Coreference Resolution
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
50.9CoNLL F1
8
Feb 26, 2026
60.4CoNLL F1
8
Feb 26, 2026
88.3CoNLL F1
8
Feb 26, 2026
80.9CoNLL F1
8
Feb 26, 2026
36.57MUC
7
Jun 17, 2026
58.36F1 Score
7
Feb 26, 2026
86.4Avg F1
7
Feb 26, 2026
66.6Average F1
7
Feb 26, 2026
83.5Avg F1 Score
7
Feb 26, 2026
93.47COREF
7
Feb 26, 2026
84.96COREF
7
Feb 26, 2026
95Accuracy
7
Feb 26, 2026
92.2Accuracy
7
Feb 26, 2026
63.9Precision
7
Feb 26, 2026
0.154ECE
6
Feb 26, 2026
75.7Accuracy (0-shot)
6
Feb 26, 2026
85.7Accuracy (0-shot)
6
Feb 26, 2026
65.9Avg F1
6
Feb 26, 2026
85.6Accuracy
6
Feb 26, 2026
89.7Accuracy
6
Feb 26, 2026
64.5MUC Precision
6
Feb 26, 2026
94.1Male F1
6
Feb 26, 2026
91.1Male F1 Score
6
Feb 26, 2026
99.16MUC F1
5
Apr 3, 2026
99.39MUC F1
5
Apr 3, 2026