Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Math Reasoning on AIME 25 (Speedup, tau)
Loading...
5.68
Speedup
DFlash
1.468
2.5615
3.655
4.7485
Feb 5, 2026
Speedup
tau
Updated 4d ago
Evaluation Results
Method
Method
Links
Speedup
tau
DFlash
Model=Q3-4B, Temperatu...
2026.02
5.68
7.27
DFlash
Model=Q3-8B, Temperatu...
2026.02
5.62
7.08
DFlash
Model=Q3-4B, Temperatu...
2026.02
3.73
4.92
DFlash
Model=Q3-8B, Temperatu...
2026.02
3.57
4.73
EAGLE-3
Model=Q3-4B, Temperatu...
2026.02
2.13
3.51
EAGLE-3
Model=Q3-8B, Temperatu...
2026.02
2.05
3.44
EAGLE-3
Model=Q3-8B, Temperatu...
2026.02
1.84
3.18
EAGLE-3
Model=Q3-4B, Temperatu...
2026.02
1.83
3.2
EAGLE-3
Model=Q3-4B, Temperatu...
2026.02
1.79
3.05
EAGLE-3
Model=Q3-8B, Temperatu...
2026.02
1.79
3
EAGLE-3
Model=Q3-4B, Temperatu...
2026.02
1.64
2.79
EAGLE-3
Model=Q3-8B, Temperatu...
2026.02
1.63
2.74
Feedback
Search any
task
Search any
task