Multi-hop QA on MuSiQue
52.8EM
CoopRAG (Gemma2-27B)
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.12 | 52.8 | 66.7 | |
2025.12 | 52.6 | 66.6 | |
2025.12 | 52.3 | 67.1 | |
2025.12 | 52.2 | 65.2 | |
2025.12 | 42.2 | 54.9 | |
2025.12 | 40.5 | 53.1 | |
2025.12 | 37.2 | 48.6 | |
2025.12 | 35 | 49.3 | |
2025.12 | 34.7 | 45.7 | |
2026.02 | 34.3 | 45.8 | |
2026.01 | 34 | 47 | |
2026.02 | 33.7 | 44.7 | |
2025.12 | 33.6 | 44.8 | |
2025.12 | 30.6 | 40.9 | |
2026.01 | 28 | 41.1 | |
2025.12 | 27.7 | 39.2 | |
2025.12 | 27.3 | 38.5 | |
2025.12 | 27 | 42 | |
2025.12 | 26.2 | 35.1 | |
2025.12 | 25.8 | 34.6 | |
2026.01 | 24.7 | 36.2 | |
2025.12 | 24 | 31.3 | |
2025.12 | 24 | 35.9 | |
2026.02 | 22.7 | 36.9 | |
2025.12 | 20.7 | 28.9 | |
2025.12 | 20.3 | 28.8 | |
2026.01 | 19.7 | 30.6 | |
2026.01 | 19.5 | 30.3 | |
2026.02 | 18.7 | 28.1 | |
2026.01 | 17.8 | 26.7 | |
2026.01 | 16.7 | 25.6 | |
2025.01 | 16.6 | 28.2 | |
2025.01 | 14.8 | 23.6 | |
2025.01 | 13.6 | 25.5 | |
2025.01 | 13 | 25.4 | |
2025.01 | 11.4 | 20.4 | |
2025.01 | 10.6 | 20.2 | |
2025.01 | 10.4 | 19.8 | |
2025.01 | 9 | 18.9 | |
2025.01 | 8.4 | 18 | |
2025.12 | 2 | 9.3 | |
2025.12 | 0.5 | 1.6 |