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

Perfect Maze Planning

Benchmarks

Task NameDataset NameSOTA ResultTrend
Maze PlanningPerfect Maze Planning Hard
Accuracy97.9
6
Maze PlanningPerfect Maze Planning Medium
Accuracy98.1
6
Maze PlanningPerfect Maze Planning Easy
Accuracy99.4
6
Showing 3 of 3 rows