Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Rollout-level failure detection on ManiSkill-Long (test)
Loading...
84
ROC-AUC
Foresight-Transformer
60.08
66.29
72.5
78.71
Jun 22, 2026
ROC-AUC
Balanced Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
ROC-AUC
Balanced Accuracy
Foresight-Transformer
architecture=Transform...
2026.06
84
80
RND
2026.06
83
68
SAFE-LSTM
architecture=LSTM
2026.06
82
74
Gauge
2026.06
80
77
Foresight-LSTM
architecture=LSTM, act...
2026.06
76
79
FAIL-Detect
2026.06
71
50
Foresight-MLP
architecture=MLP, acti...
2026.06
70
71
SAFE-MLP
architecture=MLP
2026.06
61
53
Feedback
Search any
task
Search any
task