Search Arena

View overall rankings across LLMs with integrated web search.

Mar 26, 2026
335,858 votes
23 models
Rank Spread
1
11
Anthropic
Anthropic · Proprietary
1254±6
16,183$5 / $251M
2
28
Google · Proprietary
1219±9
6,478N/AN/A
3
28
Anthropic
Anthropic · Proprietary
1217±6
16,232$3 / $151M
4
28
OpenAI · Proprietary
1214±6
28,427$1.75 / $14400K
5
28
Google · Proprietary
1214±5
38,332N/AN/A
6
28
Google · Proprietary
1209±5
37,364$2 / $12N/A
7
28
xAI · Proprietary
1207±6
17,142N/AN/A
8
28
OpenAI · Proprietary
1207±5
32,659$1.25 / $10400K
9
912
OpenAI · Proprietary
1177±5
33,380$1.75 / $14400K
10
912
xAI · Proprietary
1177±5
39,840$0.20 / $0.502M
11
912
Anthropic
Anthropic · Proprietary
1176±6
26,831$5 / $25200K
12
912
xAI · Proprietary
1171±4
43,002$0.20 / $0.502M
13
1318
OpenAI · Proprietary
1143±5
20,730$2 / $8200K
14
1318
Google · Proprietary
1143±4
55,388$1.25 / $101M
15
1320
Anthropic
Anthropic · Proprietary
1141±6
24,023$3 / $151M
16
1320
xAI · Proprietary
1141±6
19,321$3 / $15256K
17
1320
Anthropic
Anthropic · Proprietary
1139±4
55,048$15 / $75200K
18
1320
Perplexity · Proprietary
1139±5
29,161$1 / $1127.1K
19
1521
OpenAI · Proprietary
1132±5
20,856$1.25 / $10400K
20
1521
Perplexity · Proprietary
1130±5
28,659$1 / $1127.1K
21
1921
Anthropic
Anthropic · Proprietary
1128±5
31,164$15 / $75200K
22
2223
Diffbot · Apache 2.0
1022±8
6,410N/AN/A
23
2223
OpenAI · Proprietary
1006±11
3,416$30 / $608.2K

Default Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

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

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