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

Multilingual Text Generation research benchmarks · SOTA2 Research

Multilingual Text Generation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Long FLORES and XL-Sum Average across Arabic, German, Japanese, Swahili

10.02Long FLORES en->x Score

8

May 12, 2026

Multilingual Text Generation Evaluation Set Italian

97.4Character Score

3

Mar 11, 2026

Multilingual Text Generation Evaluation Set Japanese

92.65Character Score

3

Mar 11, 2026

Multilingual Text Generation Evaluation Set (Korean)

94.41Char Score

3

Mar 11, 2026

Multilingual Text Generation Evaluation Set German

98.28Char Score

3

Mar 11, 2026

Multilingual Text Generation Evaluation Set French

98.67Char Score

3

Mar 11, 2026

Multilingual Text Generation Evaluation Set Greek

97.02Char Score

2

Mar 11, 2026

Multilingual Text Generation Evaluation Set Vietnamese

96.05Char Score

2

Mar 11, 2026

Multilingual Text Generation Evaluation Set Thai

96.28Character Score

2

Mar 11, 2026

Popular datasets

Multilingual Text Generation Evaluation Set FLORES and XL-Sum

Follow for updates

Join SOTA2 Contact