Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Closed-loop Evaluation on Real-world sidewalk environments (long-horizon)
Loading...
1.2
IR
FlowPilot-HP
0.664
4.282
7.9
11.518
Jun 10, 2026
IR
NIR
DCR
TCR
Updated 1mo ago
Evaluation Results
Method
Method
Links
IR
NIR
DCR
TCR
FlowPilot-HP
2026.06
1.2
3.5
92.8
93.9
FlowPilot-Base
2026.06
2
7.3
90.4
91.6
ViNT
2026.06
8.1
30.4
86.7
85.8
NoMaD
2026.06
9.3
42.3
88.5
86.4
CityWalker
2026.06
14.6
48.3
80.9
80.4
Feedback
Search any
task
Search any
task