Pinned
Wow… jumping from 23 gems to 61 on MazeBench is definitely mind-blowing 🤯🤯
🚨New level unlocked! 🚨 We doubled GPT‑6 Astra’s score on MazeBench with WorldBox, our agentic sandbox for spatial reasoning.
Astra: 23 gems 💎💎
Astra+WorldBox: 61 gems 💎💎💎💎💎
MazeBench, by @patience_cave, is a tough test of long-horizon spatial reasoning: 256



