GPT-6.2 Tops VoxelBench 2 in Error Rate Despite Strong Voxel Scenes

legit_api · x · 2026-11-18

VoxelBench testing found GPT-6.2 Astra and GPT-6.2 Sol have the highest error rate of any model so far on VoxelBench 2: 19 failures for Astra and 62 for Sol, nearly all from syntax errors or dumb mistakes like forgetting to define something.

That said, aside from the unusually high error rate, GPT-6.2 Astra produces wonderful voxel scenes, and 20 examples were shared for review.

Related event: GPT-6.2 Models Top VoxelBench 2 Error Rates(2 posts)→

Original post →

More from Models

Models channel →