List your company

Mathematical Reasoning on GSM8K (Acc, RL, SL, RE, SE)

100AccuracyVanilla
82.663287.164191.66596.1659Mar 23, 2026

Evaluation results

MethodLinks
Vanilla2026.031001,7222,0435.814.89
L12026.031009831,25910.177.94
EAT2026.031001,2731,5947.866.27
ROMCSC2026.031007851,04212.749.6
ROM2026.0399.21,0061,2549.867.91
Cut20482026.0398.331,4092,0416.984.82
Cut10242026.0396.679682,0419.994.74
Cut5122026.0383.335132,04116.244.08