Multi-hop Reasoning on HotpotQA (Accuracy, Success Rate)
72.2Accuracy
Qwen3-14B
Updated 1d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.05 | 72.2 | - | - | - | |
2026.05 | 71.4 | - | - | - | |
2026.05 | 70.9 | - | - | - | |
2026.05 | 70.3 | - | - | - | |
2026.05 | 69.6 | - | - | - | |
2026.05 | 68.7 | - | - | - | |
2026.05 | 68.3 | - | - | - | |
2026.05 | 67.1 | - | - | - | |
2026.05 | 66.5 | - | - | - | |
2026.05 | 60.9 | - | - | - | |
2026.05 | 60.9 | - | - | - | |
2026.05 | 60.6 | - | - | - | |
2026.05 | 57.6 | - | - | - | |
2026.05 | 56.5 | - | - | - | |
2026.05 | 55.8 | - | - | - | |
2026.04 | 50 | 0.63 | - | - | |
2026.05 | 49.9 | - | - | - | |
2026.05 | 48.5 | - | - | - | |
2026.05 | 47.7 | - | - | - | |
2026.05 | 41.8 | - | - | - | |
2026.04 | 38 | 0.41 | 0 | 80 | |
2026.05 | 34.8 | - | - | - | |
2026.05 | 30.8 | - | - | - |