{"config":"text_factuality","id":"arena-text-factuality","title":"Text · factuality","category":"Language models","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":[],"rows":[{"name":"Gemini 4 Carbon (High)","organization":"google","score":1521.585410134738,"low":1513.3667061288143,"high":1529.8041141406618,"observations":4403,"sourceRank":1,"publishedAt":"2026-10-28","rank":1},{"name":"Claude Opus 5.5 (High)","organization":"anthropic","score":1508.6768839478725,"low":1502.9830978565276,"high":1514.3706700392174,"observations":11415,"sourceRank":2,"publishedAt":"2026-10-28","rank":1},{"name":"Claude Fable 5.1 (Max)","organization":"anthropic","score":1499.6872570429105,"low":1494.740185797157,"high":1504.634328288664,"observations":17178,"sourceRank":3,"publishedAt":"2026-10-28","rank":2},{"name":"Gemini 4 Argon (High)","organization":"google","score":1499.5393093700945,"low":1494.088506203995,"high":1504.9901125361944,"observations":11889,"sourceRank":4,"publishedAt":"2026-10-28","rank":2},{"name":"Muse Wonder (Max)","organization":"meta","score":1494.3281894689617,"low":1487.977316252489,"high":1500.6790626854345,"observations":7749,"sourceRank":5,"publishedAt":"2026-10-28","rank":3},{"name":"Claude Opus 4.6 (High)","organization":"anthropic","score":1492.6206364725124,"low":1489.9946636735622,"high":1495.2466092714626,"observations":84183,"sourceRank":6,"publishedAt":"2026-10-28","rank":3},{"name":"Claude Opus 5 (Max)","organization":"anthropic","score":1488.3899253060238,"low":1484.6248968502975,"high":1492.1549537617502,"observations":35531,"sourceRank":7,"publishedAt":"2026-10-28","rank":5},{"name":"Claude Opus 4.6","organization":"anthropic","score":1487.3636037987114,"low":1484.7968655827601,"high":1489.9303420146625,"observations":88951,"sourceRank":8,"publishedAt":"2026-10-28","rank":6},{"name":"GPT-5.5 (High)","organization":"openai","score":1485.6946993858064,"low":1482.836395514758,"high":1488.553003256855,"observations":69331,"sourceRank":9,"publishedAt":"2026-10-28","rank":6},{"name":"MiMo-V2.6-Pro","organization":"xiaomi","score":1484.500529278321,"low":1476.524155185843,"high":1492.476903370799,"observations":4037,"sourceRank":10,"publishedAt":"2026-10-28","rank":5},{"name":"GPT-5.4 (High)","organization":"openai","score":1484.2552745842195,"low":1481.3072036742658,"high":1487.2033454941734,"observations":64664,"sourceRank":11,"publishedAt":"2026-10-28","rank":7},{"name":"Claude Fable 5 (High)","organization":"anthropic","score":1482.7252484146788,"low":1479.4170776396372,"high":1486.0334191897202,"observations":45341,"sourceRank":12,"publishedAt":"2026-10-28","rank":7},{"name":"GPT-5.5","organization":"openai","score":1481.82937808558,"low":1479.00543873967,"high":1484.65331743149,"observations":70892,"sourceRank":13,"publishedAt":"2026-10-28","rank":8},{"name":"Gemini 3 Pro","organization":"google","score":1481.2423640533875,"low":1477.8334515142537,"high":1484.6512765925213,"observations":41121,"sourceRank":14,"publishedAt":"2026-10-28","rank":8},{"name":"Qwen3.7-Max-Preview","organization":"alibaba","score":1479.6414572900849,"low":1470.8617185138291,"high":1488.4211960663408,"observations":3932,"sourceRank":15,"publishedAt":"2026-10-28","rank":6},{"name":"Muse Spark 1.3 (Max)","organization":"meta","score":1479.0976183377575,"low":1474.576738124158,"high":1483.6184985513569,"observations":22134,"sourceRank":16,"publishedAt":"2026-10-28","rank":9},{"name":"Muse Spark 1.2 (xHigh)","organization":"meta","score":1479.0311309903066,"low":1473.5623633426728,"high":1484.4998986379405,"observations":11724,"sourceRank":17,"publishedAt":"2026-10-28","rank":9},{"name":"Claude Opus 5 (High)","organization":"anthropic","score":1478.2463912748244,"low":1475.3507143000018,"high":1481.142068249647,"observations":73167,"sourceRank":18,"publishedAt":"2026-10-28","rank":11},{"name":"Claude Opus 4.7 (High)","organization":"anthropic","score":1477.3835732801695,"low":1474.3654419392242,"high":1480.4017046211147,"observations":65015,"sourceRank":19,"publishedAt":"2026-10-28","rank":11},{"name":"Gemini 3.5 Flash (High)","organization":"google","score":1477.1554098803163,"low":1473.834359539686,"high":1480.4764602209464,"observations":48376,"sourceRank":20,"publishedAt":"2026-10-28","rank":11},{"name":"GPT-5.6 Sol (xHigh)","organization":"openai","score":1476.3986819228764,"low":1473.070379010414,"high":1479.7269848353392,"observations":43796,"sourceRank":21,"publishedAt":"2026-10-28","rank":11},{"name":"Gemini 3.7 Flash (High)","organization":"google","score":1475.7612738640719,"low":1471.8802128766686,"high":1479.6423348514752,"observations":32289,"sourceRank":22,"publishedAt":"2026-10-28","rank":11},{"name":"Claude Sonnet 5.5 (xHigh)","organization":"anthropic","score":1475.5673384524132,"low":1469.7852458728614,"high":1481.349431031965,"observations":10033,"sourceRank":23,"publishedAt":"2026-10-28","rank":10},{"name":"Claude Opus 