Multi-Hop Question Answering on Musique (test val)
22.1Exact Match (EM)DeepControl
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DeepControlBackbone Model=Qwen2.5-7B2026.02 | 22.1 | 47.9 | |
| DeepControlBackbone Model=Qwen2.5-3B2026.02 | 11.8 | 41.1 |
| Method | Links | ||
|---|---|---|---|
| DeepControlBackbone Model=Qwen2.5-7B2026.02 | 22.1 | 47.9 | |
| DeepControlBackbone Model=Qwen2.5-3B2026.02 | 11.8 | 41.1 |