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

6 languages dataset and benchmarks · SOTA2 Research

Research Datasets

6 languages

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Natural Language Inference

6 languages Averaged (test)

53.4Accuracy

4

Dependency Labeling

6 languages Averaged (test)

58.8F1 Score

4

Masked Language Modeling

6 languages Averaged (test)

42.7MRR

4

Vocabulary Allocation

6 languages Averaged (test)

2,198AR

4

Sentence Retrieval

6 languages All transfers

27.1Accuracy

4

Sentence Retrieval

6 languages (Different script split)

0.23Accuracy

4

Natural Language Inference

6 languages (Same script split)

45.2Accuracy

4

Natural Language Inference

6 languages (Different script split)

42.4Accuracy

4

Dependency Labeling

6 languages Same script

27.8F1 Score

4

Part-of-Speech Tagging

6 languages All transfers

28.8F1 Score

4

Part-of-Speech Tagging

6 languages Different script split

25.8F1 Score

4

Named Entity Recognition

6 languages All transfers

38.7F1 Score

4

Named Entity Recognition

6 languages (Same script split)

59.9F1 Score

4

Named Entity Recognition

6 languages Different script

33.5F1 Score

4

Popular tasks

Natural Language Inference Named Entity Recognition Sentence Retrieval Part-of-Speech Tagging Dependency Labeling

Follow for updates

Join SOTA2 Contact