Atlas

Benchmarks

← All benchmarks

Arena Code WebDev — Content Creation Tools

Code

Arena Code WebDev rating for content-creation and editing tools. Anonymous generated applications are compared through blind pairwise user votes.

Top models (higher is better)

ModelScore
Claude Opus 5.51768
GPT-6 Astra1741
GPT-6.1 Sol1716
Claude Sonnet 5.51709
Claude Fable 5.11705
Muse Wonder Full1695
Gemini 4 Argon1676
Claude Opus 51662
GPT-6 Sol1649
DeepSeek V4.1 Flash 10171647
Qwen3.8-Max1636
Kimi K3.1 Pro1632
Qwen3.8 Max (0902)1625
Muse Spark 1.31612
Kimi K31611
Claude Fable 51608
DeepSeek V4.1 Flash1602
Grok 4.71602
Muse Wonder1601
GPT-5.6 Sol1594
MiMo-V2.6-Pro1585
MiMo-V2.6-Flash1584
MiniMax M3.1 Flash1581
GLM-5.31580
Grok 4.61577
Gemini 3.7 Flash1574
Qwen3.8-Flash-Next1570
GLM-5.21569
Claude Haiku 5.51568
Hy4 Preview1564
DeepSeek-V4-Flash1562
GPT-6 Luna1559
Qwen3.8 27B1556
GLM-5.3 Flash1554
Gemini 3.8 Flash1554
Opus 4.81554
Grok 4.51553
DeepSeek V4 Pro 08131546
Opus 4.71545
Muse Spark 1.21543
Loading Atlas data…