| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Subjective Rubric-based Scoring | OmniScore overall (test) | MAE0.78 | 5 | |
| Multi-task Scoring | OmniScore (Evaluation Set) | Average MA0.99 | 5 | |
| Translation | OmniScore Evaluation Set | MAE0.68 | 5 | |
| Summarization | OmniScore Evaluation Set | MAE0.91 | 5 | |
| Question Answering | OmniScore Evaluation Set | MAE0.64 | 5 | |
| Paraphrase | OmniScore Evaluation Set | MAE0.86 | 5 | |
| Headline Generation | OmniScore Evaluation Set | MAE0.6 | 5 |