{"config":"agent_praise_complaint","id":"arena-agent-praise-complaint","title":"Agents · praise and complaints","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":0.42913782151617097,"low":0.35045079977415283,"high":0.5078248432581891,"observations":1761,"sourceRank":1,"publishedAt":"2026-11-04","rank":1},{"name":"Gemini 4 Carbon (High)","organization":"google","score":0.40120405826089656,"low":0.3731678449541248,"high":0.4292402715676683,"observations":10208,"sourceRank":2,"publishedAt":"2026-11-04","rank":1},{"name":"GPT-6 Astra (Max)","organization":"openai","score":0.32742552746725206,"low":0.25138791994648374,"high":0.4034631349880204,"observations":2577,"sourceRank":3,"publishedAt":"2026-11-04","rank":1},{"name":"Claude Sonnet 5.5 (Max)","organization":"anthropic","score":0.29711867378133383,"low":0.189183074302552,"high":0.40505427326011567,"observations":906,"sourceRank":4,"publishedAt":"2026-11-04","rank":1},{"name":"Claude Fable 5.1 (Max)","organization":"anthropic","score":0.2797175157419315,"low":0.2108587499596452,"high":0.34857628152421777,"observations":3286,"sourceRank":5,"publishedAt":"2026-11-04","rank":3},{"name":"GPT-6.1 Sol (Max)","organization":"openai","score":0.2741800701303798,"low":0.2341897824120281,"high":0.31417035784873154,"observations":5246,"sourceRank":6,"publishedAt":"2026-11-04","rank":3},{"name":"Gemini 4 Argon (High)","organization":"google","score":0.22866079080954782,"low":0.19971845737464264,"high":0.257603124244453,"observations":12485,"sourceRank":7,"publishedAt":"2026-11-04","rank":3},{"name":"GPT-6.1 Terra (Max)","organization":"openai","score":0.1731599305366338,"low":0.12493515662071308,"high":0.22138470445255454,"observations":5399,"sourceRank":8,"publishedAt":"2026-11-04","rank":5},{"name":"Muse Wonder Full (Max)","organization":"meta","score":0.16261485460466052,"low":0.13226315661337976,"high":0.19296655259594128,"observations":8487,"sourceRank":9,"publishedAt":"2026-11-04","rank":7},{"name":"Claude Fable 5 (High)","organization":"anthropic","score":0.15051894968215918,"low":0.11453474816234865,"high":0.1865031512019697,"observations":14520,"sourceRank":10,"publishedAt":"2026-11-04","rank":8},{"name":"Claude Opus 5 (Max)","organization":"anthropic","score":0.1192393456998001,"low":0.07810351442750732,"high":0.1603751769720929,"observations":8202,"sourceRank":11,"publishedAt":"2026-11-04","rank":8},{"name":"GPT-6 Sol (Max)","organization":"openai","score":0.1045674210990627,"low":0.05343728526203592,"high":0.15569755693608947,"observations":2974,"sourceRank":12,"publishedAt":"2026-11-04","rank":8},{"name":"Kimi K3.1 Pro (Max)","organization":"moonshot","score":0.08458550265928988,"low":0.04439805514003622,"high":0.12477295017854353,"observations":5688,"sourceRank":13,"publishedAt":"2026-11-04","rank":10},{"name":"Hy4","organization":"tencent","score":0.07327675694668812,"low":0.012746363629332035,"high":0.1338071502640442,"observations":2084,"sourceRank":14,"publishedAt":"2026-11-04","rank":8},{"name":"GPT-5.6 Sol (xHigh)","organization":"openai","score":0.05713611019306497,"low":0.024532663552606596,"high":0.08973955683352335,"observations":13030,"sourceRank":15,"publishedAt":"2026-11-04","rank":11},{"name":"Gemini 3.8 Flash (High)","organization":"google","score":0.05264242690973686,"low":0.027479296251863544,"high":0.07780555756761018,"observations":14974,"sourceRank":16,"publishedAt":"2026-11-04","rank":12},{"name":"MiMo-V2.6-Pro","organization":"xiaomi","score":0.04753055784127913,"low":0.01963192503521418,"high":0.07542919064734407,"observations":11318,"sourceRank":17,"publishedAt":"2026-11-04","rank":12},{"name":"GLM-5.3 (Max)","organization":"zai","score":0.04374919793525722,"low":0.019977332483399,"high":0.06752106338711544,"observations":30739,"sourceRank":18,"publishedAt":"2026-11-04","rank":12},{"name":"Grok 4.7 (xHigh)","organization":"xai","score":0.028641523155706894,"low":-0.016926016335130856,"high":0.07420906264654464,"observations":4637,"sourceRank":19,"publishedAt":"2026-11-04","rank":12},{"name":"GLM-5.2 (Max)","organization":"zai","score":0.023170351423320135,"low":0.00020941377089813903,"high":0.04613128907574213,"observations":25273,"sourceRank":20,"publishedAt":"2026-11-04","rank":13},{"name":"Muse