Highlights
10 imagesBest models, by
Best Text-to-Image Models by Price
1 model without pricing omitted.
Best Text-to-Image Models by Speed
8 models waiting for enough speed data.
Best AI Models for Photorealism
| # | Model | Elo |
|---|---|---|
| 1 | 1245 | |
| 2 | 1243 | |
| 3 | 1237 | |
| 4 | 1236 | |
| 5 | 1235 | |
| 6 | 1234 | |
| 7 | 1227 | |
| 8 | 1225 | |
| 9 | 1223 | |
| 10 | 1217 |
| 11 | 1216 | |
| 12 | 1211 | |
| 13 | 1207 | |
| 14 | 1203 | |
| 15 | 1203 | |
| 16 | 1200 | |
| 17 | 1196 | |
| 18 | 1192 | |
| 19 | 1192 | |
| 20 | 1191 | |
| 21 | 1190 | |
| 22 | 1184 | |
| 23 | 1183 | |
| 24 | 1182 | |
| 25 | 1180 | |
| 26 | 1171 | |
| 27 | 1169 | |
| 28 | 1167 | |
| 29 | 1167 | |
| 30 | 1166 |
Nano Banana Pro leads the Photorealism category with 1245 Elo, though second-place GPT Image 2 maintains a significantly higher win rate of 85.4% at nearly half the cost per image. Budget-conscious photorealism is dominated by FLUX.2 [dev] Flash and Z-Image Turbo, which achieve competitive Elo scores above 1215 while costing 92% less per generation than the category leader.
Rivalries
Aggregate head-to-head across the arena
Highlighted challenges
The Reversed Rodeo
This competition tests how well AI image models truly understand language versus how much they rely on visual habits from their training data. The prompt is deliberately simple on the surface but devilishly hard in practice. Most models default to the familiar trope of an astronaut riding a horse. By forcing the reversal, we measure three critical capabilities that separate good models from great ones: Strict instruction following (including negations) Accurate subject-object relationships and spatial hierarchy Resistance to strong dataset biases
Geometric Composition
A spatial-reasoning test. Each object has a precise relationship (inside, on top, behind, seen through the glass), so it measures whether a model follows explicit placement instructions and handles transparency and refraction rather than just approximating the scene.
Keep the arena honest
Cast your vote
Pick winners in blind matchups. Every vote nudges the Elo and shapes these rankings.
Cast Your VoteSuggest a prompt
Got an idea worth testing? Submit a prompt and watch the models battle it out.