Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Sycophancy Detection on Sycophancy benchmark (full evaluation set)
Loading...
0.732
AUROC
Hypocrisy Gap
0.40856
0.49253
0.5765
0.66047
Jan 14, 2026
AUROC
Updated 4d ago
Evaluation Results
Method
Method
Links
AUROC
Hypocrisy Gap
Predictor=H, Base Mode...
2026.01
0.732
Hypocrisy Gap
Predictor=H, Model=Gem...
2026.01
0.731
Hypocrisy Gap
Predictor=H, Base Mode...
2026.01
0.588
Hypocrisy Gap
Predictor=H, Model=Lla...
2026.01
0.587
Hypocrisy Gap
Predictor=H, Model=Qwe...
2026.01
0.549
Hypocrisy Gap
Predictor=H, Base Mode...
2026.01
0.549
Log-probability baseline
Predictor=ΔLP, Base Mo...
2026.01
0.5
log-probability baseline
Predictor=Baseline, Mo...
2026.01
0.499
log-probability baseline
Predictor=Baseline, Mo...
2026.01
0.453
Log-probability baseline
Predictor=ΔLP, Base Mo...
2026.01
0.452
Log-probability baseline
Predictor=ΔLP, Base Mo...
2026.01
0.424
log-probability baseline
Predictor=Baseline, Mo...
2026.01
0.421
Feedback
Search any
task
Search any
task