Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

PerfectMaze

Benchmarks

Task NameDataset NameSOTA ResultTrend
Maze SolvingPerfectMaze XL (held-out)
Solved Rate14
9
Maze SolvingPerfectMaze Large (held-out)
Solved Rate27
9
Showing 2 of 2 rows