Wiki-based QA
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Question Answering | Wiki-based QA Finance (overall) | LLM-as-judge Score (1-5)3.9 | 5 | |
| Question Answering | Wiki-based QA Finance Event-driven queries (Q^vol_t) pin-layer quality | LLM Judge Score (1-5)3.97 | 5 | |
| Question Answering | Wiki-based QA Finance Standing queries (Q^bg_t) base-wiki quality | Score (1-5)3.87 | 5 |
Showing 3 of 3 rows