VoxelBench Text Rating
Games · 2025-09-12
VoxelBench text rating is the Glicko-2 leaderboard track for models creating voxel builds from text prompts. Ratings come from head-to-head human votes over rendered voxel constructions.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-5.6 Sol | 2291 |
| Claude Opus 5 | 2276 |
| Claude Fable 5 | 2225 |
| Kimi K3 | 2015 |
| GPT-5.5 Pro | 1997 |
| GPT-5.5 | 1980 |
| Grok 4.5 | 1803 |
| Gemini 3.6 Flash | 1787 |
| Opus 4.8 | 1681 |
| Gemini 3.1 Pro Preview | 1681 |
| Gemini 3.5 Flash | 1675 |
| Qwen3.7-Max | 1625 |
| Sonnet 5 | 1595 |
| GLM-5.2 | 1591 |
| Muse Spark 1.1 | 1518 |
| GPT-5.4 | 1513 |
| Opus 4.5 | 1504 |
| Gemini 2.5 Deep Think | 1491 |
| Opus 4.6 | 1478 |
| GPT-5.2 | 1447 |
| Gemini 3 Deep Think | 1446 |
| GLM-5.1 | 1420 |
| MiniMax M3 | 1420 |
| Opus 4.7 | 1415 |
| Gemini 3 Pro Preview | 1359 |
| Gemini 3 Flash Preview | 1316 |
| Qwen3.6 Plus (2026-04-02) | 1308 |
| GPT-5 | 1300 |
| Gemini 2.5 Pro | 1257 |
| GLM-5 | 1252 |
| GPT-5.4 Mini | 1251 |
| GPT-5-Codex | 1251 |
| Kimi K2.6 | 1243 |
| GPT-5 Pro | 1233 |
| DeepSeek-V4-Pro | 1227 |
| Sonnet 4.5 | 1226 |
| Opus 4.1 | 1223 |
| GPT-5.1 | 1221 |
| Sonnet 4 | 1138 |
| DeepSeek-V4-Flash | 1133 |