Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Pot-Food on Pot-Food (held-out)
Loading...
50
Success Rate
π0
1.2552
13.9101
26.565
39.2199
Jun 15, 2026
Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
π0
Training data=30 Source
2026.06
50
DP
Training data=30 Source
2026.06
43.8
π0
Training data=15 Source
2026.06
25
R2RDreamer
Policy=DP, Training da...
2026.06
21.9
R2RDreamer
Policy=π0, Training da...
2026.06
21.9
DP
Training data=15 Source
2026.06
18.8
DP
Training data=5 Source
2026.06
6.25
π0
Training data=5 Source
2026.06
6.25
DP
Training data=1 Source
2026.06
3.13
π0
Training data=1 Source
2026.06
3.13
Feedback
Search any
task
Search any
task