Multi-hop Question Answering on MuSiQue (avg@3)
73.3Score (avg@3)Qwen3-235B-A22B-Thinking
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-235B-A22B-ThinkingBaseline category=Strong Baseline2026.05 | 73.3 | |
| Qwen3-30B-A3B-Thinking + ACCMethod category=Our Method2026.05 | 70.4 | |
| Qwen3-30B-A3B-ThinkingBaseline category=Base Model2026.05 | 70.1 |