Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Stack on PandaGym Stack
Loading...
98.4
Success Rate
Ours Ens
-3.936
22.632
49.2
75.768
Sep 24, 2025
Success Rate
Updated 1d ago
Evaluation Results
Method
Method
Links
Success Rate
Ours Ens
Number of demos=400
2025.09
98.4
Ours IL
Number of demos=400
2025.09
92
Ours Ens
Number of demos=200
2025.09
88
Ours Ens
Number of demos=100
2025.09
80.8
ACT
Number of demos=400
2025.09
79.6
Ours IL
Number of demos=200
2025.09
61.2
ACT
Number of demos=200
2025.09
52.4
Ours IL
Number of demos=100
2025.09
34.8
Ours Ens
Number of demos=50
2025.09
29.6
ACT
Number of demos=100
2025.09
25.2
Ours Ens
Number of demos=25
2025.09
9.2
Ours IL
Number of demos=50
2025.09
4.8
ACT
Number of demos=50
2025.09
2.4
Ours IL
Number of demos=25
2025.09
0.8
ACT
Number of demos=25
2025.09
0
Feedback
Search any
task
Search any
task
