Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Maze Solving on PerfectMaze XL (held-out)
Loading...
14
Solved Rate
ADD
-0.56
3.22
7
10.78
Jun 24, 2025
Solved Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Solved Rate
ADD
Update=20k, Zero-shot=...
2025.06
14
PLR⊥
Update=20k, Zero-shot=...
2025.06
12
TRACED
Update=10k, Zero-shot=...
2025.06
10
ACCEL
Update=20k, Zero-shot=...
2025.06
9
ADD
Update=10k, Zero-shot=...
2025.06
2
PLR⊥
Update=10k, Zero-shot=...
2025.06
1
ACCEL
Update=10k, Zero-shot=...
2025.06
1
DR
Update=10k, Zero-shot=...
2025.06
0
DR
Update=20k, Zero-shot=...
2025.06
0
Feedback
Search any
task
Search any
task