Machine Translation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
88.2COMET Score
17
Feb 26, 2026
61.59XCOMET-XXL
17
Feb 26, 2026
87.73XCOMET-XXL
17
Feb 26, 2026
94.13XCOMET-XXL
17
Feb 26, 2026
0.898XCOMET-XXL
17
Feb 26, 2026
83.42XCOMET
17
Feb 26, 2026
1.68GPT-4 Score
17
Feb 26, 2026
1.76GPT-4 Score
17
Feb 26, 2026
1.84GPT-4 Score
17
Feb 26, 2026
2.08GPT-4 Score
17
Feb 26, 2026
74.64Translation Score (X -> Ar)
17
Feb 26, 2026
28Average BLEU
17
Feb 26, 2026
46.8CHRF
17
Feb 26, 2026
41.95BLEU
17
Feb 26, 2026
25.8BLEU
17
Feb 27, 2026
33.27BLEU
17
Feb 26, 2026
0.013MAE
16
May 11, 2026
36.7ChrF++ (All total)
16
Mar 18, 2026
63.6ChrF++ (high)
16
Mar 18, 2026
66.5ChrF++ (high)
16
Mar 18, 2026
10Standard Deviation of Score
16
Mar 13, 2026
34.1MT Score
16
Feb 26, 2026
48.2MT Score
16
Feb 26, 2026
0.617XCOMET-XXL
16
Feb 26, 2026
40.24BLEU
16
Feb 27, 2026