Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Rollout-level failure detection on LIBERO Long (test)
Loading...
91
ROC-AUC
SAFE-LSTM
50.44
60.97
71.5
82.03
Jun 22, 2026
ROC-AUC
BalAcc
Updated 1mo ago
Evaluation Results
Method
Method
Links
ROC-AUC
BalAcc
SAFE-LSTM
architecture=LSTM
2026.06
91
88
FAIL-Detect
2026.06
90
82
RND
2026.06
90
83
Foresight-Transformer
architecture=Transform...
2026.06
89
94
Gauge
2026.06
88
81
Foresight-MLP
architecture=MLP, acti...
2026.06
88
80
Foresight-LSTM
architecture=LSTM, act...
2026.06
86
89
SAFE-MLP
architecture=MLP
2026.06
52
50
Feedback
Search any
task
Search any
task