4.7","organization":"anthropic","score":1475.543843481287,"low":1472.472248357954,"high":1478.6154386046203,"observations":66042,"sourceRank":24,"publishedAt":"2026-10-28","rank":13},{"name":"GPT-5.4","organization":"openai","score":1474.8511789658708,"low":1471.9522963706072,"high":1477.7500615611343,"observations":67730,"sourceRank":25,"publishedAt":"2026-10-28","rank":14},{"name":"Qwen3.5-Max-Preview","organization":"alibaba","score":1474.5883851863553,"low":1470.2353299036665,"high":1478.9414404690438,"observations":22544,"sourceRank":26,"publishedAt":"2026-10-28","rank":13},{"name":"Gemini 3.8 Flash (High)","organization":"google","score":1471.999695318515,"low":1468.2424630054468,"high":1475.7569276315835,"observations":47803,"sourceRank":27,"publishedAt":"2026-10-28","rank":15},{"name":"Gemini 3.6 Flash (High)","organization":"google","score":1471.8834448872242,"low":1468.2596037527064,"high":1475.507286021742,"observations":36028,"sourceRank":28,"publishedAt":"2026-10-28","rank":15},{"name":"Gemini 3.1 Pro Preview","organization":"google","score":1471.681102473267,"low":1469.4173555205043,"high":1473.9448494260294,"observations":132208,"sourceRank":29,"publishedAt":"2026-10-28","rank":18},{"name":"Kimi K3 (Max)","organization":"moonshot","score":1471.512844599586,"low":1468.0131135711244,"high":1475.0125756280474,"observations":36780,"sourceRank":30,"publishedAt":"2026-10-28","rank":16},{"name":"Qwen3.8-Max","organization":"alibaba","score":1471.1131041117414,"low":1467.103881859301,"high":1475.1223263641818,"observations":31915,"sourceRank":31,"publishedAt":"2026-10-28","rank":16},{"name":"Claude Opus 4.8 (High)","organization":"anthropic","score":1469.8134836095273,"low":1466.7311395791944,"high":1472.8958276398603,"observations":63939,"sourceRank":32,"publishedAt":"2026-10-28","rank":21},{"name":"DeepSeek-V4.1-Flash-20260910 (Max)","organization":"deepseek","score":1468.9852148895247,"low":1463.8192373647732,"high":1474.1511924142762,"observations":13657,"sourceRank":33,"publishedAt":"2026-10-28","rank":18},{"name":"GPT-6 Luna (Max)","organization":"openai","score":1468.7054783447384,"low":1465.481370395562,"high":1471.9295862939146,"observations":86478,"sourceRank":34,"publishedAt":"2026-10-28","rank":23},{"name":"GPT-5.6 Terra (xHigh)","organization":"openai","score":1468.6812021842547,"low":1465.4727445117437,"high":1471.8896598567658,"observations":48166,"sourceRank":35,"publishedAt":"2026-10-28","rank":23},{"name":"Muse Spark","organization":"meta","score":1467.631515883443,"low":1462.1957888204793,"high":1473.0672429464066,"observations":14122,"sourceRank":36,"publishedAt":"2026-10-28","rank":21},{"name":"Gemini 3 Flash","organization":"google","score":1467.4990310300334,"low":1463.5522765882176,"high":1471.4457854718494,"observations":30651,"sourceRank":37,"publishedAt":"2026-10-28","rank":24},{"name":"Gemini 3.5 Flash (Medium)","organization":"google","score":1467.4855449615793,"low":1464.145659623262,"high":1470.8254302998967,"observations":47196,"sourceRank":38,"publishedAt":"2026-10-28","rank":25},{"name":"GPT-6 Astra (Max)","organization":"openai","score":1466.5224195807928,"low":1461.5145102302367,"high":1471.5303289313488,"observations":15038,"sourceRank":39,"publishedAt":"2026-10-28","rank":24},{"name":"GLM-5.3 (Max)","organization":"zai","score":1466.11196945312,"low":1461.9326355949956,"high":1470.2913033112443,"observations":26606,"sourceRank":40,"publishedAt":"2026-10-28","rank":25},{"name":"GPT-6.1 Sol (Max)","organization":"openai","score":1465.556737221429,"low":1459.559368125661,"high":1471.5541063171972,"observations":9367,"sourceRank":41,"publishedAt":"2026-10-28","rank":24},{"name":"Grok 4.5","organization":"xai","score":1465.1934568686472,"low":1461.7487487962794,"high":1468.6381649410148,"observations":39801,"sourceRank":42,"publishedAt":"2026-10-28","rank":28},{"name":"Claude Opus 4.8","organization":"anthropic","score":1464.7280992390686,"low":1461.6982431164172,"high":1467.75795536172,"observations":65075,"sourceRank":43,"publishedAt":"2026-10-28","rank":31},{"name":"MiMo-V2.5-Pro","organization":"xiaomi","score":1464.3256731385068,"low":1461.5307614498647,"high":1467.1205848271488,"observations":77666,"sourceRank":44,"publishedAt":"2026-10-28","rank":31},{"name":"GLM-5.3-Flash","organization":"zai","score":1463.788059382684,"low":1460.0097351606237,"high":1467.5663836047445,"observations":41642,"sourceRank":45,"publishedAt":"2026-10-28","rank":31},{"name":"GLM-5.2 (Max)","organization":"zai","score":1462.5992663491702,"low":1459.3682240109092,"high":1465.8303086874314,"observations":53702,"sourceRank":46,"publishedAt":"2026-10-28","rank":33},{"name":"Muse Spark 1.1","organization":"meta","score":1462.4390990353086,"low":1458.9648983399986,"high":1465.9132997306185,"observations":46354,"sourceRank":47,"publishedAt":"2026-10-28","rank":33},{"name":"Gemini 2.5 