":"8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53","role":"rows"}]},"status":"fresh"}
