Atlas

Benchmarks

← All benchmarks

Arena Code WebDev — Data & Analytics

Code

Arena Code WebDev rating for data and analytics applications. Anonymous generated applications are compared through blind pairwise user votes.

Top models (higher is better)

ModelScore
GPT-6 Astra1683
Claude Opus 5.51680
GPT-6.1 Sol1654
Muse Wonder Full1632
GPT-6 Sol1616
Qwen3.8-Max1615
Claude Fable 5.11615
Gemini 4 Argon1612
Claude Sonnet 5.51610
Qwen3.8 Max (0902)1607
Kimi K3.1 Pro1606
Claude Opus 51604
DeepSeek V4.1 Flash 10171600
Muse Wonder1593
Muse Spark 1.31588
Kimi K31579
Gemini 3.7 Flash1577
Qwen3.8-Flash-Next1571
GPT-5.6 Sol1568
MiMo-V2.6-Pro1568
GLM-5.31565
Grok 4.61562
DeepSeek V4.1 Flash1560
Grok 4.71556
Hy4 Preview1555
Claude Fable 51553
MiMo-V2.6-Flash1553
Gemini 3.8 Flash1553
GLM-5.3 Flash1551
Qwen3.8 27B1551
GLM-5.21546
DeepSeek-V4-Flash1539
GPT-6 Luna1539
MiniMax M3.1 Flash1539
Muse Spark 1.11537
DeepSeek V4 Pro 08131534
Opus 4.71529
Grok 4.51521
Gemini 3.6 Flash1521
Opus 4.81520
Loading Atlas data…