Explainable AI Evaluation
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
66.01Area Coverage
26
Feb 26, 2026
0.613Del
20
Apr 21, 2026
0.609Deletion Metric (Del)
20
Apr 21, 2026
73.1Deletion Score (Del)
20
Apr 21, 2026
0.123Deletion Score
20
Apr 21, 2026
1.4Infidelity (FID)
18
Mar 18, 2026
6.785Selection
17
Feb 27, 2026
46.8IoU
8
Feb 26, 2026
0.383Area Coverage
8
Feb 26, 2026
0.13Scaled Infidelity
5
Jun 30, 2026
0.09Scaled Infidelity
5
Jun 30, 2026
0Scaled Infidelity
5
Jun 30, 2026