Atlas

Benchmarks

← All benchmarks

LMArena Code Arena WebDev

Code · 2024-12-10

LMArena Code Arena WebDev is an arena-style leaderboard where users compare generated websites and web apps from anonymous model outputs. Scores are reported as Elo ratings for the web-development track.

Top models (higher is better)

ModelScore
Claude Opus 5.51807
GPT-6 Astra1774
Claude Sonnet 5.51769
GPT-6.1 Sol1749
Claude Fable 5.11742
Muse Wonder Full1726
Kimi K3.1 Pro1692
Claude Opus 51691
GPT-6 Sol1681
Gemini 4 Argon1674
Qwen3.8 Max (0902)1673
Qwen3.8-Max1672
DeepSeek V4.1 Flash 10171665
Muse Spark 1.31657
Kimi K31655
Muse Wonder1651
Grok 4.71638
MiMo-V2.6-Flash1635
Hy4 Preview1631
Qwen3.8-Flash-Next1629
MiMo-V2.6-Pro1625
Claude Fable 51624
GLM-5.31623
DeepSeek V4.1 Flash1619
Grok 4.61617
GPT-5.6 Sol1615
GLM-5.3 Flash1608
GLM-5.21604
Qwen3.8 27B1591
Gemini 3.7 Flash1590
MiniMax M3.1 Flash1589
Claude Haiku 5.51586
Gemini 3.8 Flash1585
DeepSeek V4 Pro 08131582
DeepSeek-V4-Flash1582
GPT-6 Luna1579
Opus 4.71558
Opus 4.81556
Grok 4.51553
Opus 4.61546
Loading Atlas data…