MazeBench B
AI benchmark · Reasoning
What is MazeBench?
MazeBench is an open-world visual-spatial reasoning environment for evaluating long-running AI agents. Agents navigate more than 200 three-dimensional rooms, solve Sokoban-style puzzles, and collect hidden gems while using movement, camera rotation, undo, reset, and teleport actions. The benchmark supports vision, ASCII, and JSON observation modes, with separate tracks for agents with and without Python tool access. Its public leaderboard reports gem collection and room exploration.
Tier B
Established: 15 or more models scored, or curated RL directories rate it.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- 24 models scored
- in curated RL directories (1 pt)
How we got to tier B
- Adoption: 24 models scored. Tier B.
- Not yet read on X.
- In curated RL directories: 1 point, a floor of none.
- Not yet confirmed by a line from its own site or paper.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Not on the map yet: no line from its own site or paper places it in a domain.
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-10-11 snapshot.