Machine Translation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
96.93XCOMET Score
24
Feb 26, 2026
88.5COMET
24
Feb 26, 2026
32.09SacreBLEU
24
Apr 8, 2026
30.17BLEU
24
Mar 11, 2026
81.11KIWI Score
23
Apr 28, 2026
37.1Translation Quality Score
23
Mar 16, 2026
79.23COMET
23
May 29, 2026
30.96BLEU
23
May 26, 2026
36.2BLEU
23
Jun 16, 2026
39.1BLEU
23
Feb 26, 2026
60.23BLEU Score
23
Feb 26, 2026
29.12BLEU
23
Feb 26, 2026
4.589M-Prometheus (Macro Avg.)
22
Jun 23, 2026
13.27SacreBLEU
22
Jun 11, 2026
21.9BLEU
22
May 26, 2026
37.85BLEU Score
22
Mar 31, 2026
26.56BLEU Score
22
Mar 31, 2026
34.12BLEU
22
Mar 31, 2026
15.78BLEU Score
22
Mar 31, 2026
80.7KIWI Score
22
Feb 26, 2026
27.78SacreBLEU
22
Apr 8, 2026
28.3SacreBLEU
22
Apr 8, 2026
98.04xCOMET (DE)
22
Feb 26, 2026
37.95BLEU Score
22
Feb 26, 2026
27.25BLEU
22
Feb 26, 2026