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
Google
|
1285 |
| 2 |
GPT Image 1.5
OpenAI
|
1282 |
| 3 |
Wan 2.6
Alibaba
|
1276 |
| 4 |
Qwen Image Edit 2511
Alibaba
|
1268 |
| 5 |
Nano Banana
Google
|
1257 |
| 6 |
Nano Banana 2
Google
|
1252 |
| 7 |
FLUX.2 [flex]
Black Forest Labs
|
1245 |
| 8 |
FLUX.2 [max]
Black Forest Labs
|
1238 |
| 9 |
FLUX.2 [pro]
Black Forest Labs
|
1232 |
| 10 |
Seedream 4.5
ByteDance
|
1210 |
| 11 |
Seedream 5.0 Lite
ByteDance
|
1174 |
| 12 |
Grok Imagine Image
xAI
|
1170 |
| 13 |
Seedream 4.0
ByteDance
|
1142 |
Nano Banana Pro leads the leaderboard with a 1285 Elo, though GPT Image 1.5 trails by only 3 points despite being nearly 87% cheaper per image. While Nano Banana Pro maintains the highest Elo, Wan 2.6 achieves the highest individual win rate at 73.3%, outperforming the leader by 7.2 percentage points.
Elo vs Cost
Elo vs Speed
3 without speed data omitted.
Competitors
13 models, ranked by Elo
1
2
3
Highlighted Battles
The most competitive head-to-head matchups, selected by closeness and vote count.
