{"config":"search_factuality","id":"arena-search-factuality","title":"Search · factuality","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":1251.1261531398063,"low":1246.2813217060154,"high":1255.9709845735974,"observations":60437,"sourceRank":1,"publishedAt":"2026-10-13","rank":1},{"name":"gpt-5.5-search","organization":"openai","score":1247.3240553682674,"low":1243.4364654495268,"high":1251.2116452870082,"observations":125914,"sourceRank":2,"publishedAt":"2026-10-13","rank":1},{"name":"qwen3.8-max","organization":"alibaba","score":1240.4501656798468,"low":1228.60890599359,"high":1252.2914253661036,"observations":1870,"sourceRank":3,"publishedAt":"2026-10-13","rank":1},{"name":"gpt-6-astra-max","organization":"openai","score":1239.9232504445981,"low":1233.5774748278186,"high":1246.2690260613779,"observations":18483,"sourceRank":4,"publishedAt":"2026-10-13","rank":2},{"name":"gpt-6.1-sol-max","organization":"openai","score":1236.129982032647,"low":1228.3062404318575,"high":1243.9537236334363,"observations":5555,"sourceRank":5,"publishedAt":"2026-10-13","rank":2},{"name":"claude-opus-4-6-search","organization":"anthropic","score":1226.8209371049832,"low":1223.6029109121143,"high":1230.038963297852,"observations":173142,"sourceRank":6,"publishedAt":"2026-10-13","rank":4},{"name":"gpt-5.2-search","organization":"openai","score":1224.005868650217,"low":1220.1164166136575,"high":1227.8953206867766,"observations":55464,"sourceRank":7,"publishedAt":"2026-10-13","rank":6},{"name":"claude-fable-5.1-high","organization":"anthropic","score":1221.5332448639508,"low":1215.3960703690125,"high":1227.670419358889,"observations":12782,"sourceRank":8,"publishedAt":"2026-10-13","rank":6},{"name":"grok-4.5","organization":"xai","score":1219.91547354011,"low":1215.4432707198396,"high":1224.3876763603805,"observations":76458,"sourceRank":9,"publishedAt":"2026-10-13","rank":6},{"name":"claude-opus-5-high","organization":"anthropic","score":1216.8634055718924,"low":1210.7115727987236,"high":1223.0152383450613,"observations":13285,"sourceRank":10,"publishedAt":"2026-10-13","rank":7},{"name":"ernie-5.1","organization":"baidu","score":1213.7607212719247,"low":1204.7083718164429,"high":1222.8130707274065,"observations":4024,"sourceRank":11,"publishedAt":"2026-10-13","rank":7},{"name":"gpt-5.4-search","organization":"openai","score":1212.9433551367517,"low":1209.1003505108486,"high":1216.786359762655,"observations":126672,"sourceRank":12,"publishedAt":"2026-10-13","rank":8},{"name":"claude-fable-5-high","organization":"anthropic","score":1212.313325307199,"low":1207.3230864173831,"high":1217.303564197015,"observations":73596,"sourceRank":13,"publishedAt":"2026-10-13","rank":8},{"name":"claude-opus-4-7","organization":"anthropic","score":1210.1814290866187,"low":1206.4439424328925,"high":1213.9189157403448,"observations":127472,"sourceRank":14,"publishedAt":"2026-10-13","rank":10},{"name":"claude-opus-5.5-medium","organization":"anthropic","score":1205.1854865084692,"low":1198.8639197195323,"high":1211.507053297406,"observations":10842,"sourceRank":15,"publishedAt":"2026-10-13","rank":10},{"name":"gpt-5.1-search","organization":"openai","score":1203.4798361951696,"low":1199.4296488766329,"high":1207.530023513706,"observations":62869,"sourceRank":16,"publishedAt":"2026-10-13","rank":12},{"name":"claude-sonnet-4-6-search","organization":"anthropic","score":1201.7651878373258,"low":1198.3659893412841,"high":1205.1643863333677,"observations":173930,"sourceRank":17,"publishedAt":"2026-10-13","rank":14},{"name":"gpt-5.2-search-non-reasoning","organization":"openai","score":1197.9600354855127,"low":1194.705463507943,"high":1201.2146074630825,"observations":79609,"sourceRank":18,"publishedAt":"2026-10-13","rank":15},{"name":"gpt-6-sol-max","organization":"openai","score":1197.853076142792,"low":1191.9358148913634,"high":1203.7703373942204,"observations":11313,"sourceRank":19,"publishedAt":"2026-10-13","rank":15},{"name":"grok-4.20-multi-agent-beta-0309","organization":"xai","score":1197.7694921824843,"low":1193.5959307652308,"high":1201.9430535997378,"observations":126186,"sourceRank":20,"publishedAt":"2026-10-13","rank":15},{"name":"claude-opus-4-8","organization":"anthropic","score":1197.288460207515,"low":1192.837396754964,"high":1201.7395236600662,"observations":106304,"sourceRank":21,"publishedAt":