VoxelCodeBench: leaderboard
Metric: Shape correctness (%): share of the 220 tasks whose rendered voxel output a human annotator judges to match the specified geometry (the paper's primary metric); higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 87.9 |
| 2 | Claude Sonnet 4.5 | 80.4 |
| 3 | GPT-5 Mini | 80.4 |
| 4 | GPT-5 Chat | 69.7 |
| 5 | Claude Opus 4 | 69.4 |
| 6 | Claude 3.5 Sonnet | 66.9 |
| 7 | Claude 3 Opus | 45.2 |
| 8 | Gemini 3 Pro | 19.5 |
Interactive version: theaggregate.ai/benchmark?slug=voxelcodebench · How It Works · Data refreshed daily, snapshot 2026-10-07.