Labyrinth
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Labyrinth unseen problems
100Completion Rate
11
Labyrinth known optimal problems
100Optimal Solutions Rate
11
Labyrinth
100Completion Rate
9
Labyrinth
5,173Token Cost
6
Labyrinth (test)
0.54Average Solving Time (s)
5
Labyrinth
491Mean Score
5