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

Language Identification research benchmarks – Page 3 · SOTA2 Research

Language Identification

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

GlotLID-C (test)

98.6F1 Score

4

Mar 11, 2026

GlotLID-C CLD3 label set 83 languages (test)

99F1

4

Feb 26, 2026

FLORES-200 Full (190 labels) (test)

96.8F1 Score

4

Feb 26, 2026

UDHR Full (366 labels) (test)

87.1F1 Score

4

Feb 26, 2026

HPLT-LID reannotated

14.6Bosnian FPR

4

Feb 26, 2026

14Bosnian FPR

4

Feb 26, 2026

0Bosnian FPR

4

Feb 26, 2026

0.007FPR (Norwegian Bokmål)

4

Feb 26, 2026

0.5FPR (Norwegian Bokmål)

4

Feb 26, 2026

2.7Norwegian Bokmål FPR

4

Feb 26, 2026

AfroScope-Data Low resource

100Macro-F1

4

Feb 26, 2026

ML-SUPERB 10-min Few-shots 1.0

LID-CA-XLSR_dual^L

85.8LID Accuracy

4

Feb 26, 2026

ML-SUPERB 10-min Few-shots

85.8LID Acc

4

Feb 26, 2026

VoxLingua107 (dev)

5.7Average Error Rate

4

Feb 26, 2026

87.41Weighted F1

4

Feb 26, 2026

Common Crawl (CC) (test)

72.59Macro Precision

3

Mar 25, 2026

GlotLID-C Full (1940 labels) (test)

94.4F1 Score

3

Feb 26, 2026

ITDI restricted to Ligurian, Venetian and Friulian (test)

0.4FPR

3

Feb 26, 2026

94.1Accuracy

3

Feb 26, 2026

Whisper-large-v3

99.9Accuracy

3

Feb 26, 2026

Bhasha-Abhijnaanam 20 languages native-script (test)

99.28Precision

3

Feb 26, 2026

Bhasha-Abhijnaanam 12 languages native-script (test)

99.73Precision

3

Feb 26, 2026

FLORES-200 ∩ CLD3 95 languages (test)

fasttext LID model

98.9F1 Score

3

Feb 26, 2026

77.7Accuracy

3

Feb 26, 2026

Agnostic Statistical Language Learning

Pure DP Identification

1Error Rate

2

Apr 10, 2026

Page 3 of 4

Popular datasets

FLORES UDHR FLEURS ML-SUPERB GlotLID-C

Follow for updates

Join SOTA2 Contact