Multi-Hop QA on 2Wiki out-of-domain (test)
37Accuracy
GiGPO
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.06 | 37 | |
2026.06 | 36.6 | |
2026.06 | 32 | |
2026.06 | 31.9 | |
2026.06 | 30 | |
2026.06 | 29.2 |
GiGPO
| Method | Links | |
|---|---|---|
2026.06 | 37 | |
2026.06 | 36.6 | |
2026.06 | 32 | |
2026.06 | 31.9 | |
2026.06 | 30 | |
2026.06 | 29.2 |