Coreference Resolution
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
98.5Accuracy
116
Jun 1, 2026
88MUC F1 Score
114
Feb 27, 2026
95Accuracy
72
Jun 26, 2026
89.9Overall F1
53
Feb 26, 2026
93.7MUC
46
May 8, 2026
90.1Accuracy
34
Feb 26, 2026
85.2Accuracy@1
33
Apr 28, 2026
94.79Accuracy
33
Feb 26, 2026
81.8Avg. F1
30
May 12, 2026
81CoNLL F1
27
Feb 26, 2026
79.9Accuracy
26
May 22, 2026
59.98Precision
22
May 1, 2026
0.02Loss
20
Jun 1, 2026
90.98EM
20
Apr 30, 2026
82.7Accuracy
19
Jun 1, 2026
69.9Score
18
Apr 23, 2026
90.5Accuracy
18
Mar 13, 2026
88.6MUC Precision
18
Feb 26, 2026
49.67MUC Recall
17
Jun 17, 2026
83.1Average F1
17
Feb 27, 2026
64.72Accuracy
15
Jun 9, 2026
80.5CoNLL F1
15
Feb 26, 2026
60.5Accuracy
13
Feb 26, 2026
65.4Accuracy
13
Feb 26, 2026
83.4CoNLL F1
13
Feb 26, 2026