Spark 1.3 (Max)","organization":"meta","score":0.021459493682319142,"low":-0.003868273039801133,"high":0.04678726040443942,"observations":22469,"sourceRank":21,"publishedAt":"2026-11-04","rank":13},{"name":"DeepSeek-V4.1-Flash-20261017 (Max)","organization":"deepseek","score":0.01913389733903359,"low":0.0017219142626077322,"high":0.03654588041545945,"observations":20235,"sourceRank":22,"publishedAt":"2026-11-04","rank":14},{"name":"Kimi K3 (Max)","organization":"moonshot","score":0.01367256262321026,"low":-0.0035603250271905966,"high":0.030905450273611117,"observations":47105,"sourceRank":23,"publishedAt":"2026-11-04","rank":14},{"name":"DeepSeek-V4-Pro (High, 20260813)","organization":"deepseek","score":0.007326621912662978,"low":-0.044369144561848074,"high":0.05902238838717403,"observations":1608,"sourceRank":24,"publishedAt":"2026-11-04","rank":12},{"name":"Qwen3.8-Max","organization":"alibaba","score":0.0023027190600241054,"low":-0.017553672570609025,"high":0.022159110690657235,"observations":21636,"sourceRank":25,"publishedAt":"2026-11-04","rank":16},{"name":"Hy4 preview","organization":"tencent","score":0.002148777291806958,"low":-0.019222886488840886,"high":0.023520441072454802,"observations":18086,"sourceRank":26,"publishedAt":"2026-11-04","rank":16},{"name":"Muse Wonder (Max)","organization":"meta","score":-0.002546705974754926,"low":-0.04326387083896973,"high":0.03817045888945988,"observations":4607,"sourceRank":27,"publishedAt":"2026-11-04","rank":14},{"name":"MiMo-V2.6-Flash","organization":"xiaomi","score":-0.0048163613742124856,"low":-0.036303524124463346,"high":0.026670801376038375,"observations":6895,"sourceRank":28,"publishedAt":"2026-11-04","rank":15},{"name":"Claude Sonnet 5 (High)","organization":"anthropic","score":-0.010620687415345609,"low":-0.04570961566784104,"high":0.024468240837149824,"observations":10020,"sourceRank":29,"publishedAt":"2026-11-04","rank":16},{"name":"GPT-6 Luna (Max)","organization":"openai","score":-0.011909283261533954,"low":-0.02552887688131046,"high":0.0017103103582425516,"observations":51440,"sourceRank":30,"publishedAt":"2026-11-04","rank":20},{"name":"GPT-5.6 Terra (xHigh)","organization":"openai","score":-0.015535565410917163,"low":-0.03881029400567253,"high":0.007739163183838202,"observations":13527,"sourceRank":31,"publishedAt":"2026-11-04","rank":19},{"name":"Gemini 3.1 Pro Preview","organization":"google","score":-0.01572957961195487,"low":-0.05222719552458273,"high":0.02076803630067299,"observations":27127,"sourceRank":32,"publishedAt":"2026-11-04","rank":16},{"name":"Grok 4.6 (xHigh)","organization":"xai","score":-0.018783974287121308,"low":-0.05296582995865275,"high":0.015397881384410138,"observations":9204,"sourceRank":33,"publishedAt":"2026-11-04","rank":18},{"name":"Gemini 3.7 Flash (High)","organization":"google","score":-0.021197583478677284,"low":-0.04503853527398249,"high":0.0026433683166279184,"observations":23463,"sourceRank":34,"publishedAt":"2026-11-04","rank":19},{"name":"GLM-5.3-Flash","organization":"zai","score":-0.04117553084454073,"low":-0.06026669378023874,"high":-0.022084367908842724,"observations":34330,"sourceRank":35,"publishedAt":"2026-11-04","rank":26},{"name":"Claude Haiku 5.5 (High)","organization":"anthropic","score":-0.04151179792240578,"low":-0.07253040991821672,"high":-0.010493185926594841,"observations":9012,"sourceRank":36,"publishedAt":"2026-11-04","rank":23},{"name":"Step 5 Preview","organization":"stepfun","score":-0.052279881148007856,"low":-0.09328987965574928,"high":-0.011269882640266425,"observations":3676,"sourceRank":37,"publishedAt":"2026-11-04","rank":23},{"name":"Qwen3.8-Flash-Next","organization":"alibaba","score":-0.05570742915725502,"low":-0.07656272079384917,"high":-0.03485213752066087,"observations":20972,"sourceRank":38,"publishedAt":"2026-11-04","rank":27},{"name":"Beam 1.0 501B A23B","organization":"reflection","score":-0.05860845242437618,"low":-0.1304755409924504,"high":0.01325863614369803,"observations":2370,"sourceRank":39,"publishedAt":"2026-11-04","rank":18},{"name":"Qwen3.8-27B","organization":"alibaba","score":-0.05975362173059584,"low":-0.08426468131554056,"high":-0.03524256214565112,"observations":16954,"sourceRank":40,"publishedAt":"2026-11-04","rank":27},{"name":"GPT-6 