{"config":"agent","id":"arena-agent","title":"Agent Arena","category":"Coding and agents","metric":"IPS score","direction":"higher","precision":6,"publishedAt":"2026-11-04","interval":"95% confidence interval","observationLabel":"Observations","description":"Agent Arena signal scores from the official dataset. Each signal is a separate measurement; it is not a success percentage.","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 5.5 (Max)","organization":"anthropic","score":0.20144840119751856,"low":0.1805897726415885,"high":0.22230702975344863,"observations":2350984,"sourceRank":1,"publishedAt":"2026-11-04","rank":1},{"name":"Gemini 4 Carbon (High)","organization":"google","score":0.16716595213257168,"low":0.15950033099714978,"high":0.1748315732679936,"observations":7450409,"sourceRank":2,"publishedAt":"2026-11-04","rank":2},{"name":"Claude Sonnet 5.5 (Max)","organization":"anthropic","score":0.15423674759515776,"low":0.1264750029811495,"high":0.18199849220916603,"observations":1201743,"sourceRank":3,"publishedAt":"2026-11-04","rank":1},{"name":"GPT-6 Astra (Max)","organization":"openai","score":0.1469702596284481,"low":0.12631806771162565,"high":0.16762245154527053,"observations":1293489,"sourceRank":4,"publishedAt":"2026-11-04","rank":2},{"name":"Claude Fable 5.1 (Max)","organization":"anthropic","score":0.13857005028518268,"low":0.11983454157431038,"high":0.15730555899605497,"observations":2422643,"sourceRank":5,"publishedAt":"2026-11-04","rank":3},{"name":"GPT-6.1 Sol (Max)","organization":"openai","score":0.12513945767905282,"low":0.11405067538908382,"high":0.13622823996902184,"observations":2909711,"sourceRank":6,"publishedAt":"2026-11-04","rank":3},{"name":"GPT-6.1 Terra (Max)","organization":"openai","score":0.11396048113208619,"low":0.09998293718572114,"high":0.12793802507845123,"observations":6713903,"sourceRank":7,"publishedAt":"2026-11-04","rank":3},{"name":"Gemini 4 Argon (High)","organization":"google","score":0.10525164824272239,"low":0.09680177928260052,"high":0.11370151720284426,"observations":6589073,"sourceRank":8,"publishedAt":"2026-11-04","rank":7},{"name":"Muse Wonder Full (Max)","organization":"meta","score":0.09422636744409608,"low":0.08477875635351872,"high":0.10367397853467344,"observations":5846669,"sourceRank":9,"publishedAt":"2026-11-04","rank":7},{"name":"Claude Fable 5 (High)","organization":"anthropic","score":0.078224963210975,"low":0.06708110305316427,"high":0.08936882336878572,"observations":3486141,"sourceRank":10,"publishedAt":"2026-11-04","rank":9},{"name":"Claude Opus 5 (Max)","organization":"anthropic","score":0.07661953023610667,"low":0.0641797475015059,"high":0.08905931297070743,"observations":4630296,"sourceRank":11,"publishedAt":"2026-11-04","rank":9},{"name":"GPT-6 Sol (Max)","organization":"openai","score":0.06778131892924635,"low":0.05234473838862066,"high":0.08321789946987204,"observations":3117453,"sourceRank":12,"publishedAt":"2026-11-04","rank":10},{"name":"Hy4","organization":"tencent","score":0.05392249728249619,"low":0.03681669587386279,"high":0.07102829869112959,"observations":1473452,"sourceRank":13,"publishedAt":"2026-11-04","rank":10},{"name":"Kimi K3.1 Pro (Max)","organization":"moonshot","score":0.052922199913780096,"low":0.040115283394755646,"high":0.06572911643280455,"observations":5477867,"sourceRank":14,"publishedAt":"2026-11-04","rank":11},{"name":"GPT-5.6 Sol (xHigh)","organization":"openai","score":0.04572267729564615,"low":0.03535525805465649,"high":0.05609009653663581,"observations":6530847,"sourceRank":15,"publishedAt":"2026-11-04","rank":12},{"name":"MiMo-V2.6-Pro","organization":"xiaomi","score":0.026810364256876926,"low":0.017665417601875982,"high":0.03595531091187787,"observations":5417543,"sourceRank":16,"publishedAt":"2026-11-04","rank":15},{"name":"Grok 4.7 (xHigh)","organization":"xai","score":0.02680192300589593,"low":0.01219937625561865,"high":0.041404469756173214,"observations":3666622,"sourceRank":17,"publishedAt":"2026-11-04","rank":13},{"name":"Gemini 3.8 Flash (High)","organization":"google","score":0.025819514653005995,"low":0.01753089198390698,"high":0.034108137322105006,"observations":8498907,"sourceRank":18,"publishedAt":"2026-11-04","rank":16},{"name":"Muse Spark 1.3 (Max)","organization":"meta","score":0.025113832728772198,"low":0.016843321461508312,"high":0.033384343996036084,"observations":8877602,"sourceRank":19,"publishedAt":"2026-11-04","rank":16},{"name":"Claude