Retrieval on HotpotQA v1 (test)
65.9R@2E
Gfm-Retriever
Updated 26d ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.03 | 65.9 | - | 83.4 | 90.5 | 1.1 | |
2026.03 | 63.4 | 70 | 80.5 | 88.1 | 3.1 | |
2026.03 | 63.4 | 70.7 | 81.9 | 88 | 2.8 | |
2026.03 | 60.7 | 70.9 | 75.6 | 89.6 | 3.7 | |
2026.03 | 56.9 | 67.3 | 67 | 83 | 4.7 | |
2026.03 | 56.4 | 65 | 73.1 | 81.3 | 6.8 | |
2026.03 | 52.4 | 66.6 | 67.9 | 82 | 8.1 | |
2026.03 | 49.3 | 62.3 | 64.7 | 79.3 | 11.6 | |
2026.03 | 48.2 | 56.5 | 61.5 | 73 | 9.3 | |
2026.03 | 47.9 | 61 | 61 | 76.4 | 15.3 | |
2026.03 | 47.3 | 60.8 | 60.1 | 78.5 | 8.6 | |
2026.03 | 46.9 | 59.5 | 65.6 | 79 | 13.3 | |
2026.03 | 46.6 | 60.6 | 58.3 | 76.6 | 11.7 | |
2026.03 | 46.5 | 57.1 | 59.4 | 73.3 | 14.1 | |
2026.03 | 45.8 | 63.7 | 65.9 | 81.6 | 12.3 | |
2026.03 | 45.5 | 56.4 | 58.7 | 71.1 | 14.6 | |
2026.03 | 44.6 | 56.7 | 58.1 | 71.2 | 17.2 | |
2026.03 | 42.9 | 52.6 | 53.3 | 65.5 | 15.6 | |
2026.03 | 41.7 | 56 | 57.2 | 75.5 | 17.7 | |
2026.03 | 40 | 53.2 | 55.4 | 72.2 | 18.3 | |
2026.03 | 39.7 | 42.5 | 38.8 | 54.7 | 20.5 |