Counterfactual Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
100VCR
9
Jun 2, 2026
98Validity
9
Feb 26, 2026
0.99Validity
9
Feb 26, 2026
100Validity Score
8
May 29, 2026
100Validity Score
8
May 29, 2026
100Validity Score
8
May 29, 2026
100Validity Score
8
May 29, 2026
18.8Target AUC
8
May 11, 2026
2.5Diversity
7
May 29, 2026
1.08Diversity
7
May 29, 2026
0.97Diversity
7
May 29, 2026
4.8Diversity
7
May 29, 2026
77.8Validity
6
Jul 3, 2026
2.1Diversity
6
May 29, 2026
3.6Diversity
6
May 29, 2026
5.1Diversity
6
May 29, 2026
13.1Target AUC
6
May 11, 2026
0.013MAE (Pendulum (p) | do(p))
6
May 8, 2026
24.875LogitTgt
6
Mar 5, 2026
24.875LogitTgt
6
Mar 5, 2026
450.6Proximity
6
Feb 26, 2026
90.4Interpretability Score
6
Feb 26, 2026
7.6Diversity
5
May 29, 2026
4.7Diversity
5
May 29, 2026
3.3Diversity
5
May 29, 2026