Sonnet 5 (High)","organization":"anthropic","score":0.024429680071076675,"low":0.012756982872221686,"high":0.036102377269931665,"observations":5157478,"sourceRank":20,"publishedAt":"2026-11-04","rank":15},{"name":"Muse Wonder (Max)","organization":"meta","score":0.024335809889644497,"low":0.010837444820625304,"high":0.03783417495866369,"observations":2088667,"sourceRank":21,"publishedAt":"2026-11-04","rank":14},{"name":"DeepSeek-V4.1-Flash-20261017 (Max)","organization":"deepseek","score":0.023700399579817785,"low":0.01804319398046836,"high":0.02935760517916721,"observations":20237992,"sourceRank":22,"publishedAt":"2026-11-04","rank":16},{"name":"GPT-6 Luna (Max)","organization":"openai","score":0.018937239039092082,"low":0.01452566731333568,"high":0.023348810764848484,"observations":41141530,"sourceRank":23,"publishedAt":"2026-11-04","rank":16},{"name":"GLM-5.3 (Max)","organization":"zai","score":0.010890920338008515,"low":0.0029352822898843396,"high":0.01884655838613269,"observations":11340717,"sourceRank":24,"publishedAt":"2026-11-04","rank":16},{"name":"Kimi K3 (Max)","organization":"moonshot","score":0.008419453885193499,"low":0.0026347704579218287,"high":0.014204137312465169,"observations":16147659,"sourceRank":25,"publishedAt":"2026-11-04","rank":21},{"name":"Hy4 preview","organization":"tencent","score":0.007490202576772596,"low":0.0005457414529819234,"high":0.01443466370056327,"observations":11647463,"sourceRank":26,"publishedAt":"2026-11-04","rank":21},{"name":"GLM-5.2 (Max)","organization":"zai","score":0.0063863950447943145,"low":-0.0013475603817149672,"high":0.014120350471303597,"observations":9213548,"sourceRank":27,"publishedAt":"2026-11-04","rank":21},{"name":"Claude Haiku 5.5 (High)","organization":"anthropic","score":0.006244188898989065,"low":-0.004023773139241094,"high":0.016512150937219222,"observations":4139248,"sourceRank":28,"publishedAt":"2026-11-04","rank":20},{"name":"Qwen3.8-Max","organization":"alibaba","score":0.004788293142734283,"low":-0.0017633433846471584,"high":0.011339929670115724,"observations":8376850,"sourceRank":29,"publishedAt":"2026-11-04","rank":23},{"name":"Grok 4.6 (xHigh)","organization":"xai","score":0.004542626115501247,"low":-0.007222960527704467,"high":0.01630821275870696,"observations":3777170,"sourceRank":30,"publishedAt":"2026-11-04","rank":20},{"name":"MiMo-V2.6-Flash","organization":"xiaomi","score":0.002000589395452135,"low":-0.009278352078914507,"high":0.013279530869818777,"observations":3647059,"sourceRank":31,"publishedAt":"2026-11-04","rank":21},{"name":"DeepSeek-V4-Pro (High, 20260813)","organization":"deepseek","score":-0.0030041093087883296,"low":-0.020014906662915204,"high":0.014006688045338545,"observations":932407,"sourceRank":32,"publishedAt":"2026-11-04","rank":21},{"name":"GPT-5.6 Terra (xHigh)","organization":"openai","score":-0.01504690834577408,"low":-0.02286932653566669,"high":-0.007224490155881471,"observations":3770129,"sourceRank":33,"publishedAt":"2026-11-04","rank":31},{"name":"Gemini 3.7 Flash (High)","organization":"google","score":-0.01602518748124285,"low":-0.024778368800773453,"high":-0.007272006161712249,"observations":6216788,"sourceRank":34,"publishedAt":"2026-11-04","rank":31},{"name":"GPT-6 Luna (Medium)","organization":"openai","score":-0.018432443020127483,"low":-0.023734592666171953,"high":-0.013130293374083012,"observations":8786320,"sourceRank":35,"publishedAt":"2026-11-04","rank":32},{"name":"GLM-5.3-Flash","organization":"zai","score":-0.023939650496158076,"low":-0.03086599467914004,"high":-0.017013306313176112,"observations":13609316,"sourceRank":36,"publishedAt":"2026-11-04","rank":32},{"name":"MiniMax-M3.1-Flash","organization":"minimax","score":-0.02843512991092605,"low":-0.043845168452524313,"high":-0.013025091369327788,"observations":2553700,"sourceRank":37,"publishedAt":"2026-11-04","rank":32},{"name":"Step 5 Preview","organization":"stepfun","score":-0.028761238788302872,"low":-0.04274569610860234,"high":-0.014776781468003403,"observations":2816931,"sourceRank":38,"publishedAt":"2026-11-04","rank":32},{"name":"Qwen3.8-27B","organization":"alibaba","score":-0.042751116969888335,"low":-0.05133870820889113,"high":-0.03416352573088554,"observations":8425447,"sourceRank":39,"publishedAt":"2026-11-04","rank":37},{"name":"Qwen3.8-Flash-Next","organization":"alibaba","score":-0.044295053150866875,"low":-0.05161741236923228,"high":-0.03697269393250147,"observations":16929386,"sourceRank":40,"publishedAt":"2026-11-04","rank":37},{"name":"Gemini 