Knowledge Editing
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
1,400Reliability
9
Feb 26, 2026
67.22Reliability
9
Feb 26, 2026
5,343Reliability
9
Feb 26, 2026
92.78Reliability
9
Feb 26, 2026
92.53Reliability
9
Feb 26, 2026
92.38Reliability
9
Feb 26, 2026
94.59Reliability
9
Feb 26, 2026
0.759Average Accuracy
8
Feb 26, 2026
75.1Reliability
8
Feb 26, 2026
1Relational Score
8
Feb 26, 2026
1Rel.
8
Feb 26, 2026
98.67DI Score
8
Feb 26, 2026
87.77Average Score
7
Feb 26, 2026
100Reliability
7
Feb 26, 2026
94.78Reliability
7
Feb 26, 2026
90.42Reliability
7
Feb 26, 2026
93.49Reliability (En Test)
7
Feb 26, 2026
99.97Reliability (Eng)
7
Feb 26, 2026
98.6Reliability
7
Feb 26, 2026
80.23Reliability
7
Feb 26, 2026
84.28Reliability
7
Feb 26, 2026
90.45Reliability
7
Feb 26, 2026
87.61Reliability
7
Feb 26, 2026
100Reliability
7
Feb 26, 2026
54.78Reliability
7
Feb 26, 2026