NQ, TruthfulQA, WoW, HotpotQA, ELI5
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Knowledge Integration Quality | NQ, TruthfulQA, WoW, HotpotQA, ELI5 Aggregate | Average Performance76.7 | 32 | |
| Question Answering | NQ, TruthfulQA, WoW, HotpotQA, ELI5 | Avg Score (All Datasets)82.9 | 20 |
Showing 2 of 2 rows