Valumigo

LMArena · AI search

We regularly fetch and display public benchmark data: LMArena user voting rankings, Epoch AI test scores, and OpenRouter usage rankings. Each leaderboard shows both its publication date and the date we retrieved it. These scores are not assigned by this site.

LMArena scores come from people comparing two models' answers side by side and voting for the better one, using an Elo-based system. If score differences fall within the confidence intervals, treat the models as roughly comparable.

How to read this leaderboard

What it measures: A ranking based on votes comparing answers from AI systems that use web search. It covers various search-based requests, including questions about current information.

How to read the score: A relative score reflecting which search answers users preferred. Distinguish the basic preference score from the Factuality-adjusted metric, which also accounts for factual accuracy.

Caveats: Check the update date, search tools and execution conditions. Do not interpret this score as the accuracy of all search answers from an actual service.

Insights from this ranking

  • The 95% confidence intervals for 1st-place gpt-5.6-sol-xhigh and 2nd-place claude-opus-4-6-search overlap. This aggregation alone does not clearly establish their order.
  • Anthropic has the most models among the top 10, with 4.
  • The 1st-place model received 29,663 votes, and this leaderboard includes 34 models.

AI search LMArena

Published 2026-08-24 · Retrieved 2026-10-04

114011701200123012601290
Ogpt-5.6-sol-xhigh
1257
Anthropicclaude-opus-4-6-search
1253
Ogpt-5.5-search
1242
Anthropicclaude-opus-4-7
1233
Anthropicclaude-fable-5
1230
Baiduernie-5.1
1227
Anthropicclaude-sonnet-4-6-search
1221
xgrok-4.5
1213
Googlegemini-3.1-pro-grounding
1210
Googlegemini-3-pro-grounding
1207
Ogpt-5.2-search
1207
Anthropicclaude-opus-4-8
1204
xgrok-4.20-multi-agent-beta-0309
1204
Ogpt-5.1-search
1199
Googlegemini-3-flash-grounding
1198
Ogpt-5.4-search
1197
Anthropicclaude-sonnet-5-search
1194
xgrok-4.20-beta1
1189
Anthropicclaude-opus-4-5-search
1180
Ogpt-5.2-search-non-reasoning
1172

Dots show scores; horizontal lines show 95% confidence intervals. Overlapping intervals suggest similar performance. The chart shows only the highest-scoring reasoning setting, such as high or max, for each model. The table shows rankings for all settings.

Top ranking by company

  • OOpenAIgpt-5.6-sol-xhigh#1
  • AnthropicAnthropicclaude-opus-4-6-search#2
  • BaiduBaiduernie-5.1#6
  • xxAIgrok-4.5#8
  • GoogleGooglegemini-3.1-pro-grounding#9
  • PerplexityPerplexityppl-sonar-reasoning-pro-high#29
  • DDiffbotdiffbot-small-xl#33
View table (top 50)
RankModelDeveloperScore95% confidence intervalVotes
1#1Ogpt-5.6-sol-xhighOpenAI12571250–126529,663
2#2Anthropicclaude-opus-4-6-searchAnthropic12531248–1258134,699
3#3Ogpt-5.5-searchOpenAI12421237–124789,873
4#4Anthropicclaude-opus-4-7Anthropic12331228–123991,394
5#5Anthropicclaude-fable-5Anthropic12301222–123841,795
6#6Baiduernie-5.1Baidu12271217–12373,788
7#7Anthropicclaude-sonnet-4-6-searchAnthropic12211216–1226134,905
8#8xgrok-4.5xAI12131206–122031,505
9#9Googlegemini-3.1-pro-groundingGoogle12101205–1216113,282
10#10Googlegemini-3-pro-groundingGoogle12071202–121337,024
11#11Ogpt-5.2-searchOpenAI12071201–121352,712
12#12Anthropicclaude-opus-4-8Anthropic12041198–121170,998
13#13xgrok-4.20-multi-agent-beta-0309xAI12041199–1209109,553
14#14Ogpt-5.1-searchOpenAI11991194–120559,909
15#15Googlegemini-3-flash-groundingGoogle11981193–1203149,334
16#16Ogpt-5.4-searchOpenAI11971192–1203110,116
17#17Anthropicclaude-sonnet-5-searchAnthropic11941187–120140,230
18#18xgrok-4.20-beta1xAI11891183–119553,921
19#19Anthropicclaude-opus-4-5-searchAnthropic11801174–118561,573
20#20Ogpt-5.2-search-non-reasoningOpenAI11721167–117875,658
21#21xgrok-4-1-fast-searchxAI11711166–117681,507
22#22xgrok-4-fast-searchxAI11711166–117541,794
23#23xgrok-4.3xAI11651160–117091,483
24#24Anthropicclaude-sonnet-4-5-searchAnthropic11581153–1163127,378
25#25Anthropicclaude-opus-4-1-searchAnthropic11481143–115376,933
26#26Oo3-searchOpenAI11441139–115020,644
27#27Googlegemini-2.5-pro-groundingGoogle11421137–114683,404
28#28xgrok-4-searchxAI11421136–114719,108
29#29Perplexityppl-sonar-reasoning-pro-highPerplexity11391133–114429,055
30#30Ogpt-5-searchOpenAI11331127–113920,781
31#31Perplexityppl-sonar-pro-highPerplexity11301124–113628,519
32#32Anthropicclaude-opus-4-searchAnthropic11261121–113231,037
33#33Ddiffbot-small-xlDiffbot10231014–10316,388
34#34Oapi-gpt-4o-searchOpenAI1006995–10173,411

Data: LMArena leaderboard dataset (CC BY 4.0). Changes: Top 50 entries per leaderboard; scores are rounded. https://huggingface.co/datasets/lmarena-ai/leaderboard-datasetCompany logos are trademarks of their respective owners and are used only for identification (icons: Simple Icons).Data: Epoch AI — Capabilities & benchmarking (CC BY 4.0). https://epoch.ai/benchmarksSource: OpenRouter (openrouter.ai/rankings), as of 2026-10-04. Licensed under CC BY 4.0. https://openrouter.ai/rankings