MazeBench author: coding lifts GPT-5.6 from 1% to 17%, GPT-6 Astra hits 23%

patience_cave · x · 2026-11-17

The creator of MazeBench, an open-world maze benchmark, answered Hamel Husain's questions with concrete data:

Related event: Fable 5.2 tops MazeBench amid benchmark contamination concerns(9 posts)→

Original post →

More from Models

Models channel →