List your company

Math Reasoning on CNMO 2024 (accuracy, Avg, Delta)

81.94AccuracyPreMoE
-3.277618.846240.9763.0938May 23, 2025

Evaluation results

MethodLinks
PreMoEBase Model=Qwen3-30B-A3B, Sparsity=50%2025.0581.9479.92-0.77
PreMoEBase Model=openPangu-Ultra, Sparsity=31.25%2025.0579.1778.45-0.8
FullBase Model=Qwen3-30B-A3B, Sparsity=50%2025.0578.6580.69—
FullBase Model=openPangu-Ultra, Sparsity=31.25%2025.0577.4379.25—
FrequencyBase Model=openPangu-Ultra, Sparsity=31.25%2025.0575.6969.67-9.58
PreMoEBase Model=DeepSeek-R1, Sparsity=50%2025.057576.521.01
SEER (L)Base Model=openPangu-Ultra, Sparsity=31.25%2025.0573.6171.29-7.96
EASY-EPBase Model=openPangu-Ultra, Sparsity=31.25%2025.0573.4376.45-2.8
SEER (G)Base Model=openPangu-Ultra, Sparsity=31.25%2025.0572.470.93-8.32
Act-LogitsBase Model=openPangu-Ultra, Sparsity=31.25%2025.0572.476.91-2.34
EASY-EPBase Model=DeepSeek-R1, Sparsity=50%2025.0572.1874.69-0.82
FullBase Model=DeepSeek-R1, Sparsity=50%2025.0571.1875.51—
FrequencyBase Model=DeepSeek-R1, Sparsity=50%2025.0564.5849.93-25.58
Act-LogitsBase Model=DeepSeek-R1, Sparsity=50%2025.0562.6262.87-12.64
FrequencyBase Model=Qwen3-30B-A3B, Sparsity=50%2025.0554.6954.26-32.76
RandomBase Model=openPangu-Ultra, Sparsity=31.25%2025.0554.5150.13-29.12
EASY-EPBase Model=Qwen3-30B-A3B, Sparsity=50%2025.0552.6554.26-26.43
SEER (L)Base Model=DeepSeek-R1, Sparsity=50%2025.0536.6323.56-51.95
SEER (G)Base Model=DeepSeek-R1, Sparsity=50%2025.0536.6324.31-51.2
RandomBase Model=DeepSeek-R1, Sparsity=50%2025.0530.8826.69-48.82
RandomBase Model=Qwen3-30B-A3B, Sparsity=50%2025.057.9913.07-67.62
All-LogitsBase Model=openPangu-Ultra, Sparsity=31.25%2025.052.955.39-73.86
All-LogitsBase Model=DeepSeek-R1, Sparsity=50%2025.050.355.46-70.05
All-LogitsBase Model=Qwen3-30B-A3B, Sparsity=50%2025.0500.35-80.34
SEER (L)Base Model=Qwen3-30B-A3B, Sparsity=50%2025.0500.64-80.05
SEER (G)Base Model=Qwen3-30B-A3B, Sparsity=50%2025.0500.34-80.35
Act-LogitsBase Model=Qwen3-30B-A3B, Sparsity=50%2025.0500.82-79.87