Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Path-Following on 10,000 Evaluation Tasks (Medium Subset n=4795)
Loading...
0.57
Mean Path Length (m)
Hybrid
0.4764
0.5007
0.525
0.5493
Jun 2, 2026
Mean Path Length (m)
Std Dev Path Length (m)
Min Path Length (m)
Max Path Length (m)
Mean Ratio to Reference (%)
Std Dev Ratio to Reference (%)
Min Ratio to Reference (%)
Max Ratio to Reference (%)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Mean Path Length (m)
Std Dev Path Length (m)
Min Path Length (m)
Max Path Length (m)
Mean Ratio to Reference (%)
Std Dev Ratio to Reference (%)
Min Ratio to Reference (%)
Max Ratio to Reference (%)
Hybrid
Initial configuration...
2026.06
0.57
0.14
0.01
1.26
92.3
16.9
1.2
235.3
RL
Initial configuration...
2026.06
0.53
0.17
0.01
1.26
87.2
24.9
1.2
243.2
Classical
Initial configuration...
2026.06
0.48
0.13
0.01
1.11
79.1
19.6
1.3
176.6
Feedback
Search any
task
Search any
task
