Abusive language detection
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
91.6A-F1
7
Mar 30, 2026
99.1Average Precision (AP)
7
Mar 12, 2026
0.762Mean F1
4
Feb 26, 2026
82F1 Score
4
Feb 26, 2026
73F1 Score
4
Feb 26, 2026
61F1 Score
4
Feb 26, 2026
0.651Macro F1
3
Feb 26, 2026
76.5Macro F1
3
Feb 26, 2026
0.829Macro F1
3
Feb 26, 2026
79Accuracy
2
Feb 26, 2026