List your company

Mathematical Reasoning on MATH original and paraphrased (train)

35.29Reference Score/RateQwen-Math
-1.21928.2591517.737527.21585May 21, 2026

Evaluation results

MethodLinks
Qwen-MathData Variant=Original, Metric Type=ACC(%)2026.0535.2953.14———1
Qwen-MathData Variant=Paraphrased, Metric Type=ACC(%)2026.0535.2947.14———1
Qwen-MathData Variant=Original, Metric Type=Con(%)2026.0533.86—50.43——1
Qwen-MathData Variant=Paraphrased, Metric Type=Con(%)2026.0533.86—46——1
DeepSeek-MathData Variant=Original, Metric Type=ACC(%)2026.0520.7137.14———1
DeepSeek-MathData Variant=Paraphrased, Metric Type=ACC(%)2026.0520.7130———1
DeepSeek-MathData Variant=Original, Metric Type=Con(%)2026.0518.57—31——1
DeepSeek-MathData Variant=Paraphrased, Metric Type=Con(%)2026.0518.57—26.57——0.999
Qwen-MathData Variant=Original, Metric Type=P_first2026.050.305——42.7—0.998
Qwen-MathData Variant=Paraphrased, Metric Type=P_first2026.050.305——40—0.998
Qwen-MathData Variant=Original, Metric Type=P_all2026.050.277———42.60.998
Qwen-MathData Variant=Paraphrased, Metric Type=P_all2026.050.277———38.80.998
DeepSeek-MathData Variant=Original, Metric Type=P_first2026.050.251——40.3—0.998
DeepSeek-MathData Variant=Paraphrased, Metric Type=P_first2026.050.251——32.7—0.998
DeepSeek-MathData Variant=Original, Metric Type=P_all2026.050.185———34.70.998
DeepSeek-MathData Variant=Paraphrased, Metric Type=P_all2026.050.185———28.40.998