MQM
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
MQM EN-ZH annotations 2024 (test)
35.95Precision
6
MQM Human Evaluation Czech→German
10.2MQM Score
3
MQM Human Evaluation English→Marathi
3.1MQM Score
3
MQM gold dataset ZH-EN
49.6Precision
2
MQM gold dataset ZH-EN
4.3Precision
2
MQM gold dataset EN-DE
40.3Precision
2