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

DM Math

Benchmarks

Task NameDataset NameSOTA ResultTrend
Membership Inference AttackDM Math Pythia
ROC AUC100
36
Mathematical ReasoningDM-Math
Pass@152.3
18
Membership InferenceDM Math Pythia (train)
TPR@1%FPR99.3
15
Showing 3 of 3 rows