Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Push on Physical Simulator Out-of-Domain evaluation

0.975Success Rate

RL w. World Model

0.099320.326660.5540.78134Dec 3, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
0.975
2025.12
0.93
2025.12
0.873
2025.12
0.84
2025.12
0.156
2025.12
0.133