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

Lemmatization research benchmarks · SOTA2 Research

Lemmatization

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

99Lemmas Accuracy

16

Feb 26, 2026

Hebrew UD Corpus v2 (test)

95.53mset Score

6

Feb 26, 2026

Tweebank (TB2) 2 (test)

98.25F1 Score

6

Feb 26, 2026

UD Finnish-TDT (dev)

95.54Lemma Accuracy

4

May 28, 2026

Vie de Saint Lambert 100 most frequent words (MFW) BnF Fr. 412

94.3Precision

2

Feb 26, 2026

Vie de Saint Lambert BnF Fr. 412 (All tokens)

90.9Precision

2

Feb 26, 2026

Tajik sentences (test)

TajikNLP Lemmatiser

89Precision

1

May 7, 2026

UniMorph Giriama verb paradigms v7 (external evaluation)

78.2Accuracy

1

Apr 27, 2026

Popular datasets

Vie de Saint Lambert TWEEBANK PDT Hebrew UD Corpus UniMorph

Follow for updates

Join SOTA2 Contact