Machine Translation
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
27.8BLEU
8
Feb 26, 2026
24.3BLEU
8
Feb 26, 2026
0.261BLEU Score
8
Feb 26, 2026
25.9Average SacreBLEU
8
Feb 26, 2026
23SacreBLEU (Source->Target)
8
Feb 26, 2026
27.7SacreBLEU (Source->Target)
8
Feb 26, 2026
21.5BLEU
8
Feb 27, 2026
35.4BLEU (de-en)
8
Feb 26, 2026
51.66BLEU Score
8
Feb 26, 2026
0.446BLEU
8
Feb 26, 2026
4.87Validation Perplexity
8
Feb 26, 2026
3.87Training Perplexity
8
Feb 26, 2026
33.8BLEU
8
Feb 26, 2026
25.19BLEU
8
Feb 26, 2026
24.34BLEU Score
8
Feb 26, 2026
26.65BLEU
8
Feb 26, 2026
35.78BLEU Score
8
Mar 31, 2026
55.46BLEU Score
8
Feb 26, 2026
43.8BLEU
8
Feb 26, 2026
27.2BLEU
8
Feb 26, 2026
28.7BLEU
8
Feb 26, 2026
44.1Perplexity
8
Feb 26, 2026
47.8Score (en->de)
8
Feb 26, 2026
-68.01Average Error
8
Feb 26, 2026
-72.14Average Score
8
Feb 26, 2026