| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Translation | Translation | COMET Score86.31 | 34 | |
| Translation | Translation | chrF41.8 | 20 | |
| Machine Translation | Translation (test) | BLEU29.58 | 20 | |
| Machine Translation | Zh-En document-level translation | d-COMET85.83 | 18 | |
| Machine Translation | Fr-En document-level translation | d-COMET87 | 18 | |
| Machine Translation | Translation Ru-En document-level | d-COMET84.59 | 18 | |
| Machine Translation | Es-En document-level translation | d-COMET88.99 | 18 | |
| Machine Translation | Translation | LLM-as-Judge Score39.23 | 13 | |
| Translation | Translation | chrF0.413 | 8 | |
| Translation | Translation Es-En | BLEU32.65 | 4 | |
| Translation | Translation Synth | R Score (%)55.8 | 3 | |
| Translation | Translation XLow Tier | R Metric53.5 | 3 | |
| Translation | Translation Low Tier | R Score70.2 | 3 | |
| Translation | Translation High Tier | R Score89.6 | 3 | |
| Machine Translation Reranking | English-Arabic Translation (Evaluation Set) | Change Rate11.44 | 1 |