Pro","organization":"google","score":1461.742743642856,"low":1459.100206987643,"high":1464.385280298069,"observations":69844,"sourceRank":48,"publishedAt":"2026-10-28","rank":35},{"name":"Claude Sonnet 4.6","organization":"anthropic","score":1460.4823389659784,"low":1457.6045544095336,"high":1463.3601235224235,"observations":70653,"sourceRank":49,"publishedAt":"2026-10-28","rank":38},{"name":"GPT-5.6 Luna (xHigh)","organization":"openai","score":1460.4696854974995,"low":1457.0715142434074,"high":1463.8678567515917,"observations":41317,"sourceRank":50,"publishedAt":"2026-10-28","rank":36},{"name":"Claude Opus 4.5 (20251101)","organization":"anthropic","score":1459.1080106979095,"low":1456.3780804064852,"high":1461.8379409893337,"observations":71687,"sourceRank":51,"publishedAt":"2026-10-28","rank":40},{"name":"Claude Opus 4.5 (High, 32K, 20251101)","organization":"anthropic","score":1458.9201223473071,"low":1455.4453438650519,"high":1462.3949008295626,"observations":36607,"sourceRank":52,"publishedAt":"2026-10-28","rank":38},{"name":"GPT-5.1 (High)","organization":"openai","score":1458.1003423447453,"low":1454.7893879524818,"high":1461.4112967370088,"observations":40765,"sourceRank":53,"publishedAt":"2026-10-28","rank":44},{"name":"Grok 4.20 Multi-Agent Beta (0309)","organization":"xai","score":1457.0108795862704,"low":1453.9856152064726,"high":1460.0361439660685,"observations":64827,"sourceRank":54,"publishedAt":"2026-10-28","rank":44},{"name":"Kimi K2.6","organization":"moonshot","score":1456.2258173219805,"low":1452.5566810936637,"high":1459.8949535502973,"observations":39929,"sourceRank":55,"publishedAt":"2026-10-28","rank":45},{"name":"ERNIE 5.1","organization":"baidu","score":1455.9871073733075,"low":1452.1500749651134,"high":1459.8241397815018,"observations":39414,"sourceRank":56,"publishedAt":"2026-10-28","rank":45},{"name":"GLM-5.1","organization":"zai","score":1455.9283164882315,"low":1452.9808122470374,"high":1458.8758207294256,"observations":66633,"sourceRank":57,"publishedAt":"2026-10-28","rank":49},{"name":"Grok 4.20 Beta (Reasoning, 0309)","organization":"xai","score":1455.6550753503377,"low":1452.608086943774,"high":1458.7020637569012,"observations":66343,"sourceRank":58,"publishedAt":"2026-10-28","rank":49},{"name":"DeepSeek-V4-Pro","organization":"deepseek","score":1454.6498315815847,"low":1451.5189283817192,"high":1457.7807347814505,"observations":57532,"sourceRank":59,"publishedAt":"2026-10-28","rank":49},{"name":"DeepSeek-V4-Pro (High, 20260813)","organization":"deepseek","score":1453.9861102584778,"low":1448.49327755831,"high":1459.4789429586456,"observations":9787,"sourceRank":60,"publishedAt":"2026-10-28","rank":46},{"name":"Qwen3.7-Plus","organization":"alibaba","score":1452.4071217241035,"low":1448.9178525676255,"high":1455.8963908805817,"observations":42011,"sourceRank":61,"publishedAt":"2026-10-28","rank":52},{"name":"Grok 4.20 Beta 1","organization":"xai","score":1452.36998558823,"low":1448.2490829193807,"high":1456.4908882570794,"observations":27693,"sourceRank":62,"publishedAt":"2026-10-28","rank":51},{"name":"Qwen3.6-Max-Preview","organization":"alibaba","score":1452.3540593625828,"low":1444.7622763186123,"high":1459.9458424065533,"observations":5419,"sourceRank":63,"publishedAt":"2026-10-28","rank":45},{"name":"Claude Sonnet 5 (High)","organization":"anthropic","score":1452.1672978024244,"low":1448.9214124838838,"high":1455.4131831209647,"observations":52952,"sourceRank":64,"publishedAt":"2026-10-28","rank":53},{"name":"Inkling","organization":"thinky","score":1451.716647233062,"low":1448.3352098915386,"high":1455.0980845745855,"observations":45472,"sourceRank":65,"publishedAt":"2026-10-28","rank":53},{"name":"amazon-nova-experimental-chat (26-02-10)","organization":"amazon","score":1451.5990061704665,"low":1442.8010295867032,"high":1460.3969827542296,"observations":3523,"sourceRank":66,"publishedAt":"2026-10-28","rank":44},{"name":"GLM-5","organization":"zai","score":1451.5303023561073,"low":1447.6924091330045,"high":1455.3681955792101,"observations":29021,"sourceRank":67,"publishedAt":"2026-10-28","rank":53},{"name":"Gemini 3 Flash (Minimal)","organization":"google","score":1451.152582897075,"low":1448.616460499691,"high":1453.6887052944592,"observations":90228,"sourceRank":68,"publishedAt":"2026-10-28","rank":55},{"name":"MiMo-V2.6-Flash","organization":"xiaomi","score":1450.728860132173,"low":1445.554257268365,"high":1455.9034629959808,"observations":15312,"sourceRank":69,"publishedAt":"2026-10-28","rank":52},{"name":"GPT-5.2 Chat (20260210)","organization":"openai","score":1450.4959509394846,"low":1446.8861275383895,"high":1454.1057743405797,"observations":35651,"sourceRank":70,"publishedAt":"2026-10-28","rank":54},{"name":"Grok 4.6 (High)","organization":"xai","score":1450.0862928445545,"low":1446.3591798602629,"high":1453.8134058288458,"observations":33824,"sourceRank":71,"publishedAt":"2026-10-28","rank":55},{"name":"Gemma 4 