Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Stack Cups on Real-World Robot Experiments v1 (test)
Loading...
55
Success Rate (In-Distribution)
VLM+GAE
-2.2
12.65
27.5
42.35
Oct 4, 2025
Success Rate (In-Distribution)
Success Rate (OOD)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate (In-Distribution)
Success Rate (OOD)
VLM+GAE
Horizon=Long Horizon,...
2025.10
55
45
pi0.5
Horizon=Long Horizon,...
2025.10
45
15
SoFAR
Horizon=Long Horizon,...
2025.10
35
25
HAMSTER
Horizon=Long Horizon,...
2025.10
30
20
VLM+IK
Horizon=Long Horizon,...
2025.10
30
20
GR00T-N1
Horizon=Long Horizon,...
2025.10
25
15
OpenVLA
Horizon=Long Horizon,...
2025.10
20
10
DP3
Horizon=Long Horizon,...
2025.10
15
10
pi0-FAST
Horizon=Long Horizon,...
2025.10
15
10
pi0
Horizon=Long Horizon,...
2025.10
10
5
ACT
Horizon=Long Horizon,...
2025.10
0
0
DP
Horizon=Long Horizon,...
2025.10
0
0
Feedback
Search any
task
Search any
task
