Design Arena: images leaderboard
- models measured
- 7
- lead over #2
- +20 Elo
- median
- 1216
Leader on Design Arena: images · read October 21
On October 21, 2026, 7 of our catalog's models had a Design Arena: images result, and Google Nano Banana 2.1 led with 1289.
Design Arena shows people two designs made by two models from the same prompt (an image) 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 | Nano Banana 2.1Google | 1289 | 3,154 | Not benchmarked | $7.50 | |
| 2 | Nano Banana 2 (Gemini 3.1 Flash Image Preview)Google | 1269 | 91,596 | Not benchmarked | $3.00 | |
| 3 | Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google | 1239 | 155,180 | Not benchmarked | $1.50 | |
| 4 | Nano Banana Pro (Gemini 3 Pro Image Preview)Google | 1216 | 5,033 | Not benchmarked | $12.00 | |
| 5 | GPT-5 ImageOpenAI | 1191 | Not published | Not benchmarked | $10.00 | |
| 6 | GPT-5 Image MiniOpenAI | 1184 | Not published | Not benchmarked | $2.00 | |
| 7 | Nano Banana (Gemini 2.5 Flash Image)Google | 1179 | 190,860 | Not benchmarked | $2.50 |
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.