MazeBench shows GPT-6.1 Terra leading at 8% vs Gemini 4 Hydrogen's 1%

patience_cave · x · 2026-11-13

patiencecave shares MazeBench maze-solving scores: Gemini 4 Hydrogen 1%, Claude Sonnet 5.5 4%, GPT-6.1 Terra 8% — the clear leader, with exploration maps showing it covering far more ground. 'It's a beast in this category,' the author notes.

Related event: Top AI Models Flunk MazeBench, Best Score Just 8%(2 posts)→

Original post →

More from Fun

Fun channel →