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

Quality Estimation research benchmarks – Page 2 · SOTA2 Research

Quality Estimation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

WMT EN-ZH 2021 (test)

0.366Pearson Correlation

5

Mar 27, 2026

WMT EN-DE 2021 (test)

51.9Pearson Correlation

5

Mar 27, 2026

WMT23 en-de AIRC translations (test)

83.3AUC

4

May 26, 2026

WMT23 en-de Lan-BridgeMT translations (test)

0.801AUC

4

May 26, 2026

en-de GPT4-5shot translations WMT23 (test)

0.715AUC

4

May 26, 2026

YouCook2 FG Eval

VC-Inspector-3B

44.29Kendall's Tau-b

4

Apr 21, 2026

ActivityNet FG (eval)

VC-Inspector-3B

49.53Kendall's Tau (b)

4

Apr 21, 2026

Surrey Low-Resource dataset (Overall)

0.592Spearman Correlation

4

Mar 17, 2026

0.625Pearson R

4

Feb 26, 2026

0.537Pearson Correlation

4

Feb 26, 2026

0.626Pearson Correlation

4

Feb 26, 2026

0.588Pearson R

4

Feb 26, 2026

0.552Pearson Correlation

4

Feb 26, 2026

0.533Pearson Correlation

4

Feb 26, 2026

0.53Pearson Correlation

4

Feb 26, 2026

0.067QE Score (en-pt)

4

Feb 26, 2026

Monte Carlo Seq. Entropy Sigmoid

1.674BCE

4

Feb 26, 2026

0.642BCE

4

Feb 26, 2026

IWSLT long-form EN-ZH 2026

65.8Accuracy

3

Jun 26, 2026

IWSLT long-form EN-DE 2026

50.1Accuracy

3

Jun 26, 2026

TruthfulQA (test)

1.698BCE

3

Feb 26, 2026

0.642BCE Loss

3

Feb 26, 2026

0.334Pearson r

3

Feb 26, 2026

0.318Pearson Correlation (r)

3

Feb 26, 2026

0.289Pearson Correlation (r)

3

Feb 26, 2026

Page 2 of 3

Popular datasets

WMT Surrey Low-Resource IWSLT English-Indic QE Surrey Low-Resource dataset

Follow for updates

Join SOTA2 Contact