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

HaluMem

Benchmarks

Task NameDataset NameSOTA ResultTrend
Memory ExtractionHaluMem
Memory Accuracy95.66
12
Memory ManagementHaluMem
Memory Updating47.28
11
Question AnsweringHaluMem
Metric C67.23
9
Memory UpdatingHaluMem
C Score94.55
9
Memory QAHaluMem Medium
C Score67.23
8
Memory UpdatingHaluMem Medium
C Score62.11
8
Memory ExtractionHaluMem Medium
R Score74.07
7
Question AnsweringHaluMem
Accuracy62.26
5
Showing 8 of 8 rows