List your company

Mathematical Reasoning on MATH-500 (VAcc, RAcc, Delta Acc, TFR)

83.2VAcc (Verification Accuracy)MASTER
25.16840.23455.370.366Jun 5, 2025

Evaluation results

MethodLinks
MASTERTarget model=DeepSeek-R1-Distill-LLaMA-8B, Prompting=zero-shot2025.0683.23152.262.74
MASTERTarget model=Qwen2.5-Math-7B-Instruct, Prompting=zero-shot2025.0681.644.237.445.83
MASTERTarget model=LLaMA-3.2-1B-Instruct, Prompting=zero-shot2025.0629.83.426.488.59
MASTERTarget model=LLaMA-3-8B-Instruct, Prompting=zero-shot2025.0629.2623.279.45
MASTERTarget model=Gemma-2-2B-IT, Prompting=zero-shot2025.0627.43.823.686.13