Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Block Stack on Simulation
Loading...
99.9
Success Rate
3PoinTr
19.82
40.61
61.4
82.19
Mar 9, 2026
Success Rate
Updated 2mo ago
Evaluation Results
Method
Method
Links
Success Rate
3PoinTr
# Demonstrations=100
2026.03
99.9
3PoinTr
# Demonstrations=50
2026.03
99.5
2D Ablation
# Demonstrations=100
2026.03
98.4
2D Ablation
# Demonstrations=50
2026.03
93.2
ATM
# Demonstrations=100
2026.03
91.9
3PoinTr
# Demonstrations=20
2026.03
90.9
Diffusion Policy
# Demonstrations=100
2026.03
87.4
DP3
# Demonstrations=100
2026.03
87.4
DP3
# Demonstrations=50
2026.03
85
2D Ablation
# Demonstrations=20
2026.03
67.9
ATM
# Demonstrations=50
2026.03
67.6
Diffusion Policy
# Demonstrations=50
2026.03
45.5
Diffusion Policy
# Demonstrations=20
2026.03
45.4
DP3
# Demonstrations=20
2026.03
44.4
AMPLIFY
# Demonstrations=100
2026.03
41.7
ATM
# Demonstrations=20
2026.03
40
AMPLIFY
# Demonstrations=50
2026.03
30.9
AMPLIFY
# Demonstrations=20
2026.03
22.9
Feedback
Search any
task
Search any
task