Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Sycophancy Mitigation on BCT Sycophancy (held-out)
Loading...
100
BRR Ratio
Base model
0.16
26.08
52
77.92
Jun 4, 2026
BRR Ratio
Updated 1mo ago
Evaluation Results
Method
Method
Links
BRR Ratio
Base model
Note=no training
2026.06
100
BCT
Train threat=Frustration
2026.06
94
BCT
Train threat=Jailbreak
2026.06
42
MLPCT
Train threat=Sycophancy
2026.06
4
Feedback
Search any
task
Search any
task