31B","organization":"google","score":1449.3377203064383,"low":1442.4719930435745,"high":1456.2034475693022,"observations":6135,"sourceRank":72,"publishedAt":"2026-10-28","rank":52},{"name":"Claude Sonnet 4.5 (20250929)","organization":"anthropic","score":1448.5189780697515,"low":1445.972942649897,"high":1451.0650134896061,"observations":77498,"sourceRank":73,"publishedAt":"2026-10-28","rank":60},{"name":"Gemini 3.5 Flash-Lite","organization":"google","score":1447.580494786147,"low":1443.8736174723206,"high":1451.2873720999733,"observations":35740,"sourceRank":74,"publishedAt":"2026-10-28","rank":60},{"name":"DeepSeek-V4-Pro Preview (High)","organization":"deepseek","score":1447.4218515820812,"low":1444.23264589734,"high":1450.6110572668224,"observations":54811,"sourceRank":75,"publishedAt":"2026-10-28","rank":60},{"name":"Step 5 Preview","organization":"stepfun","score":1447.1624091214642,"low":1441.6240104199806,"high":1452.7008078229478,"observations":11355,"sourceRank":76,"publishedAt":"2026-10-28","rank":56},{"name":"GLM-4.6","organization":"zai","score":1446.8297359794094,"low":1442.9505077552665,"high":1450.7089642035523,"observations":28684,"sourceRank":77,"publishedAt":"2026-10-28","rank":60},{"name":"DeepSeek-V3.2-Exp (Thinking)","organization":"deepseek","score":1446.4524690389417,"low":1435.7523725857675,"high":1457.1525654921156,"observations":2523,"sourceRank":78,"publishedAt":"2026-10-28","rank":50},{"name":"GPT-5.4 mini (High)","organization":"openai","score":1446.3034701090373,"low":1443.3153722930672,"high":1449.2915679250073,"observations":63316,"sourceRank":79,"publishedAt":"2026-10-28","rank":60},{"name":"Claude Sonnet 4.5 (High, 32K, 20250929)","organization":"anthropic","score":1446.2279636765907,"low":1443.6597934511965,"high":1448.7961339019848,"observations":74727,"sourceRank":80,"publishedAt":"2026-10-28","rank":62},{"name":"Hy3","organization":"tencent","score":1445.7379061850843,"low":1440.7413183551623,"high":1450.7344940150062,"observations":13840,"sourceRank":81,"publishedAt":"2026-10-28","rank":60},{"name":"ERNIE 5.0 (0110)","organization":"baidu","score":1445.2163560770446,"low":1441.6652981817326,"high":1448.7674139723567,"observations":35909,"sourceRank":82,"publishedAt":"2026-10-28","rank":62},{"name":"Kimi K2.5 (Thinking)","organization":"moonshot","score":1444.8415581602603,"low":1442.1075627225491,"high":1447.5755535979715,"observations":74317,"sourceRank":83,"publishedAt":"2026-10-28","rank":67},{"name":"Gemma 4 26B A4B","organization":"google","score":1444.5426839031836,"low":1437.6537052783822,"high":1451.431662527985,"observations":6088,"sourceRank":84,"publishedAt":"2026-10-28","rank":60},{"name":"Qwen3.5-397B-A17B","organization":"alibaba","score":1444.3871683506661,"low":1441.9181896184714,"high":1446.8561470828608,"observations":97351,"sourceRank":85,"publishedAt":"2026-10-28","rank":68},{"name":"GPT-5.1","organization":"openai","score":1443.928748414397,"low":1440.6715829925383,"high":1447.1859138362556,"observations":43458,"sourceRank":86,"publishedAt":"2026-10-28","rank":67},{"name":"GLM-4.7","organization":"zai","score":1443.8717907491957,"low":1438.1995938432824,"high":1449.5439876551088,"observations":11796,"sourceRank":87,"publishedAt":"2026-10-28","rank":60},{"name":"ChatGPT-4o Latest (20250326)","organization":"openai","score":1443.7390566169809,"low":1440.3466223015055,"high":1447.131490932456,"observations":40465,"sourceRank":88,"publishedAt":"2026-10-28","rank":67},{"name":"MiMo-V2-Pro","organization":"xiaomi","score":1443.2389649005952,"low":1439.04589807335,"high":1447.4320317278405,"observations":25385,"sourceRank":89,"publishedAt":"2026-10-28","rank":67},{"name":"GPT-5.5 Instant","organization":"openai","score":1442.7613495603573,"low":1438.5875921862678,"high":1446.9351069344468,"observations":27128,"sourceRank":90,"publishedAt":"2026-10-28","rank":67},{"name":"ERNIE-5.0-Preview (1203)","organization":"baidu","score":1441.9325175900392,"low":1435.7677332936848,"high":1448.0973018863936,"observations":9545,"sourceRank":91,"publishedAt":"2026-10-28","rank":66},{"name":"GPT-5.2","organization":"openai","score":1441.5668613661435,"low":1438.9930893094306,"high":1444.1406334228566,"observations":83183,"sourceRank":92,"publishedAt":"2026-10-28","rank":73},{"name":"Qwen3-Max-Preview","organization":"alibaba","score":1441.3719488589427,"low":1434.6369845694096,"high":1448.1069131484755,"observations":7567,"sourceRank":93,"publishedAt":"2026-10-28","rank":66},{"name":"GPT-5.2 (High)","organization":"openai","score":1440.9090735026814,"low":1437.8131380138134,"high":1444.0050089915492,"observations":49087,"sourceRank":94,"publishedAt":"2026-10-28","rank":73},{"name":"Beam 1.0 501B A23B","organization":"reflection","score":1440.8509672227542,"low":1432.9579235706963,"high":1448.744010874812,"observations":4233,"sourceRank":95,"publishedAt":"2026-10-28","rank":62},{"name":"GLM-5V-Turbo","organization":"zai","score":1440.776862369954,"low":1435.1074108050752,"high":1446.446313934833,"observations":10476,"sourceRank":96,"publishedAt":"2026-10-28","rank":68},{"name":"GPT-6 