Design Arena (Game Dev): leaderboard
Crowdsourced arena for AI game development. Models generate browser games and are ranked by Elo from human votes.
Metric: Elo. Source: www.designarena.ai. Saturation forecast: Around December 2027. 182 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra (Max) | 1475 | #6 (GPT-6 Astra) |
| 2 | Claude Sonnet 5.5 | 1474 | #11 |
| 3 | Claude Opus 5.5 | 1457 | #3 |
| 4 | GPT-6 Astra | 1450 | #6 |
| 5 | GPT-6.1 Sol | 1391 | #7 |
| 6 | Claude Fable 5.1 | 1381 | #9 |
| 7 | Muse Wonder | 1378 | #15 |
| 8 | Gemini 4 Argon | 1373 | #8 |
| 9 | GPT-5.6 Sol (xHigh) | 1369 | #19 (GPT-5.6 Sol) |
| 10 | Kimi K3 | 1362 | #30 |
| 11 | Muse Spark 1.3 (Max) | 1344 | #24 (Muse Spark 1.3) |
| 12 | Claude Opus 5 | 1338 | #12 |
| 13 | Claude Fable 5 | 1335 | #16 |
| 14 | DeepSeek V4.1 Flash | 1330 | #36 |
| 15 | Muse Spark 1.3 | 1328 | #24 |
No result here: #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=design-arena-game-dev · How It Works · Data refreshed daily, snapshot 2026-10-20.