List your company

Physical Paradox Detection on L3 AD Paradox Zone 1.0 (n=30)

100AccuracyCAAF
-4235077Apr 18, 2026

Evaluation results

MethodLinks
CAAFModel=all-GPT-4o-mini, Temperature=0.7/0.0, Hint=×, n=302026.04100100
CAAFModel=all-GPT-4o-mini, Temperature=0.7/0.0, Hint=✓, n=302026.04100100
GPT-4oSystem=Monolithic, Temperature=0.7, Hint=✓, n=302026.0490100
GPT-4o-miniSystem=Monolithic, Temperature=0.7, Hint=✓, n=302026.0450100
GPT-4oSystem=Monolithic, Temperature=0.7, Hint=×, n=302026.040100
GPT-4o-miniSystem=Monolithic, Temperature=0.7, Hint=×, n=302026.040100
GPT-4oSystem=Monolithic, Temperature=0.0, Hint=×, n=302026.040100