3.1 Pro Preview","organization":"google","score":-0.044409818497287236,"low":-0.058551643326517515,"high":-0.030267993668056957,"observations":2970564,"sourceRank":41,"publishedAt":"2026-11-04","rank":36},{"name":"Beam 1.0 501B A23B","organization":"reflection","score":-0.05380886946699661,"low":-0.0788626132932326,"high":-0.028755125640760614,"observations":701442,"sourceRank":42,"publishedAt":"2026-11-04","rank":36},{"name":"Mistral Large 4","organization":"mistral","score":-0.05462655237209272,"low":-0.07391152415670967,"high":-0.035341580587475774,"observations":447184,"sourceRank":43,"publishedAt":"2026-11-04","rank":37},{"name":"GPT-6 Luna (Low)","organization":"openai","score":-0.059288669287671014,"low":-0.06633312192091537,"high":-0.05224421665442666,"observations":3349837,"sourceRank":44,"publishedAt":"2026-11-04","rank":41},{"name":"Qwen3.7-Max","organization":"alibaba","score":-0.0651996046174915,"low":-0.07732616737786324,"high":-0.05307304185711976,"observations":2294942,"sourceRank":45,"publishedAt":"2026-11-04","rank":41},{"name":"Qwen3.7-Plus","organization":"alibaba","score":-0.07459946086080223,"low":-0.0901581418044559,"high":-0.05904077991714855,"observations":1280054,"sourceRank":46,"publishedAt":"2026-11-04","rank":42},{"name":"Muse Spark 1.1","organization":"meta","score":-0.07659459536438275,"low":-0.08320481901043716,"high":-0.06998437171832833,"observations":8564936,"sourceRank":47,"publishedAt":"2026-11-04","rank":43},{"name":"Muse Spark 1.2 (xHigh)","organization":"meta","score":-0.07698988459758775,"low":-0.08544272677146553,"high":-0.06853704242370998,"observations":3876357,"sourceRank":48,"publishedAt":"2026-11-04","rank":43},{"name":"Hy3","organization":"tencent","score":-0.0771969842666558,"low":-0.09166024101215944,"high":-0.06273372752115217,"observations":1234715,"sourceRank":49,"publishedAt":"2026-11-04","rank":42},{"name":"MiMo-V2.5-Pro","organization":"xiaomi","score":-0.09027032879654748,"low":-0.10044266629630592,"high":-0.08009799129678903,"observations":2517888,"sourceRank":50,"publishedAt":"2026-11-04","rank":46},{"name":"Spark-X2.6","organization":"synlan","score":-0.0990263629533583,"low":-0.11284563802954233,"high":-0.08520708787717428,"observations":1027728,"sourceRank":51,"publishedAt":"2026-11-04","rank":47},{"name":"MiniMax-M3","organization":"minimax","score":-0.10396707055734586,"low":-0.1158541739455209,"high":-0.09207996716917081,"observations":3672031,"sourceRank":52,"publishedAt":"2026-11-04","rank":50},{"name":"Mistral Medium 3.5","organization":"mistral","score":-0.1334397149879274,"low":-0.15035865115306213,"high":-0.11652077882279266,"observations":680776,"sourceRank":53,"publishedAt":"2026-11-04","rank":53},{"name":"Nemotron 3 Ultra","organization":"nvidia","score":-0.15597102936055585,"low":-0.18896208210448834,"high":-0.12297997661662335,"observations":228023,"sourceRank":54,"publishedAt":"2026-11-04","rank":53},{"name":"NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)","organization":"nvidia","score":-0.1593210465176367,"low":-0.16809600705931385,"high":-0.15054608597595956,"observations":1618598,"sourceRank":55,"publishedAt":"2026-11-04","rank":54},{"name":"Inkling","organization":"thinky","score":-0.16332138597542212,"low":-0.17822976167059953,"high":-0.1484130102802447,"observations":1748439,"sourceRank":56,"publishedAt":"2026-11-04","rank":53},{"name":"Inkling-Small","organization":"thinky","score":-0.1703963452049372,"low":-0.18910059930551645,"high":-0.15169209110435797,"observations":564788,"sourceRank":57,"publishedAt":"2026-11-04","rank":54},{"name":"Solar Pro 4","organization":"upstage","score":-0.2180465973587057,"low":-0.23946473000441232,"high":-0.1966284647129991,"observations":546591,"sourceRank":58,"publishedAt":"2026-11-04","rank":58}],"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":"7c16d94881dac8fe596fbd55013f2b4c5a5a88fef6d91768dbd234475fe1327a.parquet","sha256":"7c16d94881dac8fe596fbd55013f2b4c5a5a88fef6d91768dbd234475fe1327a","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53/agent/latest-00000-of-00001.parquet","revision":"8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53","role":"rows"}]},"status":"fresh"}