List your company

Mathematics Reasoning on MATH (EM)

92.8Exact Match (EM)CoT2-Meta
77.92881.78985.6589.511Mar 30, 2026

Evaluation results

MethodLinks
CoT2-MetaStrategy=Ours (CoT2-Meta), Inference Budget=C=162026.0392.8
ReST-MCTS*Strategy=ReST-MCTS*, Inference Budget=C=162026.0389.2
Vanilla ToTStrategy=Vanilla ToT, Inference Budget=C=162026.0387.4
Best-of-16Strategy=Best-of-16, Inference Budget=C=162026.0384.2
Greedy CoTStrategy=Greedy CoT, Inference Budget=C=162026.0378.5