Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on AIME 25 (Speedup, Avg Tau)
Loading...
8.78
Speedup
JetFlow
1.8432
3.6441
5.445
7.2459
Jun 16, 2026
Speedup
Avg Accepted Length (τ)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Speedup
Avg Accepted Length (τ)
JetFlow
Budget=256, Temperature=0
2026.06
8.78
9.82
DFlash-T
Budget=256, Temperature=0
2026.06
8.33
9.24
JetFlow
Budget=128, Temperature=0
2026.06
8.26
9.1
DFlash-T
Budget=128, Temperature=0
2026.06
7.93
8.66
JetFlow
Budget=64, Temperature=0
2026.06
6.47
7
DFlash-T
Budget=64, Temperature=0
2026.06
6.4
6.96
JetFlow
Budget=256, Temperature=1
2026.06
5.94
7.06
JetFlow
Budget=128, Temperature=1
2026.06
5.76
6.49
DFlash-T
Budget=128, Temperature=1
2026.06
5.4
5.98
DFlash-T
Budget=256, Temperature=1
2026.06
5.26
6.2
JetFlow
Budget=64, Temperature=1
2026.06
4.95
5.48
DFlash-T
Budget=64, Temperature=1
2026.06
4.94
5.46
EAGLE-3
Budget=64, Temperature=0
2026.06
2.35
4.04
EAGLE-3
Budget=64, Temperature=1
2026.06
2.11
3.73
Feedback
Search any
task
Search any
task