Machine Translation Evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
86.4SPA
65
Mar 16, 2026
0.327de-en
25
May 13, 2026
60.1Score (En-De)
19
Feb 26, 2026
91.2Overall Score
19
Feb 26, 2026
44.5Pearson R
19
Feb 26, 2026
67.3Pearson Correlation (Pyramid)
19
Feb 26, 2026
91.6Accuracy (System, 3 LPs)
16
Feb 26, 2026
0.588MAE (EN→DE)
12
Feb 26, 2026
73.79MT Empty Score
12
Feb 26, 2026
0.653Kendall Tau
12
Feb 26, 2026
65Score (XX-En)
7
Mar 18, 2026
0.945Quality (cs-uk)
6
Mar 11, 2026
54.3Score (en-ha)
6
Mar 11, 2026
0.65Correlation
5
Feb 26, 2026
0.883Pearson Correlation (|r|)
5
Feb 26, 2026
0.951Pearson Correlation (|r|)
5
Feb 26, 2026
0.974Pearson Correlation (|r|)
5
Feb 26, 2026
0.991|r|
5
Feb 26, 2026
8.657HT Mean Score
4
Jun 25, 2026