# Design Arena

People ask several AI models to build the same thing, such as a website, game or slide deck, then vote on which result looks and works better. The votes become a ranking of which models are best at making designs and apps.

Category: arenas. Type: arena. Status: active.
Metric: Elo rating from head-to-head user votes (higher means the model's output was preferred more often) (higher is better).
Source: DesignArena — https://www.designarena.ai/leaderboard, results as of 2026-11-17, retrieved 2026-11-17, license: not stated.

| Rank | Model | Organization | Elo | Win Rate | Battles |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 (high) | Anthropic | 1445 | 69.1% | 2,670 |
| 2 | GPT-6 Astra (max) | OpenAI | 1399 | 67.2% | 2,526 |
| 3 | Claude Fable 5.2 | Anthropic | 1367 | 69.0% | 1,738 |
| 4 | GPT-6.1 Sol (max) | OpenAI | 1366 | 51.3% | 2,069 |
| 5 | Qwen4-Max | Alibaba | 1360 | 62.5% | 3,474 |
| 6 | Claude Fable 5.1 | Anthropic | 1336 | 59.5% | 5,155 |
| 7 | Inkling 2 Small | Thinking Machines | 1311 | 57.2% | 7,217 |
| 8 | Gemini 4 Carbon | Google | 1306 | 60.5% | 1,054 |
| 9 | Kimi K3.1 Pro | Moonshot AI | 1297 | 59.4% | 4,489 |
| 10 | Claude Sonnet 5.5 | Anthropic | 1290 | 57.5% | 3,030 |
| 11 | DeepSeek-V4.1-Flash (1017) | DeepSeek | 1288 | 47.8% | 404 |
| 12 | Muse Spark 1.3 Max | Meta | 1279 | 56.9% | 13,091 |
| 13 | Grok 4.7 | xAI | 1273 | 54.4% | 1,506 |
| 14 | Claude Fable 5 | Anthropic | 1272 | 60.5% | 13,563 |
| 15 | Gemini 4 Hydrogen | Google | 1268 | 56.6% | 380 |

Notes: 'Overall Agentic' board (combines web apps, full-stack, game dev, React Native, Android, slides and spreadsheets). Only the first 15 rows are shown on the page without expanding; separate boards exist per output type. Page says 'Updated Nov 17, 2026, 10:31 AM UTC'.
