VoxelBench Image Rating
Games
VoxelBench image rating is the Glicko-2 leaderboard track for image-capable models creating voxel builds. Ratings come from head-to-head human votes over rendered voxel constructions.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-6.1 Sol | 2184 |
| Gemini 3.1 Pro Preview | 1580 |
| Gemini 3 Pro Preview | 1438 |
| Opus 4.6 | 1427 |
| GPT-5.4 | 1420 |
| GPT-5.2 | 1380 |
| Opus 4.5 | 1297 |
| Opus 4.7 | 1267 |
| GPT-5-Codex | 1221 |
| Gemini 2.5 Pro | 1191 |
| GPT-5 | 1183 |
| GPT-5.1 | 1170 |
| Opus 4.1 | 1147 |