Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

MACE

Benchmarks

Task NameDataset NameSOTA ResultTrend
Confidence CalibrationMACE (test)
AUROC81.2
84
Model CalibrationMACE
AUROC82.4
84
LLM CalibrationMACE
ECE8.6
60
Showing 3 of 3 rows