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

Failure Detection on LIBERO 10 Unseen Tasks

89.2bACC

Hide-and-Seek

44.37656.01367.6579.287May 29, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2026.05
89.292.170.5
2026.05
83.482.866.3
2026.05
80.186.764.8
2026.05
77.574.159
2026.05
73.260.455.2
2026.05
68.666.655.3
2026.05
68.167.957.4
2026.05
67.167.252.4
2026.05
63.95952.2
2026.05
63.45154.3
2026.05
62.464.252.8
2026.05
62.369.654.2
2026.05
61.366.849.5
2026.05
60.96350.5
2026.05
60.952.852.4
2026.05
60.460.254.2
2026.05
5757.854.8
2026.05
54.550.250.5
2026.05
52.552.848.8
2026.05
52.151.848.8
2026.05
5264.350.5
2026.05
51.349.550.4
2026.05
50.950.447.8
2026.05
49.548.747
2026.05
49.14945.6
2026.05
4959.644
2026.05
48.649.444.2
2026.05
46.147.139.4