Atlas

Benchmarks

← All benchmarks

Arena Code WebDev — Frontend

Code

Arena Code WebDev rating for front-end web development tasks: multi-step reasoning, tool use and HTML or React code generation. It holds most overall WebDev votes and nearly duplicates the overall board, so it is a component of the WebDev family.

Top models (higher is better)

ModelScore
Claude Opus 5.51849
Claude Sonnet 5.51806
GPT-6 Astra1795
Claude Fable 5.11777
GPT-6.1 Sol1767
Muse Wonder Full1743
Claude Opus 51712
GPT-6 Sol1688
Qwen3.8 Max (0902)1686
Gemini 4 Argon1685
Qwen3.8-Max1679
DeepSeek V4.1 Flash 10171673
Muse Spark 1.31673
Kimi K31669
Grok 4.71660
Muse Wonder1657
MiMo-V2.6-Flash1652
Hy4 Preview1651
Qwen3.8-Flash-Next1647
GLM-5.31639
Claude Fable 51637
MiMo-V2.6-Pro1637
Grok 4.61630
DeepSeek V4.1 Flash1630
GPT-5.6 Sol1623
GLM-5.3 Flash1621
GLM-5.21614
Claude Haiku 5.51603
MiniMax M3.1 Flash1602
Qwen3.8 27B1598
Gemini 3.7 Flash1593
DeepSeek V4 Pro 08131590
Gemini 3.8 Flash1589
GPT-6 Luna1585
DeepSeek-V4-Flash1585
Opus 4.71563
Grok 4.51563
Opus 4.81560
Mistral Large 4 Preview1551
Opus 4.61548
Loading Atlas data…