Man and Car in California
Vote
Image Editing
Photorealism
13 models were given the same image and edit instruction, and the community voted blind on which outputs looked best. How it works
#1 — Nano Banana Pro
Edit instruction
“Make a photo of the man driving the car down the California coastline”
Challenge Rankings
| # | Model | Elo |
|---|---|---|
| 1 |
Nano Banana Pro
|
1291 |
| 2 |
GPT Image 1.5
|
1291 |
| 3 |
Wan 2.6
|
1269 |
| 4 |
Qwen Image Edit 2511
|
1269 |
| 5 |
Nano Banana
|
1265 |
| 6 |
Nano Banana 2
|
1263 |
| 7 |
FLUX.2 [pro]
|
1259 |
| 8 |
FLUX.2 [flex]
|
1251 |
| 9 |
FLUX.2 [max]
|
1239 |
| 10 |
Seedream 4.5
|
1222 |
| 11 |
Seedream 5.0 Lite
|
1189 |
| 12 |
Grok Imagine Image
|
1173 |
| 13 |
Seedream 4.0
|
1136 |
Nano Banana Pro and GPT Image 1.5 share the top rank at 1291 Elo, though GPT Image 1.5 achieves this position at a significant price advantage, costing roughly 86% less per image than the lead Google model. Alibaba’s Qwen Image Edit 2511 remains competitive at 1269 Elo, matching the performance of models with significantly slower generation times while maintaining a "Fast" speed rating.
Elo vs Cost
Elo vs Speed
2 models waiting for enough speed data
Competitors
13 models, ranked by Elo
1
2
3
Highlighted Battles
The most competitive head-to-head matchups, selected by closeness and vote count.