Design Arena: websites leaderboard
- Muse Wonder leads
- 1361
- models measured
- 133
- lead over #2
- +5 Elo
- median
- 1201
Leader on Design Arena: websites · read October 21
On October 21, 2026, 133 of our catalog's models had a Design Arena: websites result, and Meta Muse Wonder led with 1361.
Design Arena shows people two designs made by two models from the same prompt (a website) and asks which is better. The number is the Elo rating built from those votes, as Design Arena publishes it.
Role in the index
We collect this benchmark and show it as supporting evidence. It is not part of the Vibe Coding Index, because it measures something other than coding and the index is about coding. Read the methodology
| # | Model | Result | Battles | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|---|
| 1 | Muse WonderMeta | 1361 | 4,220 | 64.5 | $20.00 | |
| 2 | Muse Spark 1.3Meta | 1356 | 27,880 | 79.7 | $4.25 | |
| 3 | GPT-6 AstraOpenAI | 1337 | 2,269 | 88.7 | $50.00 | |
| 4 | Kimi K3Moonshot AI | 1336 | 4,144 | 61.8 | $11.936 | |
| 5 | Claude Opus 5.5Anthropic | 1335 | 2,173 | 92.2 | $20.00 | |
| 6 | Claude Sonnet 5.5Anthropic | 1326 | 1,873 | 88.9 | $10.00 | |
| 7 | GPT-5.6 SolOpenAI | 1321 | 7,175 | 76.7 | $20.00 | |
| 8 | GPT-6.1 SolOpenAI | 1321 | 2,158 | 88.7 | $10.00 | |
| 9 | Gemini 4 ArgonGoogle | 1315 | 7,746 | 80.5 | $10.00 | |
| 10 | Claude Fable 5.1Anthropic | 1313 | 6,043 | 89.1 | $50.00 |
Only models in our catalog are listed, and each appears once with its best published run. 141 rows were read from the source on October 21, 2026, and rows that match no catalog model are left out. Every other column is a figure the board publishes for the same run.
Cheapest good model on Design Arena: websites · Best open-weight model on Design Arena: websites