Question Answering on ARC Easy (ARC-e, Avg)
78.37ARC-e AccuracyBaseline
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| BaselineType=None, Storage=31.41GB, Model Family=DeepSeek-V2-Lite, Evaluation Protocol=Zero-shot2026.06 | 78.37 | 68.6 | |
| WandaType=P25%, Storage=31.41GB, Model Family=DeepSeek-V2-Lite, Evaluation Protocol=Zero-shot2026.06 | 76.64 | 66.62 | |
| WandaType=P25% Q4b, Storage=7.70GB, Model Family=DeepSeek-V2-Lite, Evaluation Protocol=Zero-shot2026.06 | 76.64 | 69.2 | |
| OursQType=P25% Q4b, Storage=6.00GB, Model Family=DeepSeek-V2-Lite, Evaluation Protocol=Zero-shot2026.06 | 76.35 | 67.61 | |
| PuzzleMoEType=M25%, Storage=25.04GB, Model Family=Deepseek-MoE-16B, Evaluation Protocol=Zero-shot2026.06 | 75.7 | 62.36 | |
| PuzzleMoEType=M50%, Storage=17.34GB, Model Family=Deepseek-MoE-16B, Evaluation Protocol=Zero-shot2026.06 | 75.2 | 62.08 | |
| MoNEType=P25%, Storage=24.00GB, Model Family=DeepSeek-V2-Lite, Evaluation Protocol=Zero-shot2026.06 | 74.62 | 65.65 | |
| Attribution-guided and Coverage-Maximized Expert-wise PruningType=P50%, Storage=16.57GB, Model Family=DeepSeek-V2-Lite, Evaluation Protocol=Zero-shot2026.06 | 73.78 | 64.92 | |
| OursQType=P25% Q4b, Storage=6.26GB, Model Family=Deepseek-MoE-16B, Evaluation Protocol=Zero-shot2026.06 | 73.74 | 63.78 | |
| MoNEType=P25% Q4b, Storage=6.00GB, Model Family=DeepSeek-V2-Lite, Evaluation Protocol=Zero-shot2026.06 | 73.51 | 63.97 | |
| He et al.Type=P25% Q4b, Storage=6.00GB, Model Family=DeepSeek-V2-Lite, Evaluation Protocol=Zero-shot2026.06 | 73.51 | 63.97 | |
| BaselineType=None, Storage=32.7GB, Model Family=Deepseek-MoE-16B, Evaluation Protocol=Zero-shot2026.06 | 73.19 | 65.62 | |
| EAC-MoEType=P11% Q3.03b, Storage=7.19GB, Model Family=Deepseek-MoE-16B, Evaluation Protocol=Zero-shot2026.06 | 73.15 | 65.3 | |
| C-PruneType=P25% Q4b, Storage=6.00GB, Model Family=DeepSeek-V2-Lite, Evaluation Protocol=Zero-shot2026.06 | 72.81 | 61.81 | |
| WandaType=P25%, Storage=32.7GB, Model Family=Deepseek-MoE-16B, Evaluation Protocol=Zero-shot2026.06 | 72.26 | 61.56 | |
| MoE-I2Type=L53.98%, Storage=15.39GB, Model Family=DeepSeek-V2-Lite, Evaluation Protocol=Zero-shot2026.06 | 71.8 | 59.62 | |
| EAC-MoEType=P38% Q3.03b, Storage=4.47GB, Model Family=Deepseek-MoE-16B, Evaluation Protocol=Zero-shot2026.06 | 71.55 | 62.7 | |
| WandaType=P50%, Storage=32.7GB, Model Family=Deepseek-MoE-16B, Evaluation Protocol=Zero-shot2026.06 | 71.46 | 60.82 | |
| Attribution-guided and Coverage-Maximized Expert-wise PruningType=P50%, Storage=17.34GB, Model Family=Deepseek-MoE-16B, Evaluation Protocol=Zero-shot2026.06 | 71.38 | 62.34 | |
| He et al.Type=P25% Q4b, Storage=7.70GB, Model Family=Deepseek-MoE-16B, Evaluation Protocol=Zero-shot2026.06 | 70.75 | 59.7 | |
| MoNEType=P50%, Storage=16.57GB, Model Family=DeepSeek-V2-Lite, Evaluation Protocol=Zero-shot2026.06 | 67.17 | 59.8 | |
| He et al.Type=P50%, Storage=16.57GB, Model Family=DeepSeek-V2-Lite, Evaluation Protocol=Zero-shot2026.06 | 58.92 | 53.88 | |
| WandaType=P50%, Storage=31.41GB, Model Family=DeepSeek-V2-Lite, Evaluation Protocol=Zero-shot2026.06 | 50.84 | 49.29 | |
| He et al.Type=P50%, Storage=17.34GB, Model Family=Deepseek-MoE-16B, Evaluation Protocol=Zero-shot2026.06 | 41.41 | 44.17 | |
| C-PruneType=P50%, Storage=16.57GB, Model Family=DeepSeek-V2-Lite, Evaluation Protocol=Zero-shot2026.06 | 35.65 | 42.39 | |
| MoNEType=P25%, Storage=25.04GB, Model Family=Deepseek-MoE-16B, Evaluation Protocol=Zero-shot2026.06 | 25.08 | 33.94 | |
| MoNEType=P50%, Storage=17.34GB, Model Family=Deepseek-MoE-16B, Evaluation Protocol=Zero-shot2026.06 | 24.58 | 33.24 |