For frontier AI news
Powered by Code Arena

WebDev Leaderboard

Compare the performance of AI models for web development tasks built in the Code Arena
The legacy WebDev leaderboard is still available at web.lmarena.ai

Last Updated

Nov 26, 2025

Total Votes

41,430

Total Models

22

Rank Spread
(Upper-Lower)
1
1◄─►3
1493+20/-201,109
Anthropic
Proprietary
2
1◄─►3
1479+17/-171,421
Anthropic
Proprietary
3
1◄─►3
1473+11/-116,037
Google
Proprietary
4
4◄─►8
1399+12/-123,937
OpenAI
Proprietary
5
4◄─►8
1397+10/-105,376
Anthropic
Proprietary
6
4◄─►8
1395+13/-132,431
OpenAI
Proprietary
7
4◄─►8
1393+10/-105,204
Anthropic
Proprietary
8
4◄─►9
1387+10/-106,422
Anthropic
Proprietary
9
8◄─►11
1370+11/-115,035
Z.ai
MIT
10
9◄─►12
1358+11/-114,258
Moonshot
Modified MIT
11
9◄─►12
1358+11/-114,484
OpenAI
Proprietary
12
10◄─►13
1340+12/-122,793
OpenAI
Proprietary
13
12◄─►13
Minimax
1321+11/-114,956
MiniMax
Apache 2.0
14
14◄─►16
1294+11/-114,650
DeepSeek AI
MIT
15
14◄─►16
1293+11/-115,159
Alibaba
Apache 2.0
16
14◄─►16
1289+10/-105,158
Anthropic
Proprietary
17
17◄─►18
1253+16/-161,563
OpenAI
Proprietary
18
17◄─►20
1228+17/-171,534
xAI
Proprietary
19
18◄─►20
1211+12/-123,503
Google
Proprietary
20
18◄─►20
1207+19/-191,253
xAI
Proprietary
21
21◄─►22
1124+24/-24727
xAI
Proprietary
22
21◄─►22
1120+29/-29530
xAI
Proprietary

Remove Style Control Leaderboard Plots

Battle Count for Each Combination of Models (without Ties)

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

Confidence Intervals on Model Strength (via Bootstrapping)

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