Logic on Zebra-grid
26AccuracyNPG-Muse-8B
Evaluation Results
| Method | Links | |
|---|---|---|
| NPG-Muse-8BBackbone=Qwen3-8B-Base2025.08 | 26 | |
| Qwen2.5-14B-Instruct-1MSize=14B, Type=Instruct, Context Length=1M2025.08 | 20.5 | |
| Qwen3-14B-BaseSize=14B, Type=Base2025.08 | 15.9 | |
| Qwen3-8B-BaseSize=8B, Type=Base2025.08 | 11.9 | |
| NPG-Muse-7BBackbone=Qwen2.5-7B-Instruct-1M2025.08 | 10.5 | |
| Qwen2.5-7B-Instruct-1MSize=7B, Type=Instruct, Context Length=1M2025.08 | 9.2 |