Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Long-horizon manipulation on Real-world Long-Horizon Tasks (seen environment)
Loading...
40
Task Success Rate: Make coffee
VLMimic
-1.6
9.2
20
30.8
Oct 28, 2024
Task Success Rate: Make coffee
Task Success Rate: Clean table
Task Success Rate: Make a pie
Task Success Rate: Wash pan
Task Success Rate: Make slices
Task Success Rate: Chem. exp.
Overall Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Task Success Rate: Make coffee
Task Success Rate: Clean table
Task Success Rate: Make a pie
Task Success Rate: Wash pan
Task Success Rate: Make slices
Task Success Rate: Chem. exp.
Overall Success Rate
VLMimic
Type of demos=Video, N...
2024.10
40
70
70
40
50
30
-
R3M-DP
Type of demos=Obs-act,...
2024.10
10
30
20
10
0
10
-
DP
Type of demos=Obs-act,...
2024.10
0
20
10
0
10
0
-
GraphIRL
Type of demos=Video, N...
2024.10
0
10
0
0
0
0
-
CaP
Type of demos=Template...
2024.10
0
10
0
0
0
0
-
Demo2Code
Type of demos=Video, N...
2024.10
0
10
0
0
0
0
-
Feedback
Search any
task
Search any
task