Long-term memory evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
93Overall F1
128
Jun 2, 2026
94.4KU (Knowledge Update)
30
May 6, 2026
95.6Overall Score
23
Apr 21, 2026
97.14Single-User Score
17
Jul 2, 2026
46.7F1 Score
7
Apr 10, 2026
71.45Accuracy
6
May 12, 2026
47.7Mean Accuracy
4
Apr 28, 2026
0.767Overall Score
2
Jun 4, 2026