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

Machine Translation research benchmarks – Page 28 · SOTA2 Research

Machine Translation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

RefuteBench Machine Translation 1.0 (test)

87.6FA

7

Feb 26, 2026

Opus-100 non-English

18.4BLEU

7

Feb 26, 2026

88.5COMET

7

Feb 26, 2026

91.9COMET

7

Feb 26, 2026

WMT average '22 (test)

85.8COMET Score

7

Feb 26, 2026

WMT'22 en-de (test)

87COMET Score

7

Feb 26, 2026

Adaptive kNN-MT

15.96BLEU

7

Feb 26, 2026

31.72BLEU

7

Feb 26, 2026

JRC-Acquis De-En (test)

M-RAG (Mixtral 8 × 7B)

48.15BLEU

7

Feb 26, 2026

JRC-Acquis En-Es (test)

M-RAG (Mixtral 8 × 7B)

32.7BLEU

7

Feb 26, 2026

JRC-Acquis Es-En (test)

M-RAG (Mixtral 8 × 7B)

39.98BLEU

7

Feb 26, 2026

WMT Zh-En subset of 300 sentences 2022 (test)

2Δ Under-translation

7

Feb 26, 2026

WMT 2016, 2019, 2020 (test)

33.5Score (Ro)

7

Feb 26, 2026

FLORES-200 snd_Arab-English (test)

87.5COMET-22

7

Feb 26, 2026

FLORES-200 npi_Deva-English (test)

91.1COMET-22

7

Feb 26, 2026

FLORES-200 khm_Khmr-English (test)

87.1COMET-22

7

Feb 26, 2026

FLORES-200 amh_Ethi-English (test)

88COMET-22

7

Feb 26, 2026

FLORES-200 hye_Armn-English (test)

88.8COMET-22

7

Feb 26, 2026

NEWS En-De (test)

back-translation

35.7BLEU

7

Feb 26, 2026

57.3BLEU Score

7

Feb 26, 2026

DGT-TM en-de 1M

62.02BLEU

7

Feb 26, 2026

DGT-TM de-en DGT-1M

69.99BLEU Score

7

Feb 26, 2026

JRC-A en -> de (test)

88.88COMET-22

7

Feb 26, 2026

JRC-A de -> en (test)

88.46COMET-22 Score

7

Feb 26, 2026

DGT-TM en -> de (test)

89.44COMET-22

7

Feb 26, 2026

Page 28 of 58

Popular datasets

WMT FLORES IWSLT newstest Flores-200

Follow for updates

Join SOTA2 Contact