Sol (Max)","organization":"openai","score":1439.7856719354993,"low":1434.7529670699514,"high":1444.8183768010472,"observations":15807,"sourceRank":97,"publishedAt":"2026-10-28","rank":71},{"name":"ERNIE-5.0-Preview (1022)","organization":"baidu","score":1439.5408963236578,"low":1430.872794716449,"high":1448.2089979308664,"observations":4017,"sourceRank":98,"publishedAt":"2026-10-28","rank":66},{"name":"MiMo-V2.5","organization":"xiaomi","score":1438.813930244841,"low":1435.3738827018078,"high":1442.2539777878742,"observations":47279,"sourceRank":99,"publishedAt":"2026-10-28","rank":79},{"name":"DeepSeek-V4-Flash","organization":"deepseek","score":1438.7755020588872,"low":1435.4749809142972,"high":1442.076023203477,"observations":51876,"sourceRank":100,"publishedAt":"2026-10-28","rank":80},{"name":"Qwen3.6-Plus","organization":"alibaba","score":1437.43937831819,"low":1434.0022983281212,"high":1440.8764583082586,"observations":48068,"sourceRank":101,"publishedAt":"2026-10-28","rank":83},{"name":"DeepSeek-V3.2","organization":"deepseek","score":1436.5364065134613,"low":1433.3635495033882,"high":1439.7092635235344,"observations":47123,"sourceRank":102,"publishedAt":"2026-10-28","rank":86},{"name":"Qwen3.8-27B","organization":"alibaba","score":1436.1361626156697,"low":1431.9207487160907,"high":1440.3515765152488,"observations":27779,"sourceRank":103,"publishedAt":"2026-10-28","rank":85},{"name":"Gemini 2.5 Flash","organization":"google","score":1436.0276868271442,"low":1433.4628903753778,"high":1438.5924832789108,"observations":70533,"sourceRank":104,"publishedAt":"2026-10-28","rank":88},{"name":"DeepSeek-V3.2-Exp","organization":"deepseek","score":1435.985335168823,"low":1430.0780607290012,"high":1441.8926096086448,"observations":11902,"sourceRank":105,"publishedAt":"2026-10-28","rank":81},{"name":"MiMo-V2-Omni","organization":"xiaomi","score":1435.287240312845,"low":1430.551913762732,"high":1440.0225668629578,"observations":20572,"sourceRank":106,"publishedAt":"2026-10-28","rank":86},{"name":"Claude Opus 4.1 (20250805)","organization":"anthropic","score":1434.9232910469534,"low":1431.5991569775003,"high":1438.2474251164065,"observations":41534,"sourceRank":107,"publishedAt":"2026-10-28","rank":89},{"name":"Grok 4.7 (xHigh)","organization":"xai","score":1434.4943353878352,"low":1429.570891129781,"high":1439.4177796458894,"observations":16442,"sourceRank":108,"publishedAt":"2026-10-28","rank":86},{"name":"Mistral Large 3","organization":"mistral","score":1434.1365154669438,"low":1431.7210034718962,"high":1436.5520274619914,"observations":87371,"sourceRank":109,"publishedAt":"2026-10-28","rank":92},{"name":"Grok 4.1 (Thinking)","organization":"xai","score":1434.0439842483283,"low":1431.1223160904572,"high":1436.9656524061995,"observations":65534,"sourceRank":110,"publishedAt":"2026-10-28","rank":92},{"name":"MiniMax-M3","organization":"minimax","score":1433.9890639016808,"low":1430.975524347091,"high":1437.0026034562707,"observations":68611,"sourceRank":111,"publishedAt":"2026-10-28","rank":92},{"name":"DeepSeek-V4-Flash Preview (High)","organization":"deepseek","score":1433.5402351598668,"low":1430.1213089880137,"high":1436.9591613317198,"observations":51698,"sourceRank":112,"publishedAt":"2026-10-28","rank":92},{"name":"Mistral Large 4","organization":"mistral","score":1433.305154293928,"low":1427.8701021881511,"high":1438.7402063997044,"observations":12066,"sourceRank":113,"publishedAt":"2026-10-28","rank":88},{"name":"Claude Opus 4.1 (Thinking 16K, 20250805)","organization":"anthropic","score":1433.1590553434705,"low":1429.092954219797,"high":1437.2251564671437,"observations":25935,"sourceRank":114,"publishedAt":"2026-10-28","rank":92},{"name":"Gemini 3.1 Flash-Lite Preview","organization":"google","score":1432.8127588449756,"low":1429.7579454258464,"high":1435.8675722641049,"observations":63927,"sourceRank":115,"publishedAt":"2026-10-28","rank":92},{"name":"DeepSeek-V3.2 (Thinking)","organization":"deepseek","score":1432.1823402286104,"low":1428.9314073809785,"high":1435.4332730762424,"observations":41144,"sourceRank":116,"publishedAt":"2026-10-28","rank":95},{"name":"NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)","organization":"nvidia","score":1431.6040565784454,"low":1425.4752723006359,"high":1437.7328408562548,"observations":11563,"sourceRank":117,"publishedAt":"2026-10-28","rank":91},{"name":"Grok 4.1","organization":"xai","score":1431.0004089613703,"low":1428.1261063824768,"high":1433.874711540264,"observations":67654,"sourceRank":118,"publishedAt":"2026-10-28","rank":100},{"name":"Qwen3-235B-A22B-Instruct (2507)","organization":"alibaba","score":1430.7630126824047,"low":1428.1040407210014,"high":1433.4219846438077,"observations":66630,"sourceRank":119,"publishedAt":"2026-10-28","rank":101},{"name":"Mistral Medium 