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)→
More from Models
- Raschka: benchmarking new LLMs is like using IQ tests for hiring — rasbt · 2026-11-18
- Open-source Karpo-Decision-31B tops 300-model Decision Index with zero-token, one-forward-pass answers — rohanpaul_ai · 2026-11-18
- GPT-6.2 backlash is real user experience, not astroturf: dev says Astra has quirks but Sol is a solid daily driver — pvncher · 2026-11-18
- LLM protein-folding test on fresh PDB entry lands near-random structures — MoAlQuraishi · 2026-11-18
- Per-task costs span 20x: GPT-6.2 Sol at $2.63 vs Claude Fable 5.2 at $54.25 — haider1 · 2026-11-18
- Every's founder pushes back: we re-tested the model to the wire, OpenAI gave us no heads-up — kieranklaassen · 2026-11-18