LMArena Image Edit leaderboard
- models measured
- 5
- lead over #2
- +36 Elo
- median
- 1387
Leader on LMArena Image Edit · read October 21
On October 21, 2026, 5 of our catalog's models had a LMArena Image Edit result, and Google Nano Banana 2.1 led with 1426.
Requests to edit an uploaded image; people compare the two edits. People ask a question, compare two anonymous answers and vote for the better one; the rating is built from those votes, as LMArena 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 | Votes | Interval (±) | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|---|---|
| 1 | Nano Banana 2.1Google | 1426 | 12,938 | ±5.8 | Not benchmarked | $7.50 | |
| 2 | Nano Banana Pro (Gemini 3 Pro Image)Google | 1390 | 676,298 | ±2.6 | Not benchmarked | $12.00 | |
| 3 | Nano Banana 2 (Gemini 3.1 Flash Image)Google | 1387 | 253,535 | ±3.3 | Not benchmarked | $3.00 | |
| 4 | Nano Banana Pro (Gemini 3 Pro Image Preview)Google | 1385 | 540,728 | ±2.9 | Not benchmarked | $12.00 | |
| 5 | Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google | 1313 | 65,657 | ±4.7 | Not benchmarked | $1.50 |
Only models in our catalog are listed, and each appears once with its best published run. 172 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.