3.5","organization":"mistral","score":1430.0000400205877,"low":1424.1994928613015,"high":1435.800587179874,"observations":11729,"sourceRank":120,"publishedAt":"2026-10-28","rank":92},{"name":"Kimi K2.5 (Instant)","organization":"moonshot","score":1428.8204522408676,"low":1422.7835544587767,"high":1434.8573500229581,"observations":8250,"sourceRank":121,"publishedAt":"2026-10-28","rank":97},{"name":"LongCat-Flash-Chat Exp (2602)","organization":"meituan","score":1428.6927515976618,"low":1424.6225291716219,"high":1432.7629740237016,"observations":29163,"sourceRank":122,"publishedAt":"2026-10-28","rank":103},{"name":"Mistral Medium 3.1 (2508)","organization":"mistral","score":1428.6859796921824,"low":1426.01731558407,"high":1431.3546438002948,"observations":68688,"sourceRank":123,"publishedAt":"2026-10-28","rank":106},{"name":"Qwen3.5-122B-A10B","organization":"alibaba","score":1427.6084999782863,"low":1423.7576747238354,"high":1431.459325232737,"observations":29517,"sourceRank":124,"publishedAt":"2026-10-28","rank":106},{"name":"Grok 4.3","organization":"xai","score":1426.7920139679495,"low":1423.9158489540307,"high":1429.6681789818683,"observations":71249,"sourceRank":125,"publishedAt":"2026-10-28","rank":113},{"name":"Inkling-Small","organization":"thinky","score":1425.6452985365283,"low":1421.9035839058158,"high":1429.3870131672406,"observations":36999,"sourceRank":126,"publishedAt":"2026-10-28","rank":114},{"name":"Gemini 2.5 Flash Preview (09-2025)","organization":"google","score":1424.1720172361431,"low":1419.8365582943322,"high":1428.507476177954,"observations":23417,"sourceRank":127,"publishedAt":"2026-10-28","rank":116},{"name":"NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)","organization":"nvidia","score":1424.0222146715516,"low":1416.2917863905382,"high":1431.752642952565,"observations":4178,"sourceRank":128,"publishedAt":"2026-10-28","rank":104},{"name":"amazon-nova-experimental-chat (12-10)","organization":"amazon","score":1423.7567351011362,"low":1414.5569374720144,"high":1432.956532730258,"observations":3549,"sourceRank":129,"publishedAt":"2026-10-28","rank":103},{"name":"Kimi K2 Thinking Turbo","organization":"moonshot","score":1422.917369176638,"low":1420.1195402550197,"high":1425.7151980982562,"observations":62351,"sourceRank":130,"publishedAt":"2026-10-28","rank":120},{"name":"MiniMax-M2.7","organization":"minimax","score":1422.2193176539183,"low":1419.538515233569,"high":1424.9001200742675,"observations":89123,"sourceRank":131,"publishedAt":"2026-10-28","rank":121},{"name":"MiMo-V2-Flash (Non-Thinking)","organization":"xiaomi","score":1421.7031540109342,"low":1418.548999437526,"high":1424.8573085843425,"observations":47349,"sourceRank":132,"publishedAt":"2026-10-28","rank":121},{"name":"GPT-5 Chat","organization":"openai","score":1421.5991299403652,"low":1414.9913021980437,"high":1428.2069576826866,"observations":7764,"sourceRank":133,"publishedAt":"2026-10-28","rank":116},{"name":"GPT-5 (High)","organization":"openai","score":1420.4183934247822,"low":1413.6032563151634,"high":1427.2335305344006,"observations":6923,"sourceRank":134,"publishedAt":"2026-10-28","rank":119},{"name":"Dola Seed 2.0 Pro","organization":"bytedance","score":1419.8586595857073,"low":1416.8591900358012,"high":1422.8581291356134,"observations":78771,"sourceRank":135,"publishedAt":"2026-10-28","rank":125},{"name":"Qwen3.5-27B","organization":"alibaba","score":1419.3421261079632,"low":1415.4587557042016,"high":1423.2254965117247,"observations":28461,"sourceRank":136,"publishedAt":"2026-10-28","rank":125},{"name":"Claude Haiku 5.5 (High)","organization":"anthropic","score":1419.0822601602135,"low":1412.6847134208333,"high":1425.479806899594,"observations":7890,"sourceRank":137,"publishedAt":"2026-10-28","rank":120},{"name":"Claude Haiku 4.5 (20251001)","organization":"anthropic","score":1418.4569367380825,"low":1416.433827618727,"high":1420.480045857438,"observations":147416,"sourceRank":138,"publishedAt":"2026-10-28","rank":127},{"name":"Qwen3-Next-80B-A3B-Instruct","organization":"alibaba","score":1418.2974309829663,"low":1411.633750257141,"high":1424.9611117087916,"observations":7740,"sourceRank":139,"publishedAt":"2026-10-28","rank":121},{"name":"Grok 4 (0709)","organization":"xai","score":1418.0560313237554,"low":1412.1418203283552,"high":1423.9702423191557,"observations":10438,"sourceRank":140,"publishedAt":"2026-10-28","rank":123},{"name":"GPT-5.3 Chat","organization":"openai","score":1417.4487869263994,"low":1413.6963745591465,"high":1421.2011992936525,"observations":34113,"sourceRank":141,"publishedAt":"2026-10-28","rank":127},{"name":"Grok 4 Fast (Reasoning)","organization":"xai","score":1417.0459989572087,"low":1411.095273185817,"high":1422.9967247286006,"observations":10657,"sourceRank":142,"publishedAt":"2026-10-28","rank":125},{"name":"GPT-5.4 nano (High)","organization":"openai","score":1416.8060258326213,"low":1413.8013754405808,"high":1419.8106762246616,"observations":62208,"sourceRank":143,"publishedAt":"2026-10-28","rank":129},{"name":"Step-3.5-Flash","organization":"stepfun","score":1416.0650446233642,"low":1413.065175434687,"high":1419.0649138120416,"observations":59956,"sourceRank":144,"publishedAt":"2026-10-28","rank":130},{"name":"amazon-nova-experimental-chat (11-10)","organization":"amazon","score":1414.8471905447936,"low":1410.8627590324295,"high":1418.8316220571578,"observations":25511,"sourceRank":145,"publishedAt":"2026-10-28","rank":130},{"name":"Qwen3-VL-235B-A22B-Instruct","organization":"alibaba","score":1414.3417353328887,"low":1396.7219927958631,"high":1431.961477869914,"observations":3040,"sourceRank":146,"publishedAt":"2026-10-28","rank":103},{"name":"Solar Pro 4","organization":"upstage","score":1414.3150535331652,"low":1410.0164842383676,"high":1418.6136228279624,"observations":26159,"sourceRank":147,"publishedAt":"2026-10-28","rank":130},{"name":"Qwen3.5-Flash","organization":"alibaba","score":1413.6078920398788,"low":1410.5202353264046,"high":1416.6955487533533,"observations":61569,"sourceRank":148,"publishedAt":"2026-10-28","rank":132},{"name":"Grok 4.1 Fast (Reasoning)","organization":"xai","score":1413.3751075061048,"low":1410.4120238111357,"high":1416.3381912010739,"observations":56561,"sourceRank":149,"publishedAt":"2026-10-28","rank":133},{"name":"Hy3 preview","organization":"tencent","score":1411.973898824742,"low":1405.0784490520418,"high":1418.869348597442,"observations":6866,"sourceRank":150,"publishedAt":"2026-10-28","rank":130},{"name":"MiniMax-M2.1 Preview","organization":"minimax","score":1410.534222022454,"low":1405.7372672968763,"high":1415.3311767480316,"observations":16776,"sourceRank":151,"publishedAt":"2026-10-28","rank":135},{"name":"MiMo-V2-Flash (Thinking)","organization":"xiaomi","score":1409.1767254241613,"low":1403.4601268183555,"high":1414.8933240299668,"observations":11049,"sourceRank":152,"publishedAt":"2026-10-28","rank":136},{"name":"GPT-4.1 (2025-04-14)","organization":"openai","score":1407.4792197568727,"low":1400.8955714506742,"high":1414.0628680630714,"observations":7877,"sourceRank":153,"publishedAt":"2026-10-28","rank":137},{"name":"Qwen3.5-35B-A3B","organization":"alibaba","score":1407.0811380111736,"low":1403.2518919293234,"high":1410.910384093024,"observations":30222,"sourceRank":154,"publishedAt":"2026-10-28","rank":145},{"name":"Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)","organization":"google","score":1406.3972727599876,"low":1402.928583580729,"high":1409.865961939246,"observations":37558,"sourceRank":155,"publishedAt":"2026-10-28","rank":149},{"name":"o3 (2025-04-16)","organization":"openai","score":1404.1385115299727,"low":1397.512757771984,"high":1410.7642652879613,"observations":7558,"sourceRank":156,"publishedAt":"2026-10-28","rank":146},{"name":"Kimi K2 Preview (0905)","organization":"moonshot","score":1402.2956657461798,"low":1387.920299416571,"high":1416.6710320757888,"observations":1453,"sourceRank":157,"publishedAt":"2026-10-28","rank":132},{"name":"amazon-nova-experimental-chat (26-01-10)","organization":"amazon","score":1402.2596534025326,"low":1393.4191542240903,"high":1411.100152580975,"observations":3534,"sourceRank":158,"publishedAt":"2026-10-28","rank":144},{"name":"Muse Glimmer","organization":"meta","score":1401.8418389201609,"low":1393.4614425010168,"high":1410.222235339305,"observations":3884,"sourceRank":159,"publishedAt":"2026-10-28","rank":148},{"name":"Qwen3-Coder-480B-A35B-Instruct","organization":"alibaba","score":1399.801789269592,"low":1382.3509482955583,"high":1417.2526302436258,"observations":3444,"sourceRank":160,"publishedAt":"2026-10-28","rank":131},{"name":"amazon-nova-experimental-chat (10-20)","organization":"amazon","score":1399.2681496730625,"low":1393.4024824202722,"high":1405.1338169258524,"observations":11198,"sourceRank":161,"publishedAt":"2026-10-28","rank":150},{"name":"GLM-4.5-Air","organization":"zai","score":1394.1053237959795,"low":1387.3104419431265,"high":1400.9002056488328,"observations":7272,"sourceRank":162,"publishedAt":"2026-10-28","rank":154},{"name":"GPT-5 mini (High)","organization":"openai","score":1393.4304802911795,"low":1386.546202369471,"high":1400.314758212888,"observations":6888,"sourceRank":163,"publishedAt":"2026-10-28","rank":155},{"name":"GLM-4.6V","organization":"zai","score":1391.0488209125963,"low":1380.43184996794,"high":1401.6657918572523,"observations":2515,"sourceRank":164,"publishedAt":"2026-10-28","rank":154},{"name":"NVIDIA-Nemotron-3-Super-120B-A12B","organization":"nvidia","score":1389.1843089826027,"low":1382.2824816789862,"high":1396.0861362862195,"observations":7843,"sourceRank":165,"publishedAt":"2026-10-28","rank":157},{"name":"MiniMax-M2.5","organization":"minimax","score":1385.0086362085779,"low":1381.5126082003908,"high":1388.504664216765,"observations":42435,"sourceRank":166,"publishedAt":"2026-10-28","rank":160},{"name":"gpt-oss-120b","organization":"openai","score":1384.4836730866668,"low":1377.8362388074706,"high":1391.1311073658628,"observations":7393,"sourceRank":167,"publishedAt":"2026-10-28","rank":160},{"name":"Amazon