List your company

Mathematical Reasoning on AIME 25 (Speedup, Avg Tau)

8.78SpeedupJetFlow
1.84323.64415.4457.2459Jun 16, 2026

Evaluation results

MethodLinks
JetFlowBudget=256, Temperature=02026.068.789.82
DFlash-TBudget=256, Temperature=02026.068.339.24
JetFlowBudget=128, Temperature=02026.068.269.1
DFlash-TBudget=128, Temperature=02026.067.938.66
JetFlowBudget=64, Temperature=02026.066.477
DFlash-TBudget=64, Temperature=02026.066.46.96
JetFlowBudget=256, Temperature=12026.065.947.06
JetFlowBudget=128, Temperature=12026.065.766.49
DFlash-TBudget=128, Temperature=12026.065.45.98
DFlash-TBudget=256, Temperature=12026.065.266.2
JetFlowBudget=64, Temperature=12026.064.955.48
DFlash-TBudget=64, Temperature=12026.064.945.46
EAGLE-3Budget=64, Temperature=02026.062.354.04
EAGLE-3Budget=64, Temperature=12026.062.113.73