Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Part-of-Speech Tagging research benchmarks · SOTA2 Research

Part-of-Speech Tagging

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Penn TreeBank (test)

97.96Accuracy

64

Feb 26, 2026

97.78Accuracy

51

Feb 26, 2026

TWEEBANK V2 (test)

95.8Accuracy

38

Feb 26, 2026

ELMo + Multi-task

97.79Accuracy

33

Feb 26, 2026

UD Average 1.2 (test)

96.65Accuracy

22

Feb 26, 2026

UD (Universal Dependencies) Indonesian (test)

93.7Accuracy

17

Feb 26, 2026

98.39Accuracy

14

Feb 26, 2026

83.56Accuracy

13

Feb 26, 2026

97.1Precision

13

Feb 26, 2026

DialectBench (test)

XLM-R + VAÇAÍ-Bowl

58.35aln POS Accuracy

12

May 7, 2026

MasakhaPOS Setswana

83Token Accuracy

12

Mar 24, 2026

MasakhaPOS isiZulu

90.1Token Accuracy

12

Mar 24, 2026

MasakhaPOS isiXhosa

88.7Token Accuracy

12

Mar 24, 2026

Universal Dependencies (UD) (test)

94.97Accuracy

12

Feb 26, 2026

Wall Street Journal (WSJ) section 23 (test)

97.65Accuracy

12

Feb 26, 2026

95.7F1 Score

11

Feb 26, 2026

95.74F1 Score

11

Feb 26, 2026

95.24F1 Score

11

Feb 26, 2026

96.57F1 Score

11

Feb 26, 2026

Penn Treebank POS (test)

LSTM-CRF+char-IntNet-5

97.58F1 Score

10

Feb 26, 2026

Pantagruel-B-Wk-MLM

96.8MacF1

8

Feb 26, 2026

96.3MacF1

8

Feb 26, 2026

CoNLL 2003 (test)

93.34Accuracy

8

Feb 26, 2026

84.04F1 Score

8

Feb 26, 2026

UD non-Indo-European 1.2 (test)

96.28Accuracy

8

Feb 26, 2026

Page 1 of 4

PreviousNext

Popular datasets

UD POS CTB Sonar Universal Dependencies

Follow for updates

Join SOTA2 Contact