Out-of-Distribution Generalization
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
32.72PathMNIST Accuracy
9
Apr 21, 2026
55.35Pass@1
6
Jun 5, 2026
19.8Saving Score
6
Apr 2, 2026
26.5Saving Score
6
Apr 2, 2026
29.5Saving Score
6
Apr 2, 2026
71.5Sav.
6
Apr 2, 2026
67Score (Sav.)
6
Apr 2, 2026
76.7Average Accuracy
4
May 19, 2026
47.6Minimum Accuracy
3
Feb 26, 2026
3.27EGS
2
Feb 26, 2026
49EGS
2
Feb 26, 2026
3.55EGS
2
Feb 26, 2026
0.01EGS
1
Feb 26, 2026
3.72EGS
1
Feb 26, 2026
4.62EGS
1
Feb 26, 2026
3.97EGS Score
1
Feb 26, 2026
2.4EGS
1
Feb 26, 2026
1.72EGS
1
Feb 26, 2026
100Estimated Generalization Score (EGS)
1
Feb 26, 2026
0.33EGS
1
Feb 26, 2026
7.22EGS
1
Feb 26, 2026
5.95EGS
1
Feb 26, 2026
5.04EGS
1
Feb 26, 2026
70EGS
1
Feb 26, 2026
1.16EGS
1
Feb 26, 2026