Highlights
5 imagesBest models, by
Best Text-to-Image Models by Price
Best Text-to-Image Models by Speed
7 models waiting for enough speed data.
Best AI Models for Portraits
| # | Model | Elo |
|---|---|---|
| 1 | 1279 | |
| 2 | 1267 | |
| 3 | 1252 | |
| 4 | 1233 | |
| 5 | 1232 | |
| 6 | 1232 | |
| 7 | 1232 | |
| 8 | 1230 | |
| 9 | 1229 | |
| 10 | 1223 |
| 11 | 1218 | |
| 12 | 1216 | |
| 13 | 1208 | |
| 14 | 1199 | |
| 15 | 1173 | |
| 16 | 1173 | |
| 17 | 1169 | |
| 18 | 1153 | |
| 19 | 1138 | |
| 20 | 1114 | |
| 21 | 1109 | |
| 22 | 1102 | |
| 23 | 1042 | |
| 24 | 1034 |
ByteDance
FLUX.2 [dev] Turbo leads the portrait category with a 1279 Elo and a 78.9% win rate, outperforming the overall leaderboard's preference for pro-tier models. While Google’s Nano Banana 2 maintains a higher individual win rate of 81.8% at 1267 Elo, the FLUX.2 family dominates the top five by offering superior facial fidelity at significant price-to-performance advantages.
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.