Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Misalignment Detection on Sycophancy Bloom behaviors (in-distribution)
Loading...
93.5
AUROC
RepE baseline
91.212
91.806
92.4
92.994
Jun 23, 2026
AUROC
Updated 1mo ago
Evaluation Results
Method
Method
Links
AUROC
RepE baseline
Layer=29
2026.06
93.5
18-indicator ensemble
Layer=27
2026.06
93
18-indicator ensemble
Layer=29
2026.06
92.8
RepE baseline
Layer=27
2026.06
91.3
Feedback
Search any
task
Search any
task