| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Summarization | MultiNews | F1 Score34.79 | 28 | |
| Summarization | MultiNews (test) | Comprehensiveness4.98 | 24 | |
| Summarization | MultiNews | ROUGE Score24.6 | 10 | |
| Summarization | MultiNews | ROUGE-1 Std Dev0.11 | 8 | |
| Latency Evaluation | MultiNews | End-to-End Latency3.86 | 6 | |
| Summarization | MultiNews LongBench (test) | ROUGE-1 Score48.49 | 3 | |
| Summarization | MultiNews | Accuracy25.3 | 2 |