Lighting, Shadows & Materials · Image Editing
Elo rankings from blind votes across 5 challenges in this category.
Highlights
10 imagesBest models, by
Best Image Editing Models by Price
1 model without pricing omitted.
Best Image Editing Models by Speed
2 models waiting for enough speed data.
Best AI Models for Lighting, Shadows & Materials
| # | Model | Elo |
|---|---|---|
| 1 | 1272 | |
| 2 | 1257 | |
| 3 | 1255 | |
| 4 | 1251 | |
| 5 | 1249 | |
| 6 | 1247 | |
| 7 | 1238 | |
| 8 | 1236 | |
| 9 | 1235 | |
| 10 | 1230 |
| 11 | 1230 | |
| 12 | 1229 | |
| 13 | 1225 | |
| 14 | 1224 | |
| 15 | 1217 | |
| 16 | 1211 | |
| 17 | 1207 | |
| 18 | 1193 | |
| 19 | 1173 | |
| 20 | 1159 | |
| 21 | 1151 | |
| 22 | 1150 | |
| 23 | 1133 | |
| 24 | 1103 |
Google models dominate this category, with Nano Banana Pro leading (1272 Elo) and Nano Banana 2 (1257 Elo) outperforming higher-priced competitors. While GPT Image 2 maintains a significantly higher win rate of 85.7%, it remains 21 Elo points behind the top-ranked Nano Banana Pro in overall head-to-head performance for material and light accuracy.
Rivalries
Aggregate head-to-head across the arena
Highlighted challenges
Man and Car in California
Combines two references (a person and a car) into one believable driving scene. It checks whether the model keeps the man’s identity and the car’s appearance while placing them convincingly on the coastline with matched lighting and perspective.
Bald man challenge
A targeted edit test. Adding a realistic head of hair requires a believable hairline and texture while keeping the face, expression, and lighting unchanged. Common failures are wig-like or pasted-on hair and subtle changes to the underlying face.
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.