Search Arena | Overall

View overall rankings across LLMs with integrated web search.

Feb 25, 2026
247,944 votes
22 models
Rank Spread
1
11
Anthropic
Anthropic · Proprietary
1255±10
3,607
2
25
xAI · Proprietary
1225±8
4,687
3
27
OpenAI · Proprietary
1219±6
20,150
4
27
Google · Proprietary
1218±6
25,311
5
27
Google · Proprietary
1214±5
31,966
6
37
OpenAI · Proprietary
1210±6
23,283
7
37
Anthropic
Anthropic · Proprietary
1203±10
3,602
8
811
OpenAI · Proprietary
1183±6
20,045
9
811
xAI · Proprietary
1181±5
26,758
10
811
xAI · Proprietary
1173±4
42,193
11
811
Anthropic
Anthropic · Proprietary
1170±6
15,488
12
1218
OpenAI · Proprietary
1143±5
20,407
13
1217
Google · Proprietary
1143±4
45,483
14
1218
xAI · Proprietary
1142±5
19,018
15
1218
Perplexity
Perplexity · Proprietary
1141±5
28,673
16
1220
Anthropic
Anthropic · Proprietary
1138±7
14,385
17
1220
Anthropic
Anthropic · Proprietary
1138±4
44,888
18
1320
OpenAI · Proprietary
1133±5
20,519
19
1620
Perplexity
Perplexity · Proprietary
1131±5
28,131
20
1620
Anthropic
Anthropic · Proprietary
1129±5
30,695
21
2122
Diffbot · Apache 2.0
1024±8
6,378
22
2122
OpenAI · Proprietary
1006±11
3,375

Default Leaderboard Plots

Battle Count for Each Combination of Models (without Ties)

Fraction of Model A Wins for All Non-tied A vs. B Battles

Confidence Intervals on Model Strength (via Bootstrapping)

Average Win Rate Against All Other Models (Uniform Sampling and No Ties)