Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

DETCON

Benchmarks

Task NameDataset NameSOTA ResultTrend
Data Contamination DetectionDETCON Logical Reasoning
Accuracy70.6
7
Data Contamination DetectionDETCON Code Generation
Accuracy71.5
7
Showing 2 of 2 rows