Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Deception Detection on Insider Trading
Loading...
100
AUROC
Self-Evaluation
44.464
58.882
73.3
87.718
Jun 16, 2026
AUROC
Updated 1mo ago
Evaluation Results
Method
Method
Links
AUROC
Self-Evaluation
Target Model=GEMMA4-26...
2026.06
100
STATEWITNESS
Target Model=GEMMA4-26...
2026.06
100
LLM-as-a-Judge w/ CoT
Target Model=GEMMA4-26...
2026.06
99.7
LLM-as-a-Judge
Target Model=GEMMA4-26...
2026.06
99.6
LAT probe
Target Model=GEMMA4-26...
2026.06
98.6
STATEWITNESS
Target Model=GPT-OSS-20B
2026.06
98.2
LR probe
Target Model=GEMMA4-26...
2026.06
90.6
LLM-as-a-Judge w/ CoT
Target Model=GPT-OSS-20B
2026.06
89.3
LLM-as-a-Judge
Target Model=GPT-OSS-20B
2026.06
87.9
MMS probe
Target Model=GEMMA4-26...
2026.06
82.7
Self-Evaluation
Target Model=GPT-OSS-20B
2026.06
73.2
CMMS probe
Target Model=GPT-OSS-20B
2026.06
67.2
CMMS probe
Target Model=GEMMA4-26...
2026.06
58
LAT probe
Target Model=GPT-OSS-20B
2026.06
56.6
MMS probe
Target Model=GPT-OSS-20B
2026.06
55
LR probe
Target Model=GPT-OSS-20B
2026.06
46.6
Feedback
Search any
task
Search any
task