| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Dialog Evaluation | Topical-Chat | Spearman Correlation0.577 | 35 | |
| Dialogue Evaluation Human Correlation | Topical-Chat | Naturalness Pearson (r)0.699 | 26 | |
| Text Quality Meta-evaluation | Topical-Chat (Local) | Understandability0.831 | 16 | |
| Dialogue Response Generation | Topical-Chat Global | Und98.5 | 16 | |
| Dialogue Evaluation | Topical-Chat turn-level | Naturalness (Pearson r)0.444 | 11 | |
| Comparative Assessment | Topical-Chat | Coherence60.89 | 7 |