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 51705
Kimi K31676
Claude Fable 51630
GLM-5.21586
DeepSeek-V4-Flash1577
Opus 4.81566
Opus 4.71561
Grok 4.51549
Opus 4.61545
Sonnet 51542
Muse Spark 1.11536
Gemini 3.6 Flash1533
Sonnet 4.61523
Hy31517
GLM-5.11516
Kimi K2.61510
Gemini 3.5 Flash1492
MiniMax M31491
MiMo-V2.5-Pro1474
Kimi K2.7 Code1473
Opus 4.51467
Qwen3.6 Plus (2026-04-02)1458
Gemini 3.5 Flash-Lite1452
Gemini 3.1 Pro Preview1447
DeepSeek-V4-Pro1446
Gemini 3 Pro Preview1438
Gemini 3 Flash Preview1438
Kimi K2.51436
MiMo-V2.51435
GLM-51435
GLM-4.71433
MiMo-V2-Pro1433
GPT-5.21419
GPT-51419
Inkling1411
GPT-5.3-Codex1409
Qwen3.5 397B A17B1400
GLM 5V Turbo1399
GPT-5.4 Mini1399
MiniMax M2.71398
Loading Atlas data…