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

Failure Detection on LIBERO-10 Seen Tasks

88.5bACC

Hide-and-Seek

47.83658.39368.9579.507May 29, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2026.05
88.592.669.3
2026.05
8791.568.8
2026.05
85.285.366
2026.05
82.381.963
2026.05
78.88471.5
2026.05
78.683.569.1
2026.05
77.485.166.3
2026.05
75.875.763.2
2026.05
70.678.462.9
2026.05
69.176.153.4
2026.05
67.276.457.2
2026.05
6766.760.4
2026.05
6766.559.3
2026.05
66.565.154.5
2026.05
66.363.653.6
2026.05
65.866.559.4
2026.05
61.975.150.1
2026.05
60.763.151.6
2026.05
59.159.547.6
2026.05
5884.156.5
2026.05
55.252.451.6
2026.05
54.874.945.4
2026.05
53.454.449.4
2026.05
52.652.349.3
2026.05
51.452.745.5
2026.05
51.352.447.8
2026.05
50.652.247.5
2026.05
49.449.345.6