Multi-Hop Question Answering on Bamboogle (EM, F1)
32.23EM
GraphAnchor
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.01 | 32.23 | 42.73 | |
2026.01 | 32 | - | |
2026.01 | 30.89 | - | |
2026.01 | 30.56 | - | |
2026.01 | 30.4 | - | |
2026.01 | 28.9 | - | |
2026.01 | 28.89 | - | |
2026.01 | 28.69 | 36.55 | |
2026.01 | 27.78 | - | |
2026.01 | 27.2 | 37.46 | |
2026.01 | 27.2 | 35.22 | |
2026.01 | 26.39 | - | |
2026.01 | 25.56 | - | |
2026.01 | 24.8 | 34.25 | |
2026.01 | 24 | - | |
2026.01 | 24 | 32.66 | |
2026.01 | 23.2 | 32.46 | |
2026.01 | 22.56 | - | |
2026.01 | 22.4 | - | |
2026.01 | 21.44 | - | |
2026.01 | 20 | 25.13 | |
2026.01 | 20 | 26.09 | |
2026.01 | 18.5 | - | |
2026.01 | 16.8 | - | |
2026.01 | 16.8 | 24.82 | |
2026.01 | 16.8 | 25.91 | |
2026.01 | 16.67 | - | |
2026.01 | 16 | 24.4 | |
2026.01 | 15.2 | - | |
2026.01 | 15.2 | 26.74 | |
2026.01 | 14.4 | - | |
2026.01 | 14.4 | - | |
2026.01 | 13.6 | 21.62 | |
2026.01 | 12.8 | 21.15 | |
2026.01 | 12.5 | - | |
2026.01 | 6.2 | - | |
2026.01 | 5.56 | - |