Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Stack Blocks on Real-robot Stack Blocks Height (OOD)
Loading...
50
Success Rate
World Pilot
-2
11.5
25
38.5
Jun 10, 2026
Success Rate
Absolute Success Drop
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
Absolute Success Drop
World Pilot
Fine-tuning steps=10,0...
2026.06
50
-20
Cosmos Policy
Fine-tuning steps=10,0...
2026.06
15
-50
ABot-M0
Fine-tuning steps=10,0...
2026.06
10
-50
pi_0.5
Fine-tuning steps=10,0...
2026.06
0
-40
Feedback
Search any
task
Search any
task