Model Editing
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
89.2Score
9
Feb 26, 2026
99.75Efficacy
8
Apr 7, 2026
64.6Rel (QA Context)
8
Feb 26, 2026
77.8Rel Score (QA Context)
8
Feb 26, 2026
0.222Locality
8
Feb 26, 2026
8,183.7TRR
8
Feb 26, 2026
81TRR
7
Feb 26, 2026
72TRR
7
Feb 26, 2026
56.74Delta Accuracy (pp)
6
May 26, 2026
5.68Delta Accuracy (pp)
6
May 26, 2026
0.5Delta Accuracy (pp)
6
May 26, 2026
23Delta Accuracy (pp)
6
May 26, 2026
0.3Δ Accuracy (pp)
6
May 26, 2026
3.27ΔACC (pp)
6
May 26, 2026
57.6Generality
6
Mar 10, 2026
64.8Generality
6
Mar 10, 2026
31.1Reliability
6
Feb 26, 2026
31.7Target PPL
6
Feb 26, 2026
99.6Efficacy
6
Feb 26, 2026
88.2S
6
Feb 26, 2026
99Reliability
5
May 12, 2026
99Reliability
5
May 12, 2026
99Reliability
5
May 12, 2026
91.5Score (S)
5
Feb 26, 2026
73Efficacy
4
Jun 4, 2026