Multi-Hop QA on Bamboogle (out-of-domain, test)
34.4Accuracy
StepSearch
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.06 | 34.4 | |
2026.06 | 29.3 | |
2026.06 | 27.2 | |
2026.06 | 26.4 | |
2026.06 | 26.4 | |
2026.06 | 11.1 |
StepSearch
| Method | Links | |
|---|---|---|
2026.06 | 34.4 | |
2026.06 | 29.3 | |
2026.06 | 27.2 | |
2026.06 | 26.4 | |
2026.06 | 26.4 | |
2026.06 | 11.1 |