Luna (Medium)","organization":"openai","score":-0.06797275384911217,"low":-0.08350957116537229,"high":-0.05243593653285204,"observations":19400,"sourceRank":41,"publishedAt":"2026-11-04","rank":34},{"name":"MiniMax-M3.1-Flash","organization":"minimax","score":-0.075767989270203,"low":-0.1211253386999172,"high":-0.0304106398404888,"observations":2768,"sourceRank":42,"publishedAt":"2026-11-04","rank":27},{"name":"Hy3","organization":"tencent","score":-0.08739736249481878,"low":-0.12463188217836209,"high":-0.05016284281127546,"observations":5277,"sourceRank":43,"publishedAt":"2026-11-04","rank":33},{"name":"Qwen3.7-Max","organization":"alibaba","score":-0.09447858832094203,"low":-0.1253700612067551,"high":-0.06358711543512895,"observations":13141,"sourceRank":44,"publishedAt":"2026-11-04","rank":36},{"name":"GPT-6 Luna (Low)","organization":"openai","score":-0.10420948959342824,"low":-0.12351852843299221,"high":-0.08490045075386426,"observations":12382,"sourceRank":45,"publishedAt":"2026-11-04","rank":40},{"name":"Qwen3.7-Plus","organization":"alibaba","score":-0.11300732260531254,"low":-0.15185871238201953,"high":-0.07415593282860555,"observations":6885,"sourceRank":46,"publishedAt":"2026-11-04","rank":37},{"name":"Mistral Large 4","organization":"mistral","score":-0.11817476716077135,"low":-0.1700737509205127,"high":-0.06627578340103002,"observations":1228,"sourceRank":47,"publishedAt":"2026-11-04","rank":36},{"name":"Muse Spark 1.2 (xHigh)","organization":"meta","score":-0.12844320788195818,"low":-0.14982688616693818,"high":-0.10705952959697819,"observations":17621,"sourceRank":48,"publishedAt":"2026-11-04","rank":41},{"name":"Muse Spark 1.1","organization":"meta","score":-0.13435898113813272,"low":-0.14958545955281896,"high":-0.11913250272344647,"observations":43694,"sourceRank":49,"publishedAt":"2026-11-04","rank":41},{"name":"MiMo-V2.5-Pro","organization":"xiaomi","score":-0.14034737201120318,"low":-0.16470613581939456,"high":-0.1159886082030118,"observations":13202,"sourceRank":50,"publishedAt":"2026-11-04","rank":41},{"name":"MiniMax-M3","organization":"minimax","score":-0.160777766596659,"low":-0.18703766750686468,"high":-0.1345178656864533,"observations":12413,"sourceRank":51,"publishedAt":"2026-11-04","rank":46},{"name":"Mistral Medium 3.5","organization":"mistral","score":-0.1858785275843997,"low":-0.22264872027442417,"high":-0.14910833489437525,"observations":3307,"sourceRank":52,"publishedAt":"2026-11-04","rank":46},{"name":"Nemotron 3 Ultra","organization":"nvidia","score":-0.19093935353448344,"low":-0.2632494171386752,"high":-0.11862928993029165,"observations":1290,"sourceRank":53,"publishedAt":"2026-11-04","rank":41},{"name":"Spark-X2.6","organization":"synlan","score":-0.1946255510930519,"low":-0.2266105079002974,"high":-0.1626405942858064,"observations":2513,"sourceRank":54,"publishedAt":"2026-11-04","rank":49},{"name":"NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)","organization":"nvidia","score":-0.22258059055703505,"low":-0.24109369464199842,"high":-0.20406748647207168,"observations":6427,"sourceRank":55,"publishedAt":"2026-11-04","rank":52},{"name":"Inkling-Small","organization":"thinky","score":-0.22770336212033282,"low":-0.2630554741080609,"high":-0.19235125013260473,"observations":3487,"sourceRank":56,"publishedAt":"2026-11-04","rank":52},{"name":"Solar Pro 4","organization":"upstage","score":-0.2417500038596414,"low":-0.28144401474427194,"high":-0.2020559929750109,"observations":2314,"sourceRank":57,"publishedAt":"2026-11-04","rank":52},{"name":"Inkling","organization":"thinky","score":-0.2463440056371793,"low":-0.27217248410609324,"high":-0.22051552716826534,"observations":10406,"sourceRank":58,"publishedAt":"2026-11-04","rank":52}],"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":"22c80107963a734288b84edaf6045ae59a6ece9ab73a44d83633d906fd9396c4.parquet","sha256":"22c80107963a734288b84edaf6045ae59a6ece9ab73a44d83633d906fd9396c4","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53/agent_praise_complaint/latest-00000-of-00001.parquet","revision":"8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53","role":"rows"}]},"status":"fresh"}