{"config":"search_style_control","id":"arena-search-style-control","title":"Search · style controlled","category":"Search and documents","metric":"Arena score","direction":"higher","precision":2,"publishedAt":"2026-10-13","interval":"95% confidence interval","observationLabel":"Votes","description":"Human preference ratings for the overall category of this Arena task. Scores from different boards are not interchangeable.","limitations":["The population is the models in this source board, including variants and models without an available API price.","Ranks use the published confidence bounds: one plus the number of models whose lower bound exceeds this model’s upper bound. Shared ranks are not proof of equal performance."],"omissions":[],"rows":[{"name":"gpt-5.6-sol-xhigh","organization":"openai","score":1257.933378466372,"low":1251.4619129537114,"high":1264.4048439790326,"observations":60437,"sourceRank":1,"publishedAt":"2026-10-13","rank":1},{"name":"gpt-6.1-sol-max","organization":"openai","score":1249.9181501199778,"low":1240.895777035074,"high":1258.9405232048819,"observations":5555,"sourceRank":2,"publishedAt":"2026-10-13","rank":1},{"name":"gpt-6-astra-max","organization":"openai","score":1246.2387961613688,"low":1238.199092459655,"high":1254.2784998630827,"observations":18483,"sourceRank":3,"publishedAt":"2026-10-13","rank":1},{"name":"claude-fable-5.1-high","organization":"anthropic","score":1233.3718303465348,"low":1226.2009586615054,"high":1240.5427020315644,"observations":12782,"sourceRank":4,"publishedAt":"2026-10-13","rank":3},{"name":"qwen3.8-max","organization":"alibaba","score":1229.4963981050257,"low":1216.2005910513421,"high":1242.7922051587093,"observations":1870,"sourceRank":5,"publishedAt":"2026-10-13","rank":2},{"name":"claude-fable-5-high","organization":"anthropic","score":1229.0173574796083,"low":1222.4352010521866,"high":1235.5995139070303,"observations":73596,"sourceRank":6,"publishedAt":"2026-10-13","rank":4},{"name":"gpt-6-sol-max","organization":"openai","score":1228.2064872067126,"low":1220.76790691623,"high":1235.645067497195,"observations":11313,"sourceRank":7,"publishedAt":"2026-10-13","rank":4},{"name":"gpt-5.5-search","organization":"openai","score":1226.4532218375628,"low":1221.461343149382,"high":1231.4451005257433,"observations":125957,"sourceRank":8,"publishedAt":"2026-10-13","rank":4},{"name":"claude-opus-4-6-search","organization":"anthropic","score":1222.0454568426385,"low":1217.3597719889392,"high":1226.7311416963378,"observations":173191,"sourceRank":9,"publishedAt":"2026-10-13","rank":4},{"name":"claude-opus-5-high","organization":"anthropic","score":1214.351710131368,"low":1207.462316655668,"high":1221.2411036070678,"observations":13285,"sourceRank":10,"publishedAt":"2026-10-13","rank":7},{"name":"claude-opus-5.5-medium","organization":"anthropic","score":1211.2268684442495,"low":1204.1302587892944,"high":1218.3234780992045,"observations":10842,"sourceRank":11,"publishedAt":"2026-10-13","rank":8},{"name":"claude-opus-4-7","organization":"anthropic","score":1209.705740493785,"low":1204.7707355794955,"high":1214.6407454080743,"observations":127506,"sourceRank":12,"publishedAt":"2026-10-13","rank":10},{"name":"gpt-6-luna-max","organization":"openai","score":1209.2529531356533,"low":1201.8580059684211,"high":1216.6479003028855,"observations":10793,"sourceRank":13,"publishedAt":"2026-10-13","rank":9},{"name":"gemini-3.1-pro-grounding","organization":"google","score":1206.617924481997,"low":1201.8320781298366,"high":1211.4037708341575,"observations":151436,"sourceRank":14,"publishedAt":"2026-10-13","rank":10},{"name":"grok-4.20-multi-agent-beta-0309","organization":"xai","score":1206.383195935518,"low":1200.8265916263501,"high":1211.9398002446858,"observations":126238,"sourceRank":15,"publishedAt":"2026-10-13","rank":10},{"name":"grok-4.5","organization":"xai","score":1206.1917855542135,"low":1200.2946301160152,"high":1212.0889409924118,"observations":76458,"sourceRank":16,"publishedAt":"2026-10-13","rank":10},{"name":"claude-sonnet-4-6-search","organization":"anthropic","score":1201.9323575161923,"low":1197.2615273462443,"high":1206.60318768614,"observations":173986,"sourceRank":17,"publishedAt":"2026-10-13","rank":11},{"name":"gemini-3-pro-grounding","organization":"google","score":1200.751042643344,"low":1195.2601166699142,"high":1206.2419686167732,"observations":38857,"sourceRank":18,"publishedAt":"2026-10-13","rank":11},{"name":"grok-4.20-beta1","organization":"xai","score":1199.31309555303,"low":1193.2468667363369,"high":1205.3793243697235,"observations":57049,"sourceRank":19,"publishedAt":"2026-10-13","rank":11},{"name":"gpt-5.4-search","organization":"openai","score":1196.2617570828174,"low":1190.5867414370496,"high":1201.936772728585,"observations":126730,"sourceRank":20,"publishedAt":"2026-10-13","rank":13},{"name":"o3-search","organization":"openai","score":1196