Multi-Hop QA on MuSiQue (out-of-domain test)
17.4Accuracy
StepSearch
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.06 | 17.4 | |
2026.06 | 12.7 | |
2026.06 | 12.1 | |
2026.06 | 10.3 | |
2026.06 | 9.8 | |
2026.06 | 7.2 |
StepSearch
| Method | Links | |
|---|---|---|
2026.06 | 17.4 | |
2026.06 | 12.7 | |
2026.06 | 12.1 | |
2026.06 | 10.3 | |
2026.06 | 9.8 | |
2026.06 | 7.2 |