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 |
|---|---|
| Kimi K3 | 1417 |
| Claude Opus 5 | 1356 |
| GPT-5.6 Sol | 1353 |
| GLM-5.2 | 1344 |
| Claude Fable 5 | 1343 |
| Opus 4.6 | 1323 |
| Opus 4.7 | 1318 |
| Gemini 3.6 Flash | 1315 |
| Grok 4.5 | 1312 |
| MiMo-V2.5-Pro | 1309 |
| Sonnet 4.6 | 1307 |
| Kimi K2.6 | 1307 |
| Qwen3.7-Max | 1307 |
| GLM-5.1 | 1305 |
| Muse Spark 1.1 | 1303 |
| Sonnet 5 | 1301 |
| GLM 5 Turbo | 1299 |
| MiMo-V2.5 | 1291 |
| Qwen3.7-Plus | 1291 |
| Kimi K2.7 Code | 1290 |
| Gemini 3.5 Flash | 1289 |
| MiniMax M3 | 1285 |
| GPT-5.5 | 1284 |
| Muse Spark | 1281 |
| GLM-5 | 1277 |
| DeepSeek-V4-Pro | 1273 |
| Opus 4.5 | 1272 |
| Opus 4.8 | 1271 |
| Gemini 3 Pro Preview | 1271 |
| Nex-N2-Pro | 1270 |
| Kimi K2.5 | 1267 |
| GPT-5.6 Terra | 1266 |
| Qwen3.6 Plus (2026-04-02) | 1264 |
| MiniMax M2.7 | 1263 |
| Gemini 3.1 Pro Preview | 1259 |
| GLM 5V Turbo | 1259 |
| GPT-5.6 Luna | 1253 |
| Grok 4.20 | 1248 |
| GLM-4.7 | 1246 |
| GPT-5.4 | 1241 |