LongEval
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Long-context understanding | LongEval | Score79 | 16 | |
| Long-form Retrieval-Augmented Generation | LongEval Task 4 (primary) | ROUGE-L16.7 | 10 | |
| Scientific Document Retrieval | LongEval-Sci Task 1 (DCTR) (Snapshot 2) | ARP (nDCG@10)26.7 | 7 |
Showing 3 of 3 rows