Conll
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
CoNLL 2003 (test)
98.31F1 Score
556
CoNLL 2014 (test)
72.2F0.5 Score
233
CoNLL 03
78.1F1 Score
140
CoNLL English 2003 (test)
94.6F1 Score
135
CoNLL English 2012 (test)
88MUC F1 Score
114
CoNLL Spanish NER 2002 (test)
95.9F1 Score
98
CoNLL 2000 (test)
97.3F1 Score
88
CoNLL Dutch 2002 (test)
95.7F1 Score
87
Conll 2003
96.77F1 Score
86
CoNLL 04
79.73F1
85
CoNLL German 2003 (test)
88.34F1 Score
78
CONLL04
78.84Relation Strict F1
52
CoNLL 2012 (test)
88.59F1 Score
49
CoNLL 2005 (Out-of-domain (Brown))
85.1F1 Score
41
CoNLL 2005 (WSJ)
95.5F1 Score
41
CoNLL 2003 (dev)
97.21F1 Score
40
CoNLL Brown 2005 (test)
93.7F1
40
CoNLL 2014
65.2F0.5
39
CONLL04
93.26Entity F1
35
CoNLL (test)
92.7F1 Score (AVG)
35
CoNLL 2009 (test)
93.03F1 Score
32
CoNLL WSJ English benchmark 2009 (test)
92.83F1 Score
31
CoNLL 2005 (Brown)
92.1F1 Score
31
CoNLL WSJ 2005 (test)
87.13Precision
29
CoNLL04 (test)
75.8F1 Score
28