Prompt Adherence · Text-to-Image
Elo rankings from blind votes across 9 challenges in this category.
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 Prompt Adherence
| # | Model | Elo |
|---|---|---|
| 1 | 1284 | |
| 2 | 1282 | |
| 3 | 1276 | |
| 4 | 1275 | |
| 5 | 1268 | |
| 6 | 1261 | |
| 7 | 1259 | |
| 8 | 1258 | |
| 9 | 1255 | |
| 10 | 1247 |
| 11 | 1244 | |
| 12 | 1242 | |
| 13 | 1240 | |
| 14 | 1238 | |
| 15 | 1238 | |
| 16 | 1238 | |
| 17 | 1237 | |
| 18 | 1231 | |
| 19 | 1230 | |
| 20 | 1228 | |
| 21 | 1225 | |
| 22 | 1223 | |
| 23 | 1223 | |
| 24 | 1221 | |
| 25 | 1217 | |
| 26 | 1217 | |
| 27 | 1215 | |
| 28 | 1214 | |
| 29 | 1210 | |
| 30 | 1208 |
Nano Banana Pro (1284 Elo) and GPT Image 2 (1282 Elo) lead the category with a significant win rate advantage, with GPT Image 2 notably achieving an 86.4% win rate despite a premium price point. Current-generation models dominate the top tiers, as FLUX.2 [max] (1276 Elo) maintains a lead over the more specialized Recraft and Grok Pro variants in following complex instructions.
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.