.1603506359927,"low":1189.4253662417566,"high":1202.895335030229,"observations":20770,"sourceRank":21,"publishedAt":"2026-10-13","rank":13},{"name":"claude-opus-4-8","organization":"anthropic","score":1195.2496505200859,"low":1189.605757854276,"high":1200.8935431858956,"observations":106304,"sourceRank":22,"publishedAt":"2026-10-13","rank":15},{"name":"grok-4-1-fast-search","organization":"xai","score":1194.9994626746786,"low":1189.9193788418115,"high":1200.0795465075455,"observations":85919,"sourceRank":23,"publishedAt":"2026-10-13","rank":17},{"name":"claude-sonnet-5-search","organization":"anthropic","score":1193.1604234723266,"low":1186.8708636449182,"high":1199.449983299735,"observations":72978,"sourceRank":24,"publishedAt":"2026-10-13","rank":17},{"name":"grok-4.3","organization":"xai","score":1192.7901908464362,"low":1187.9289237206517,"high":1197.6514579722204,"observations":128393,"sourceRank":25,"publishedAt":"2026-10-13","rank":17},{"name":"ernie-5.1","organization":"baidu","score":1192.1436316569848,"low":1182.658270988463,"high":1201.6289923255065,"observations":4024,"sourceRank":26,"publishedAt":"2026-10-13","rank":15},{"name":"gemini-3-flash-grounding","organization":"google","score":1188.6755934523694,"low":1184.2834804728052,"high":1193.0677064319339,"observations":196399,"sourceRank":27,"publishedAt":"2026-10-13","rank":20},{"name":"gpt-5-search","organization":"openai","score":1187.7284285042017,"low":1180.3489154082597,"high":1195.1079416001437,"observations":20865,"sourceRank":28,"publishedAt":"2026-10-13","rank":19},{"name":"claude-opus-4-5-search","organization":"anthropic","score":1186.6864516500145,"low":1180.9565870292079,"high":1192.4163162708212,"observations":65047,"sourceRank":29,"publishedAt":"2026-10-13","rank":20},{"name":"gpt-5.1-search","organization":"openai","score":1183.643449814169,"low":1178.2710227259552,"high":1189.0158769023826,"observations":63042,"sourceRank":30,"publishedAt":"2026-10-13","rank":24},{"name":"claude-sonnet-4-5-search","organization":"anthropic","score":1175.9769260002347,"low":1170.7400096823358,"high":1181.2138423181336,"observations":144153,"sourceRank":31,"publishedAt":"2026-10-13","rank":28},{"name":"claude-opus-4-1-search","organization":"anthropic","score":1167.0922855846686,"low":1162.11454023824,"high":1172.0700309310976,"observations":79806,"sourceRank":32,"publishedAt":"2026-10-13","rank":31},{"name":"gpt-5.2-search","organization":"openai","score":1161.3999212920426,"low":1155.601924423676,"high":1167.1979181604092,"observations":55634,"sourceRank":33,"publishedAt":"2026-10-13","rank":32},{"name":"grok-4-fast-search","organization":"xai","score":1161.0768117467953,"low":1156.2631955645356,"high":1165.8904279290552,"observations":43083,"sourceRank":34,"publishedAt":"2026-10-13","rank":32},{"name":"claude-opus-4-search","organization":"anthropic","score":1151.8379561591457,"low":1146.2854419373705,"high":1157.3904703809208,"observations":31506,"sourceRank":35,"publishedAt":"2026-10-13","rank":33},{"name":"gemini-2.5-pro-grounding","organization":"google","score":1144.2286724716007,"low":1139.4298264295405,"high":1149.0275185136609,"observations":86689,"sourceRank":36,"publishedAt":"2026-10-13","rank":35},{"name":"ppl-sonar-pro-high","organization":"perplexity","score":1143.2159334622759,"low":1137.323793448986,"high":1149.1080734755656,"observations":28899,"sourceRank":37,"publishedAt":"2026-10-13","rank":35},{"name":"ppl-sonar-reasoning-pro-high","organization":"perplexity","score":1138.5024026440753,"low":1132.5725993432764,"high":1144.4322059448743,"observations":29439,"sourceRank":38,"publishedAt":"2026-10-13","rank":36},{"name":"gpt-5.2-search-non-reasoning","organization":"openai","score":1135.7580458647492,"low":1129.9511020452433,"high":1141.5649896842551,"observations":79796,"sourceRank":39,"publishedAt":"2026-10-13","rank":36},{"name":"grok-4-search","organization":"xai","score":1122.7389006236172,"low":1116.5543091590182,"high":1128.923492088216,"observations":19195,"sourceRank":40,"publishedAt":"2026-10-13","rank":40},{"name":"api-gpt-4o-search","organization":"openai","score":1083.3063076104124,"low":1071.882876874753,"high":1094.7297383460718,"observations":3399,"sourceRank":41,"publishedAt":"2026-10-13","rank":41},{"name":"diffbot-small-xl","organization":"diffbot","score":1062.5549337835419,"low":1053.8428778167072,"high":1071.2669897503765,"observations":6368,"sourceRank":42,"publishedAt":"2026-10-13","rank":42}],"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":"2ac3d9a63ca97bc5d8feecdd100b5de42e16a1d5d219d82e96c7d637eb69556f.parquet","sha256":"2ac3d9a63ca97bc5d8feecdd100b5de42e16a1d5d219d82e96c7d637eb69556f","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53/search_style_control/latest-00000-of-00001.parquet","revision":"8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53","role":"rows"}]},"status":"fresh"}