Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Push on Physical Simulator Out-of-Domain evaluation
Loading...
0.975
Success Rate
RL w. World Model
0.09932
0.32666
0.554
0.78134
Dec 3, 2025
Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Success Rate
RL w. World Model
Policy=OpenVLA
2025.12
0.975
RL w. ManiSkill
Policy=OpenVLA
2025.12
0.93
RL w. World Model
Policy=MLP
2025.12
0.873
Supervised Fintune
Policy=OpenVLA
2025.12
0.84
RL w. ManiSkill
Policy=MLP
2025.12
0.156
Supervised Fintune
Policy=MLP
2025.12
0.133
Feedback
Search any
task
Search any
task