Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Hidden directed graph traversal on Hidden directed graph (val)
Loading...
76.5
Success Rate
Pyligent
-3.06
17.595
38.25
58.905
Jul 8, 2026
Success Rate
Average Steps
Average Backtracks
Perfect BT Rate
Updated 16d ago
Evaluation Results
Method
Method
Links
Success Rate
Average Steps
Average Backtracks
Perfect BT Rate
Pyligent
2026.07
76.5
10.96
2.14
47.7
Gold-only SFT
2026.07
3.8
24.21
0.47
23.2
Base model + thinking
2026.07
0.2
14.69
0
-
Base model
2026.07
0
29.85
0
-
Feedback
Search any
task
Search any
task