LMArena WebDev Arena — leaderboard
LMArena's WebDev Arena leaderboard for model performance on interactive web development tasks judged by human preference.
Metric: Arena rating (self-reported). Source: benchmarklist.com. Status: saturation imminent. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 1567.85 |
| 2 | Claude Opus 4.6 | 1548.84 |
| 3 | GLM-5.1 | 1531.7 |
| 4 | Claude Sonnet 4.6 | 1526.17 |
| 5 | Muse Spark | 1509.38 |
| 6 | Claude Opus 4.5 (20251101) (Thinking 32K) | 1490.6 |
| 7 | GPT-5.5 (High) | 1490.28 |
| 8 | MiMo-V2.5-Pro | 1476.42 |
| 9 | Claude Opus 4.5 | 1467.21 |
| 10 | Qwen 3.6 Plus | 1463.97 |
| 11 | GPT-5.4 (High) | 1456.78 |
| 12 | Gemini 3.1 Pro (Preview) | 1454.71 |
| 13 | DeepSeek V4 Pro | 1454.67 |
| 14 | MiMo-V2.5 | 1445.56 |
| 15 | GLM-4.7 | 1439.9 |
Interactive version: theaggregate.ai/benchmark?slug=lmarena-webdev-arena · How the rankings work · Data refreshed daily, snapshot 2026-07-22.