List your company

Mathematical Reasoning on MATH 500 (Speedup, Acceptance Length)

7.64SpeedupDraft-OPD
3.61524.66015.7056.7499May 28, 2026

Evaluation results

MethodLinks
Draft-OPDModel=Q3-8B, Thinking Mode=Disabled, Temperature=02026.057.646.57
Draft-OPDModel=Q3-4B, Thinking Mode=Disabled, Temperature=02026.057.226.6
DFlashModel=Q3-8B, Thinking Mode=Disabled, Temperature=02026.056.816.04
Draft-OPDModel=Q3-8B, Thinking Mode=Disabled, Temperature=0.62026.056.616.02
DFlashModel=Q3-4B, Thinking Mode=Disabled, Temperature=02026.056.356.04
Draft-OPDModel=Q3-4B, Thinking Mode=Disabled, Temperature=0.62026.056.356.13
DFlashModel=Q3-8B, Thinking Mode=Disabled, Temperature=0.62026.056.185.62
EAGLE-3Model=Q3-8B, Thinking Mode=Disabled, Temperature=02026.056.075.99
DFlashModel=Q3-4B, Thinking Mode=Disabled, Temperature=0.62026.055.875.73
Draft-OPDModel=Q3-8B, Thinking Mode=Enabled, Temperature=02026.055.85.73
EAGLE-3Model=Q3-4B, Thinking Mode=Disabled, Temperature=02026.055.75.84
Draft-OPDModel=Q3-4B, Thinking Mode=Enabled, Temperature=02026.055.555.96
EAGLE-3Model=Q3-8B, Thinking Mode=Disabled, Temperature=0.62026.055.175.69
Draft-OPDModel=Q3-8B, Thinking Mode=Enabled, Temperature=0.62026.055.075.05
DFlashModel=Q3-8B, Thinking Mode=Enabled, Temperature=02026.055.015.19
EAGLE-3Model=Q3-4B, Thinking Mode=Disabled, Temperature=0.62026.054.935.66
Draft-OPDModel=Q3-4B, Thinking Mode=Enabled, Temperature=0.62026.054.915.13
DFlashModel=Q3-4B, Thinking Mode=Enabled, Temperature=02026.054.885.51
DFlashModel=Q3-8B, Thinking Mode=Enabled, Temperature=0.62026.054.574.66
DFlashModel=Q3-4B, Thinking Mode=Enabled, Temperature=0.62026.054.464.77
EAGLE-3Model=Q3-8B, Thinking Mode=Enabled, Temperature=02026.054.455.64
EAGLE-3Model=Q3-4B, Thinking Mode=Enabled, Temperature=02026.054.155.33
EAGLE-3Model=Q3-8B, Thinking Mode=Enabled, Temperature=0.62026.054.095.33
EAGLE-3Model=Q3-4B, Thinking Mode=Enabled, Temperature=0.62026.053.775.03