List your company

Mathematical Reasoning on GSM8K (test) (Acc, Steer, UTS, Entropy)

91.8AccuracyUTS-guided system
88.721689.520890.3291.1192Feb 6, 2026

Evaluation results

MethodLinks
UTS-guided systemTemperature (T)=1.02026.0291.81.721.6120.0006
UTS-guided systemTemperature (T)=0.52026.0291.651.451.6130.0001
UTS-guided systemTemperature (T)=1.52026.0291.111.851.610.0015
UTS-guided systemTemperature (T)=2.02026.0290.322.11.610.0018
UTS-guided systemTemperature (T)=2.52026.0290.312.281.6050.0068
UTS-guided systemTemperature (T)=3.02026.0288.842.441.6030.0058