Knowledge Editing
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
9,387Efficacy
407
Jun 23, 2026
97.62Generality
393
Jun 23, 2026
100Reliability
61
Feb 26, 2026
98.77Reliability
45
Feb 26, 2026
94.7M-A Score
33
Jun 4, 2026
99.2Rel.
30
Jun 2, 2026
85.89Edit Success
30
Apr 8, 2026
94.56Edit Success Rate
30
Apr 8, 2026
99.95Edit Success Rate
30
May 19, 2026
100Reliability
27
Feb 26, 2026
10,000Relational Score
27
Feb 26, 2026
99.88Reliability
26
May 25, 2026
100Reliability
24
Feb 26, 2026
100Reliability
24
Feb 26, 2026
53.1DP
23
May 21, 2026
100Efficacy
23
May 21, 2026
10,000Reliability
23
Feb 26, 2026
99.3M-A Score
22
Jun 4, 2026
100Embedding Stability (ES)
21
Feb 26, 2026
99Rel. Accuracy
21
Feb 26, 2026
99Reliability
21
Feb 26, 2026
92.96AVG Score
20
Apr 23, 2026
95.7S
19
Mar 4, 2026
86.49Efficacy
18
Jun 23, 2026
90H-Acc
18
May 28, 2026