Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Deception Detection on Instructed Deception
Loading...
99.6
AUROC
LLM-as-a-Judge w/ CoT
59.56
69.955
80.35
90.745
Jun 16, 2026
AUROC
Updated 1mo ago
Evaluation Results
Method
Method
Links
AUROC
LLM-as-a-Judge w/ CoT
Target Model=GEMMA4-26...
2026.06
99.6
LLM-as-a-Judge
Target Model=GEMMA4-26...
2026.06
99.3
LR probe
Target Model=GEMMA4-26...
2026.06
99.1
LLM-as-a-Judge
Target Model=GPT-OSS-20B
2026.06
99
Self-Evaluation
Target Model=GEMMA4-26...
2026.06
99
LLM-as-a-Judge w/ CoT
Target Model=GPT-OSS-20B
2026.06
98.8
STATEWITNESS
Target Model=GEMMA4-26...
2026.06
98.7
STATEWITNESS
Target Model=GPT-OSS-20B
2026.06
98.4
LR probe
Target Model=GPT-OSS-20B
2026.06
97.8
Self-Evaluation
Target Model=GPT-OSS-20B
2026.06
97
MMS probe
Target Model=GEMMA4-26...
2026.06
90.4
CMMS probe
Target Model=GEMMA4-26...
2026.06
88.4
CMMS probe
Target Model=GPT-OSS-20B
2026.06
81.4
MMS probe
Target Model=GPT-OSS-20B
2026.06
79.8
LAT probe
Target Model=GPT-OSS-20B
2026.06
72.7
LAT probe
Target Model=GEMMA4-26...
2026.06
61.1
Feedback
Search any
task
Search any
task