Identifying mislabeled points
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
30F1 Score
12
May 21, 2026
21F1 Score
12
May 21, 2026
42F1 Score (pol)
12
May 21, 2026
36F1 Score
12
May 21, 2026
48F1 Score
12
May 21, 2026
52F1 Score
12
May 21, 2026
15F1 Score
12
May 21, 2026
48F1 Score
12
May 21, 2026
9F1 Score
12
May 21, 2026
48F1 Score
12
May 21, 2026
33F1 Score
12
May 21, 2026
25AUC-ROC
12
May 21, 2026
24AUC-ROC
12
May 21, 2026
11AUC-ROC
12
May 21, 2026
11AUC-ROC
12
May 21, 2026
23Precision (wind)
12
May 21, 2026
16Precision
12
May 21, 2026
32Precision
12
May 21, 2026
27Precision
12
May 21, 2026
36Precision
12
May 21, 2026
39Precision
12
May 21, 2026
11Precision
12
May 21, 2026
36Precision
12
May 21, 2026
7Precision
12
May 21, 2026
36Precision (apsfail)
12
May 21, 2026