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

Long-horizon household tasks on RoboCasa-50

67.1Success Rate

Cosmos-Policy

34.75643.15351.5559.947Apr 30, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
67.1
2026.04
62.1
2026.04
53.5
2026.04
50
2026.04
48.2
2026.04
42.4
2026.04
41.4
2026.04
36