List your company

Mathematical Reasoning on MATH 500 (pass@16 metrics)

59.7Mean Accuracy @16TTSFT
42.85247.22651.655.974Dec 2, 2025

Evaluation results

MethodLinks
TTSFTBackbone=Qwen2.5-Math-1.5B2025.1259.790.863.8——
OptPO-SFTBackbone=Qwen2.5-Math-1.5B2025.125991.260.2—25.29
OptPO-SFTBackbone=Llama-3.1-8B-Instruct2025.1243.682.847—19.84
TTSFTBackbone=Llama-3.1-8B-Instruct2025.1243.581.244.2——