Nova 2 Lite","organization":"amazon","score":1379.313642862934,"low":1373.5801060959345,"high":1385.0471796299337,"observations":11939,"sourceRank":168,"publishedAt":"2026-10-28","rank":163},{"name":"Gemma 3 27B IT","organization":"google","score":1379.1322721807026,"low":1367.9895306514818,"high":1390.2750137099235,"observations":2384,"sourceRank":169,"publishedAt":"2026-10-28","rank":160},{"name":"Granite 4.2 30B","organization":"ibm","score":1375.3993159516067,"low":1366.3058497861307,"high":1384.4927821170827,"observations":3389,"sourceRank":170,"publishedAt":"2026-10-28","rank":163},{"name":"INTELLECT-3","organization":"","score":1372.6434324862914,"low":1364.8307439685498,"high":1380.4561210040329,"observations":5111,"sourceRank":171,"publishedAt":"2026-10-28","rank":166},{"name":"Trinity Large Preview","organization":"","score":1371.4660517476775,"low":1367.6242237277233,"high":1375.3078797676317,"observations":30952,"sourceRank":172,"publishedAt":"2026-10-28","rank":168},{"name":"Trinity Large Thinking","organization":"","score":1370.2482854529421,"low":1366.0387840897856,"high":1374.4577868160986,"observations":30131,"sourceRank":173,"publishedAt":"2026-10-28","rank":168},{"name":"NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4)","organization":"nvidia","score":1369.5327140668692,"low":1364.8600333611255,"high":1374.2053947726129,"observations":24230,"sourceRank":174,"publishedAt":"2026-10-28","rank":168},{"name":"MiniMax-M1","organization":"minimax","score":1369.437959621792,"low":1358.6191979862479,"high":1380.2567212573363,"observations":2569,"sourceRank":175,"publishedAt":"2026-10-28","rank":167},{"name":"GLM-4.7-Flash","organization":"zai","score":1369.3972122263758,"low":1363.8663541310445,"high":1374.928070321707,"observations":11879,"sourceRank":176,"publishedAt":"2026-10-28","rank":168},{"name":"Mercury 2","organization":"inception-ai","score":1367.6981370252483,"low":1358.2042700370166,"high":1377.19200401348,"observations":3190,"sourceRank":177,"publishedAt":"2026-10-28","rank":168},{"name":"o4-mini (2025-04-16)","organization":"openai","score":1367.4791923530222,"low":1357.2137279063727,"high":1377.7446567996717,"observations":2721,"sourceRank":178,"publishedAt":"2026-10-28","rank":168},{"name":"Command A (03-2025)","organization":"cohere","score":1362.8130387471356,"low":1356.3447455816083,"high":1369.2813319126628,"observations":7703,"sourceRank":179,"publishedAt":"2026-10-28","rank":169},{"name":"NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)","organization":"nvidia","score":1362.1976397562719,"low":1356.950729162252,"high":1367.4445503502918,"observations":15454,"sourceRank":180,"publishedAt":"2026-10-28","rank":171},{"name":"MiniMax-M2","organization":"minimax","score":1359.7325969887386,"low":1352.5107273407116,"high":1366.9544666367656,"observations":6683,"sourceRank":181,"publishedAt":"2026-10-28","rank":171},{"name":"Granite 4.2 8B","organization":"ibm","score":1342.0512793128005,"low":1332.2897748970884,"high":1351.8127837285126,"observations":3251,"sourceRank":182,"publishedAt":"2026-10-28","rank":182},{"name":"Olmo 3.1 32B Instruct","organization":"allenai","score":1341.441829092298,"low":1335.6066127002032,"high":1347.2770454843926,"observations":11693,"sourceRank":183,"publishedAt":"2026-10-28","rank":182},{"name":"Granite 4.2 3B","organization":"ibm","score":1323.8795112976848,"low":1313.9494141287973,"high":1333.8096084665724,"observations":3249,"sourceRank":184,"publishedAt":"2026-10-28","rank":183},{"name":"Olmo 3 32B Think","organization":"allenai","score":1318.6423557972273,"low":1310.8373055023217,"high":1326.447406092133,"observations":5704,"sourceRank":185,"publishedAt":"2026-10-28","rank":184},{"name":"Granite 4.1 8B","organization":"ibm","score":1310.345352874374,"low":1301.1079567907234,"high":1319.5827489580247,"observations":4177,"sourceRank":186,"publishedAt":"2026-10-28","rank":184},{"name":"Mercury","organization":"inception-ai","score":1304.2382522467697,"low":1291.6767775712717,"high":1316.7997269222678,"observations":1937,"sourceRank":187,"publishedAt":"2026-10-28","rank":184},{"name":"Olmo 3.1 32B Think","organization":"allenai","score":1299.8997286752026,"low":1292.9707430613935,"high":1306.8287142890117,"observations":8099,"sourceRank":188,"publishedAt":"2026-10-28","rank":186}],"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":"26b14382e6b8561b324cba0c156b13f3b74cae7abf321327a609c407331f9d25.parquet","sha256":"26b14382e6b8561b324cba0c156b13f3b74cae7abf321327a609c407331f9d25","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53/text_factuality/latest-00000-of-00001.parquet","revision":"8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53","role":"rows"}]},"status":"fresh"}
