Multi-hop Question Answering on SQuAD
25.8Exact Match (EM)
ZipRL-8B
Updated 6d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 25.8 | 42.4 | |
2026.05 | 25.6 | 43 | |
2026.05 | 25.2 | 40.3 | |
2026.05 | 24.4 | 41.6 | |
2026.05 | 24 | 42.2 | |
2026.05 | 23.8 | 39.5 | |
2026.05 | 23.2 | 41 | |
2026.05 | 23 | 39 | |
2026.05 | 21.8 | 36.5 | |
2026.05 | 21.4 | 38.2 | |
2026.05 | 20.8 | 34.9 | |
2026.05 | 19.4 | 33.8 | |
2026.05 | 19.2 | 36.9 | |
2026.05 | 18.6 | 35.3 | |
2026.05 | 17.8 | 32.3 | |
2026.05 | 17.4 | 37.3 | |
2026.05 | 15.2 | 30.3 | |
2026.05 | 14.6 | 28.5 | |
2026.05 | 13 | 28.1 | |
2026.05 | 13 | 26.4 | |
2026.05 | 12.8 | 29.5 | |
2026.05 | 12.2 | 30.6 | |
2026.05 | 11.4 | 20.5 | |
2026.05 | 10.4 | 25.5 | |
2026.05 | 10.2 | 22.9 | |
2026.05 | 8.8 | 17.6 | |
2026.05 | 8.6 | 24.5 | |
2026.05 | 5.6 | 19.7 | |
2026.05 | 5.6 | 17.8 | |
2026.05 | 5.4 | 13.1 |