MMT
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multi-modal Multi-image Reasoning | MMT (val) | Accuracy67.4 | 14 | |
| Machine Translation | MMT eng-xx very-low-resource | chrF++49.2 | 12 | |
| Machine Translation | MMT eng-xx high-resource | chrF++64.7 | 12 | |
| Machine Translation | MMT eng-xx (all) | chrF++55.1 | 12 | |
| Multi-image Understanding | MMT (val) | Accuracy67.4 | 11 | |
| Visual Understanding | MMT | Score1,075.5 | 8 | |
| Machine Translation | MMT xx-yy (all) | chrF++42.8 | 6 | |
| Machine Translation | MMT xx-eng low-resource | chrF++51.5 | 6 | |
| Machine Translation | MMT eng-xx low-resource | chrF++41.8 | 6 |
Showing 9 of 9 rows