Multi-hop Question Answering on MuSiQue Full (dev)
33.64EM ScoreG-reasoner
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| G-reasoner2025.09 | 33.64 | 47.89 | |
| Qwen3-Emb-8B2025.09 | 29.21 | 42.04 | |
| HippoRAG2025.09 | 24.62 | 36.16 | |
| GFM-RAG2025.09 | 23.4 | 33.87 |
| Method | Links | ||
|---|---|---|---|
| G-reasoner2025.09 | 33.64 | 47.89 | |
| Qwen3-Emb-8B2025.09 | 29.21 | 42.04 | |
| HippoRAG2025.09 | 24.62 | 36.16 | |
| GFM-RAG2025.09 | 23.4 | 33.87 |