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

UltraEditBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Model EditingUltraEditBench
Efficacy88.88
78
Lifelong Model EditingULTRAEDITBENCH
Efficacy88.88
36
Showing 2 of 2 rows