List your company
ResearchFormerly WizWand

Mathematical Reasoning on AIME 25 (Speedup and Acceptance Length)

6.99SpeedupDraft-OPD
2.91323.97165.036.0884May 28, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Draft-OPDModel=Q3-8B, Thinking Mode=Disabled, Temperature=02026.056.996.57
DFlashModel=Q3-8B, Thinking Mode=Disabled, Temperature=02026.056.46.04
Draft-OPDModel=Q3-4B, Thinking Mode=Disabled, Temperature=02026.056.396.6
DFlashModel=Q3-4B, Thinking Mode=Disabled, Temperature=02026.055.936.04
EAGLE-3Model=Q3-8B, Thinking Mode=Disabled, Temperature=02026.055.875.99
Draft-OPDModel=Q3-8B, Thinking Mode=Disabled, Temperature=0.62026.055.576.02
Draft-OPDModel=Q3-8B, Thinking Mode=Enabled, Temperature=02026.055.515.73
EAGLE-3Model=Q3-4B, Thinking Mode=Disabled, Temperature=02026.055.395.84
Draft-OPDModel=Q3-4B, Thinking Mode=Disabled, Temperature=0.62026.055.316.13
Draft-OPDModel=Q3-4B, Thinking Mode=Enabled, Temperature=02026.055.285.96
DFlashModel=Q3-8B, Thinking Mode=Disabled, Temperature=0.62026.055.195.62
DFlashModel=Q3-4B, Thinking Mode=Disabled, Temperature=0.62026.054.995.73
EAGLE-3Model=Q3-8B, Thinking Mode=Disabled, Temperature=0.62026.054.855.69
Draft-OPDModel=Q3-8B, Thinking Mode=Enabled, Temperature=0.62026.054.85.05
DFlashModel=Q3-8B, Thinking Mode=Enabled, Temperature=02026.054.775.19
DFlashModel=Q3-4B, Thinking Mode=Enabled, Temperature=02026.054.695.51
Draft-OPDModel=Q3-4B, Thinking Mode=Enabled, Temperature=0.62026.054.565.13
EAGLE-3Model=Q3-4B, Thinking Mode=Disabled, Temperature=0.62026.054.495.66
DFlashModel=Q3-8B, Thinking Mode=Enabled, Temperature=0.62026.054.344.66
DFlashModel=Q3-4B, Thinking Mode=Enabled, Temperature=0.62026.054.254.77
EAGLE-3Model=Q3-8B, Thinking Mode=Enabled, Temperature=02026.054.015.64
EAGLE-3Model=Q3-8B, Thinking Mode=Enabled, Temperature=0.62026.053.575.33
EAGLE-3Model=Q3-4B, Thinking Mode=Enabled, Temperature=02026.053.35.33
EAGLE-3Model=Q3-4B, Thinking Mode=Enabled, Temperature=0.62026.053.075.03