WebDev Arena Leaderboard
WebDev Arena is a real-time AI coding competition where models go head-to-head in web development challenges, developed by LMArena
Leaderboard
Arena Score
1419.95
License
Proprietary
95% CI
+19.28 / -17.23
Votes
2,053
Anthropic
Arena Score
1357.10
License
Proprietary
95% CI
+9.79 / -9.53
Votes
7,481
Arena Score
1272.86
License
Proprietary
95% CI
+6.51 / -6.60
Votes
9,390
OpenAI
Arena Score
1261.35
License
Proprietary
95% CI
+8.28 / -9.36
Votes
4,083
Anthropic
Arena Score
1237.84
License
Proprietary
95% CI
+4.08 / -4.27
Votes
26,338
DeepSeek
Arena Score
1206.85
License
MIT
95% CI
+21.10 / -17.84
Votes
1,097
DeepSeek
Arena Score
1198.71
License
MIT
95% CI
+11.23 / -9.85
Votes
3,760
OpenAI
Arena Score
1188.56
License
Proprietary
95% CI
+10.18 / -14.14
Votes
2,299
OpenAI
Arena Score
1187.08
License
Proprietary
95% CI
+11.37 / -14.69
Votes
2,195

Alibaba
Arena Score
1185.64
License
Apache 2.0
95% CI
+24.46 / -17.67
Votes
706
Arena Score
1145.13
License
Proprietary
95% CI
+12.62 / -10.09
Votes
2,186
xAI
Arena Score
1142.85
License
Proprietary
95% CI
+7.74 / -6.56
Votes
6,284
OpenAI
Arena Score
1136.37
License
Proprietary
95% CI
+11.68 / -11.34
Votes
2,984
Anthropic
Arena Score
1133.26
License
Proprietary
95% CI
+5.60 / -5.47
Votes
20,567
OpenAI
Arena Score
1093.02
License
Proprietary
95% CI
+11.33 / -17.49
Votes
1,300
OpenAI
Arena Score
1091.78
License
Proprietary
95% CI
+9.00 / -6.15
Votes
6,391
Arena Score
1088.91
License
Proprietary
95% CI
+5.55 / -5.07
Votes
11,936
OpenAI
Arena Score
1045.00
License
Proprietary
95% CI
+7.15 / -6.68
Votes
9,271
OpenAI
Arena Score
1041.94
License
Proprietary
95% CI
+6.03 / -5.87
Votes
13,828
Arena Score
1039.32
License
Proprietary
95% CI
+6.03 / -6.26
Votes
9,952
Arena Score
1029.71
License
Proprietary
95% CI
+19.70 / -19.92
Votes
1,064
Arena Score
1015.27
License
Llama 4
95% CI
+8.75 / -11.11
Votes
4,103
Arena Score
980.31
License
Proprietary
95% CI
+6.62 / -6.54
Votes
14,485

Alibaba
Arena Score
974.69
License
Proprietary
95% CI
+7.65 / -6.58
Votes
10,845
OpenAI
Arena Score
964.00
License
Proprietary
95% CI
+4.25 / -5.90
Votes
18,637
DeepSeek
Arena Score
959.89
License
DeepSeek
95% CI
+7.75 / -8.92
Votes
7,717

Alibaba
Arena Score
902.33
License
Apache 2.0
95% CI
+4.80 / -4.63
Votes
16,252
Arena Score
899.84
License
Llama 4
95% CI
+26.91 / -30.08
Votes
692
Arena Score
892.56
License
Proprietary
95% CI
+5.65 / -6.43
Votes
15,201
Arena Score
809.72
License
Llama 3.1
95% CI
+13.46 / -19.68
Votes
1,117
More Statistics for WebDev Arena (Overall)
Confidence Interval for Model Strength
Figure 1
Average Win Rate Against All Other Models (Assuming Uniform Sampling and No Ties)
Figure 2
Fraction of Model A Wins for All Non-tied A vs. B Battles
Figure 3
Battle Count for Each Combination of Models (without Ties)
Figure 4