CorpusQA
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multi-hop grounding | CorpusQA 1M | Score53.11 | 6 | |
| Corpus-level evidence aggregation | CorpusQA 128K-token | LLM-as-Judge Accuracy19.453 | 4 | |
| Multi-hop grounding | CorpusQA 4M | Score14.29 | 3 |
Showing 3 of 3 rows