List your company

Mathematical Reasoning on GSM8K 2021

82.6Peak AccuracyRM + Pessimism
79.16880.05980.9581.841Apr 6, 2026

Evaluation results

MethodLinks
RM + Pessimism2026.0482.681.11.5
Pessimism Only2026.0481.380.31
Reward Model2026.0479.371.57.7