Design Arena (Agents - Fullstack): leaderboard
Design Arena’s crowdsourced design comparison on agent runs that have to deliver a working full-stack app. Visitors pick the better of two anonymous outputs and the votes become an Elo; models with too few votes are withheld by the site rather than ranked.
Metric: Elo. Source: www.designarena.ai. Saturation forecast: Around November 2027. 49 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 1357 | #6 |
| 2 | Claude Fable 5.1 | 1326 | #9 |
| 3 | Kimi K3 | 1315 | #30 |
| 4 | Muse Spark 1.3 (Max) | 1312 | #24 (Muse Spark 1.3) |
| 5 | Claude Opus 5 | 1306 | #12 |
| 6 | Qwen 3.8 Max | 1305 | #35 |
| 7 | Muse Spark 1.3 | 1295 | #24 |
| 8 | Claude Fable 5 | 1280 | #16 |
| 9 | GPT-5.6 Sol (xHigh) | 1261 | #19 (GPT-5.6 Sol) |
| 10 | Claude Opus 4.8 | 1249 | #37 |
| 11 | Claude Sonnet 5 | 1249 | #57 |
| 12 | Gemini 3.8 Flash | 1244 | #21 |
| 13 | GLM-5.2 | 1241 | #73 |
| 14 | GPT-6 Sol | 1238 | #14 |
| 15 | Claude Opus 4.6 | 1220 | #63 |
No result here: #3 Claude Opus 5.5, #7 GPT-6.1 Sol, #8 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=design-arena-agents-fullstack · How It Works · Data refreshed daily, snapshot 2026-10-20.