Knowledge Editing
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
7,079Reliability
7
Feb 26, 2026
6,258Reliability
7
Feb 26, 2026
7,120Reliability
7
Feb 26, 2026
7,335Reliability
7
Feb 26, 2026
6,810Reliability
7
Feb 26, 2026
8,170Reliability
7
Feb 26, 2026
75.1Reliability
7
Feb 26, 2026
99.22Overall Score
6
Jun 15, 2026
87CEM
6
Jun 9, 2026
91CEM
6
Jun 9, 2026
83CEM
6
Jun 9, 2026
68.83Efficacy
6
May 13, 2026
100Accuracy (Acc)
6
Mar 24, 2026
100Accuracy
6
Mar 24, 2026
98.92RwA
6
Feb 26, 2026
98.41RwA
6
Feb 26, 2026
84.33RwA
6
Feb 26, 2026
91.22Efficacy
6
Feb 26, 2026
90.2Reliability
6
Feb 26, 2026
99.89Bert Score
6
Feb 26, 2026
65.4Bert Score
6
Feb 26, 2026
99.95Bert Score
6
Feb 26, 2026
98.1Reliability
5
Apr 10, 2026
96.85Reliability
5
Apr 10, 2026
81.57UnKE-BLEU
4
Jun 2, 2026