Model Editing
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
88.88Efficacy
78
May 13, 2026
1Reliability
72
May 12, 2026
99.79Efficacy
71
Apr 7, 2026
99.76Reliability
50
Apr 23, 2026
79.6Efficacy
49
Mar 11, 2026
98.23Efficacy
49
Mar 11, 2026
99.07Efficacy
36
May 13, 2026
69.5MMLU
34
May 12, 2026
92Reliability
30
Feb 26, 2026
79.4Reliability
26
Feb 26, 2026
80.5Reliability
26
Feb 26, 2026
96.12Efficacy
24
Feb 26, 2026
99.7Efficacy
21
Mar 4, 2026
98.17Reliability (Rel.)
20
Apr 10, 2026
9Skip Rate
16
Jun 18, 2026
0.975Reliability
16
Feb 26, 2026
99.9Reliability
13
Feb 26, 2026
9,980Reliability
13
Feb 26, 2026
99.1Relational Score
13
Feb 26, 2026
87.9Success Rate (%)
11
Jun 18, 2026
98Reliability (Rel.)
11
Apr 10, 2026
98.12Reliability Score
11
Apr 10, 2026
94.09Efficacy
11
Mar 11, 2026
98.1Efficacy
10
Mar 10, 2026
74.54Efficacy
9
May 13, 2026