Share your thoughts, 1 month free Claude Pro on usSee more

Mathematical Reasoning on MATH 8B Instruct (test)

23Accuracy

Prob Margin + Both

Updated 4d ago

Evaluation Results

Method	Links
Prob Margin + Both 2026.04		23
Top1 Prob + Both 2026.04		22.8
Top1 Prob + Planner 2026.04		22.4
Top1 Prob + EOS Temp. 2026.04		22.4
Prob Margin 2026.04		19.6
Temperature Sampling 2026.04		19.4
Top1 Prob 2026.04		19.2
Init. Position 2026.04		17.6
Ancestral Sampling 2026.04		13.2