Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Deception Detection on Liars' Bench Instructed Deception (test)
Loading...
0.939
AUROC
Single (28)
0.81316
0.84583
0.8785
0.91117
Apr 15, 2026
AUROC
Improvement (%)
Updated 1mo ago
Evaluation Results
Method
Method
Links
AUROC
Improvement (%)
Single (28)
Layer=28
2026.04
0.939
-
5-Layer Ensemble
Stacking Method=logist...
2026.04
0.889
5.3
3-Layer Ensemble
Stacking Method=logist...
2026.04
0.818
-
Feedback
Search any
task
Search any
task