| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Machine Translation | MQM Human Evaluation Japanese→English | MQM Score11.6 | 3 | |
| Machine Translation | MQM Human Evaluation English→Serbian | MQM Score15.8 | 3 | |
| Machine Translation | MQM Human Evaluation English→Chinese | MQM Score6.3 | 3 | |
| Machine Translation | MQM Human Evaluation Czech→Ukrainian | MQM Score5.3 | 3 | |
| Machine Translation | MQM Human Evaluation English→Swahili | MQM Score4.2 | 3 | |
| Machine Translation | MQM Human Evaluation English→Korean | MQM Score3.1 | 3 | |
| Machine Translation | MQM Human Evaluation English→German | MQM Score2.2 | 3 | |
| Machine Translation | MQM Human Evaluation English→Italian | MQM Score1.8 | 3 |