Bias Evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
99.3Accuracy
175
Jul 7, 2026
0.3BAD Score
25
Apr 9, 2026
0.017BAD Score
25
Apr 9, 2026
0.007BAD Score
25
Apr 9, 2026
-0.18BAD Score
25
Apr 9, 2026
-0.007BAD Score
25
Apr 9, 2026
-0.006BAD Score
25
Apr 9, 2026
17Mean Improvement
18
May 18, 2026
98.3Ambiguous Context Score
17
Mar 23, 2026
87.73Accuracy (Ambiguous)
16
Feb 26, 2026
0.054DR (Female Stereotype)
15
Feb 26, 2026
51.25Pct Stereotype
15
Feb 26, 2026
11.7Honest Score
15
Feb 26, 2026
-4.752t-value
15
Feb 26, 2026
0.53Male Bias (Base)
14
Feb 26, 2026
50.01CS Score
13
Mar 31, 2026
66.2GN Score
10
Mar 20, 2026
0.1Mean Improvement
9
May 18, 2026
0.11Mean Improvement
9
May 18, 2026
20Mean Improvement
9
May 18, 2026
15Mean Improvement
9
May 18, 2026
0.07Mean Improvement
9
May 18, 2026
0.12Mean Improvement
9
May 18, 2026
0.12Mean Improvement
9
May 18, 2026
0.17Mean Improvement
9
May 18, 2026