Design Arena Overall Code Categories
Code
Design Arena Overall Code Categories aggregates blind, pairwise human preferences across Website, UI Component, Game Development, Data Visualization, and 3D tasks, each produced as a single-file HTML output. The leaderboard converts head-to-head results into Bradley–Terry Elo ratings.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5.5 | 1385 |
| GPT-6 Astra | 1384 |
| Muse Wonder | 1381 |
| Kimi K3 | 1359 |
| GPT-6.1 Sol | 1357 |
| Kimi K3.1 Pro | 1354 |
| Claude Sonnet 5.5 | 1352 |
| Muse Spark 1.3 | 1351 |
| GPT-5.6 Sol | 1340 |
| Claude Fable 5.1 | 1334 |
| Gemini 4 Argon | 1330 |
| Claude Opus 5 | 1323 |
| DeepSeek V4.1 Flash | 1318 |
| MiMo-V2.6-Pro | 1316 |
| Muse Spark 1.2 | 1311 |
| Claude Fable 5 | 1309 |
| Gemini 3.7 Flash | 1306 |
| Ling 3.1 Flash | 1303 |
| Gemini 3.8 Flash | 1302 |
| Muse Spark Open | 1300 |
| GLM-5.3 | 1299 |
| MiniMax M3.1 Flash | 1298 |
| GPT-6.1 Terra | 1296 |
| GPT-6 Sol | 1296 |
| Grok 4.6 | 1290 |
| DeepSeek V4.1 Flash 1017 | 1289 |
| Gemini 3.6 Flash | 1289 |
| Opus 4.6 | 1287 |
| GLM-5.2 | 1285 |
| Claude Haiku 5.5 | 1280 |
| GLM-5.3 Flash | 1279 |
| Muse Spark 1.1 | 1275 |
| Sonnet 4.6 | 1274 |
| Sonnet 5 | 1274 |
| Grok 4.5 | 1274 |
| Qwen3.7-Max (source unspecified) | 1274 |
| Grok 4.7 | 1270 |
| Kimi K2.6 | 1270 |
| GLM-5.1 | 1267 |
| Qwen3.7-Plus (source unspecified) | 1267 |