Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Cleaning Whiteboard
Loading...
0.9
Success Rate (SR)
SARM2
0.172
0.361
0.55
0.739
Jun 9, 2026
Success Rate (SR)
Average Progress (Avg. Prog.)
Progress Gain (Prog. Gain)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate (SR)
Average Progress (Avg. Prog.)
Progress Gain (Prog. Gain)
SARM2
Training Category=Roll...
2026.06
0.9
97.5
50
RM (FT)
Training Category=Roll...
2026.06
0.65
88.8
41.3
Sparse
Training Category=Roll...
2026.06
0.55
82.5
35
RA-BC
Training Category=Demo...
2026.06
0.5
77.5
30
RL-Dense
Training Category=Demo...
2026.06
0.5
81.3
33.8
RL-Sparse
Training Category=Demo...
2026.06
0.3
62.5
15
BC
Training Category=Demo...
2026.06
0.2
47.5
-
Feedback
Search any
task
Search any
task