"2026-10-13","rank":15},{"name":"gemini-3.1-pro-grounding","organization":"google","score":1196.986735070811,"low":1193.3040863058282,"high":1200.6693838357937,"observations":151380,"sourceRank":22,"publishedAt":"2026-10-13","rank":15},{"name":"grok-4.20-beta1","organization":"xai","score":1195.7695341342787,"low":1191.3104938178599,"high":1200.2285744506976,"observations":56876,"sourceRank":23,"publishedAt":"2026-10-13","rank":15},{"name":"gemini-3-pro-grounding","organization":"google","score":1193.4494706965304,"low":1188.6609541498674,"high":1198.2379872431934,"observations":38729,"sourceRank":24,"publishedAt":"2026-10-13","rank":18},{"name":"gpt-6-luna-max","organization":"openai","score":1182.9991604798056,"low":1177.0841208012985,"high":1188.9142001583127,"observations":10793,"sourceRank":25,"publishedAt":"2026-10-13","rank":24},{"name":"claude-sonnet-5-search","organization":"anthropic","score":1181.752684101282,"low":1176.9168156188468,"high":1186.588552583717,"observations":72978,"sourceRank":26,"publishedAt":"2026-10-13","rank":25},{"name":"claude-opus-4-5-search","organization":"anthropic","score":1180.9083901179845,"low":1176.564279428831,"high":1185.2525008071382,"observations":64860,"sourceRank":27,"publishedAt":"2026-10-13","rank":25},{"name":"gemini-3-flash-grounding","organization":"google","score":1179.130913953767,"low":1175.7248662472066,"high":1182.5369616603277,"observations":196216,"sourceRank":28,"publishedAt":"2026-10-13","rank":25},{"name":"grok-4.3","organization":"xai","score":1174.9909800023322,"low":1171.242391705949,"high":1178.7395682987155,"observations":128393,"sourceRank":29,"publishedAt":"2026-10-13","rank":25},{"name":"claude-sonnet-4-5-search","organization":"anthropic","score":1162.4908899000363,"low":1158.512300037746,"high":1166.469479762327,"observations":143960,"sourceRank":30,"publishedAt":"2026-10-13","rank":30},{"name":"gemini-2.5-pro-grounding","organization":"google","score":1162.4000065598693,"low":1158.917386349332,"high":1165.8826267704067,"observations":69356,"sourceRank":31,"publishedAt":"2026-10-13","rank":30},{"name":"ppl-sonar-reasoning-pro-high","organization":"perplexity","score":1155.5795284388591,"low":1149.1448434671738,"high":1162.0142134105445,"observations":12927,"sourceRank":32,"publishedAt":"2026-10-13","rank":30},{"name":"claude-opus-4-1-search","organization":"anthropic","score":1154.0944592569458,"low":1150.0238784586184,"high":1158.1650400552733,"observations":62796,"sourceRank":33,"publishedAt":"2026-10-13","rank":32},{"name":"grok-4-1-fast-search","organization":"xai","score":1152.0171363145819,"low":1148.1781119904344,"high":1155.8561606387293,"observations":85736,"sourceRank":34,"publishedAt":"2026-10-13","rank":32},{"name":"grok-4-fast-search","organization":"xai","score":1145.9959816306748,"low":1141.229627197386,"high":1150.7623360639639,"observations":30673,"sourceRank":35,"publishedAt":"2026-10-13","rank":32},{"name":"gpt-5-search","organization":"openai","score":1143.969754345008,"low":1134.478347488074,"high":1153.4611612019419,"observations":4004,"sourceRank":36,"publishedAt":"2026-10-13","rank":32},{"name":"claude-opus-4-search","organization":"anthropic","score":1139.600002451387,"low":1133.5276684272822,"high":1145.6723364754919,"observations":14486,"sourceRank":37,"publishedAt":"2026-10-13","rank":35},{"name":"ppl-sonar-pro-high","organization":"perplexity","score":1132.6319645225485,"low":1126.1446816031698,"high":1139.1192474419272,"observations":12844,"sourceRank":38,"publishedAt":"2026-10-13","rank":36},{"name":"grok-4-search","organization":"xai","score":1131.1332887899255,"low":1120.610809409027,"high":1141.6557681708236,"observations":3189,"sourceRank":39,"publishedAt":"2026-10-13","rank":35},{"name":"o3-search","organization":"openai","score":1129.2264031032428,"low":1119.1312713267773,"high":1139.3215348797085,"observations":3818,"sourceRank":40,"publishedAt":"2026-10-13","rank":36}],"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":"c4588e6f78f5a65444d1fde2bb0733e8ccdabb46db2af7e6345c631eefe90e5a.parquet","sha256":"c4588e6f78f5a65444d1fde2bb0733e8ccdabb46db2af7e6345c631eefe90e5a","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53/search_factuality/latest-00000-of-00001.parquet","revision":"8b6deb69ace01ee8dcda9e46eba7a5e8a808ec53","role":"rows"}]},"status":"fresh"}