Arena Code WebDev — Simulations
Code
Arena Code WebDev rating for interactive simulations. Anonymous generated simulations are compared through blind pairwise user votes.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5 | 1748 |
| Kimi K3 | 1707 |
| Claude Fable 5 | 1677 |
| GLM-5.2 | 1609 |
| Grok 4.5 | 1598 |
| Opus 4.8 | 1588 |
| DeepSeek-V4-Flash | 1581 |
| Opus 4.7 | 1573 |
| Opus 4.6 | 1567 |
| GLM-5.1 | 1561 |
| Gemini 3.6 Flash | 1560 |
| Sonnet 5 | 1553 |
| Muse Spark 1.1 | 1549 |
| Hy3 | 1532 |
| Sonnet 4.6 | 1525 |
| Gemini 3.5 Flash | 1517 |
| Kimi K2.6 | 1500 |
| MiMo-V2.5-Pro | 1487 |
| Gemini 3.1 Pro Preview | 1471 |
| Kimi K2.7 Code | 1471 |
| MiniMax M3 | 1470 |
| Qwen3.6 Plus (2026-04-02) | 1468 |
| Opus 4.5 | 1464 |
| Gemini 3 Pro Preview | 1452 |
| DeepSeek-V4-Pro | 1446 |
| GLM-5 | 1441 |
| MiniMax M2.5 | 1436 |
| MiMo-V2-Pro | 1434 |
| GPT-5.4 | 1432 |
| Kimi K2.5 | 1429 |
| GPT-5.3-Codex | 1423 |
| GPT-5.2 | 1419 |
| Gemini 3 Flash Preview | 1417 |
| MiMo-V2.5 | 1416 |
| GPT-5.4 Mini | 1410 |
| GLM-4.7 | 1403 |
| Qwen3.5 397B A17B | 1390 |
| MiniMax M2.7 | 1384 |
| Sonnet 4.5 | 1383 |
| GPT-5 | 1381 |