Atlas

Benchmarks

← All benchmarks

Arena Code WebDev — Brand & Marketing

Code

Arena Code WebDev rating for brand, marketing, and informational websites. Anonymous generated experiences are compared through blind pairwise user votes.

Top models (higher is better)

ModelScore
Kimi K31705
Claude Opus 51672
Claude Fable 51623
GLM-5.21612
DeepSeek-V4-Flash1597
Opus 4.71565
Opus 4.81560
Sonnet 51559
Grok 4.51543
Opus 4.61536
Kimi K2.61527
Gemini 3.6 Flash1527
MiniMax M31526
Hy31526
Muse Spark 1.11524
Sonnet 4.61522
GLM-5.11502
Kimi K2.7 Code1500
Gemini 3.5 Flash1491
Opus 4.51467
Inkling1465
Gemini 3.1 Pro Preview1462
MiMo-V2.5-Pro1461
Gemini 3 Pro Preview1461
DeepSeek-V4-Pro1457
Kimi K2.51455
Qwen3.6 Plus (2026-04-02)1453
Gemini 3 Flash Preview1450
GLM-4.71449
MiMo-V2.51443
GLM-51434
GPT-51433
MiMo-V2-Pro1430
GLM 5V Turbo1410
MiniMax M2.71406
Qwen3.5 397B A17B1398
Gemma 4 26B A4B1396
GPT-5.21396
GPT-5.11394
GPT-5.4 Mini1394
Loading Atlas data…