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

Semantic Role Labeling research benchmarks · SOTA2 Research

Semantic Role Labeling

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

CoNLL 2012 (test)

Fei et al. (2021a) ++ROBERTa

88.59F1 Score

49

Feb 26, 2026

CoNLL 2005 (WSJ)

95.5F1 Score

41

Feb 27, 2026

CoNLL Brown 2005 (test)

93.7F1

40

Feb 26, 2026

CoNLL WSJ English benchmark 2009 (test)

Fei et al. (2021a) ++ROBERTa

92.83F1 Score

31

Feb 26, 2026

CoNLL 2005 (Brown)

92.1F1 Score

31

Feb 27, 2026

CoNLL WSJ 2005 (test)

87.13Precision

29

Feb 26, 2026

CoNLL English Brown 2009 (test)

Llama3-8B (Fine-tune)

86.05F1 Score

28

Feb 26, 2026

CoNLL 2005 (WSJ (in-domain))

88.93F1 Score

24

Feb 26, 2026

CoNLL 2012 (dev)

87.36F1

23

Feb 26, 2026

CoNLL 2005 (dev)

87.63F1 Score

22

Feb 26, 2026

97.2F1 Score

21

Feb 27, 2026

CoNLL WSJ 2005 (dev)

89.25F1 Score

19

Feb 26, 2026

CPB Zh 1.0 (test)

Qwen2.5-7B (Fine-tune)

89.37F1 Score

11

Feb 26, 2026

97.2Micro F1

11

Feb 27, 2026

CoNLL 2005 (ALL)

87.4F1 Score

10

Feb 26, 2026

TypesDev-ucofia

90.12CIDEr

9

Apr 28, 2026

OntoNotes CoNLL-2005 (test)

87.53F1 Score

8

Feb 26, 2026

CoNLL Combined 2005

84.6F1 Score

8

Feb 26, 2026

83.68CIDEr

5

Apr 28, 2026

CoNLL Zh 2009 (test)

Qwen2.5-7B (Fine-tune)

89.56Precision

5

Feb 26, 2026

Full Fine-tuning

88.8Micro F1

5

Feb 26, 2026

CoNLL shared-task 2009 (test)

k order pruning+Glyce

85.4Precision

4

Feb 26, 2026

OntoNotes SRL (test)

ELMo + Baseline

0.846F1 Score

3

Feb 26, 2026

FrameNet 1.7 (test)

analogical transfer

49.81Accuracy

2

Mar 23, 2026

75.2nF1 Score

2

Feb 26, 2026

Popular datasets

Conll OntoNotes VidSitu QA-SRL FrameNet

Follow for updates

Join SOTA2 Contact