Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Real-world Manipulation (Average) on Real World (test)
Loading...
15
Successes Count
CAP-AGENT0 + RATS Skills (MolmoSpaces)
1.48
4.99
8.5
12.01
Jun 17, 2026
Successes Count
Success Rate
Delta (Percentage Points)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Successes Count
Success Rate
Delta (Percentage Points)
CAP-AGENT0 + RATS Skills (MolmoSpaces)
Agent System=CAP-AGENT...
2026.06
15
25
21.7
CAP-AGENT0
Agent System=CAP-AGENT...
2026.06
2
3.3
-
Feedback
Search any
task
Search any
task