Maze Bench: GPT-6 Astra without code execution reportedly beats GPT-5.6 Sol with code
patience_cave · x · 2026-09-14
Maze Bench, a visual spatial reasoning benchmark in a 3D open world (playable free online), reportedly shows GPT-6 Astra with code execution nearly doubling GPT-5.6 Sol's score. Bigger surprise: GPT-6 Astra without code execution still beats GPT-5.6 Sol with code, suggesting strong agentic spatial reasoning. Note: GPT-6 is unannounced, treat as unverified.
Related event: GPT-6 Astra on MazeBench: Bare Model Beats GPT-5.6 With Tools(6 posts)→
More from Models
- Perplexity early evals: Gemini 4 Carbon tops WANDR benchmark for long-form research — AravSrinivas · 2026-10-31
- DeepSeek's silent downtime upgrade caught by the pelican bicycle test — teortaxesTex · 2026-10-31
- ARC Prize 2026 closes in 3 days as Yi-Chia Chen tops ARC-AGI-3 at 75.56% — GregKamradt · 2026-10-31
- Fable 5.5 Max stuns with gorgeous SVG of a pelican riding a bicycle, headed to Claude Code — ChrisGPT · 2026-10-31
- OpenAI reportedly to train on users' Daybreak sessions with no opt-out — dyn___ · 2026-10-31
- NVIDIA Nemotron 3.5 scales LLM self-verification, +9-10 points on agentic benchmarks — sarahcat21 · 2026-10-31