Mathematical Reasoning on MATH 500 (MATH-500 Metric)
78MATH-500 ScoreFull
Evaluation Results
| Method | Links | |
|---|---|---|
| FullModel=ERNIE-21B, Pruning Ratio=0%, Protocol=Zero-shot2026.03 | 78 | |
| AIMERModel=ERNIE-21B, Pruning Ratio=25%, Protocol=Zero-shot2026.03 | 69.2 | |
| MagnitudeModel=ERNIE-21B, Pruning Ratio=25%, Protocol=Zero-shot2026.03 | 64 | |
| RandomModel=ERNIE-21B, Pruning Ratio=25%, Protocol=Zero-shot2026.03 | 60.6 | |
| REAPModel=ERNIE-21B, Pruning Ratio=25%, Protocol=Zero-shot2026.03 | 47.4 | |
| SEERModel=ERNIE-21B, Pruning Ratio=25%, Protocol=Zero-shot2026.03 | 36.8 | |
| EANModel=ERNIE-21B, Pruning Ratio=25%, Protocol=Zero-shot2026.03 | 35.6 | |
| AIMERModel=ERNIE-21B, Pruning Ratio=50%, Protocol=Zero-shot2026.03 | 34.8 | |
| FrequencyModel=ERNIE-21B, Pruning Ratio=25%, Protocol=Zero-shot2026.03 | 31.6 | |
| FullModel=OLMoE-7B, Pruning Ratio=0%, Protocol=Zero-shot2026.03 | 22.2 | |
| RandomModel=ERNIE-21B, Pruning Ratio=50%, Protocol=Zero-shot2026.03 | 19.8 | |
| REAPModel=ERNIE-21B, Pruning Ratio=50%, Protocol=Zero-shot2026.03 | 17.8 | |
| MagnitudeModel=ERNIE-21B, Pruning Ratio=50%, Protocol=Zero-shot2026.03 | 13 | |
| REAPModel=OLMoE-7B, Pruning Ratio=25%, Protocol=Zero-shot2026.03 | 5.6 | |
| AIMERModel=OLMoE-7B, Pruning Ratio=25%, Protocol=Zero-shot2026.03 | 5.6 | |
| RandomModel=OLMoE-7B, Pruning Ratio=25%, Protocol=Zero-shot2026.03 | 3.4 | |
| EANModel=ERNIE-21B, Pruning Ratio=50%, Protocol=Zero-shot2026.03 | 2.6 | |
| FrequencyModel=OLMoE-7B, Pruning Ratio=25%, Protocol=Zero-shot2026.03 | 2.4 | |
| SEERModel=ERNIE-21B, Pruning Ratio=50%, Protocol=Zero-shot2026.03 | 2 | |
| FrequencyModel=ERNIE-21B, Pruning Ratio=50%, Protocol=Zero-shot2026.03 | 1.8 | |
| SEERModel=OLMoE-7B, Pruning Ratio=25%, Protocol=Zero-shot2026.03 | 1.2 | |
| EANModel=OLMoE-7B, Pruning Ratio=25%, Protocol=Zero-shot2026.03 | 0.6 | |
| MagnitudeModel=OLMoE-7B, Pruning Ratio=25%, Protocol=Zero-shot2026.03 | 0.4 |