Mathematical Reasoning on MATH original and paraphrased (train)
35.29Reference Score/RateQwen-Math
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Qwen-MathData Variant=Original, Metric Type=ACC(%)2026.05 | 35.29 | 53.14 | — | — | — | 1 | |
| Qwen-MathData Variant=Paraphrased, Metric Type=ACC(%)2026.05 | 35.29 | 47.14 | — | — | — | 1 | |
| Qwen-MathData Variant=Original, Metric Type=Con(%)2026.05 | 33.86 | — | 50.43 | — | — | 1 | |
| Qwen-MathData Variant=Paraphrased, Metric Type=Con(%)2026.05 | 33.86 | — | 46 | — | — | 1 | |
| DeepSeek-MathData Variant=Original, Metric Type=ACC(%)2026.05 | 20.71 | 37.14 | — | — | — | 1 | |
| DeepSeek-MathData Variant=Paraphrased, Metric Type=ACC(%)2026.05 | 20.71 | 30 | — | — | — | 1 | |
| DeepSeek-MathData Variant=Original, Metric Type=Con(%)2026.05 | 18.57 | — | 31 | — | — | 1 | |
| DeepSeek-MathData Variant=Paraphrased, Metric Type=Con(%)2026.05 | 18.57 | — | 26.57 | — | — | 0.999 | |
| Qwen-MathData Variant=Original, Metric Type=P_first2026.05 | 0.305 | — | — | 42.7 | — | 0.998 | |
| Qwen-MathData Variant=Paraphrased, Metric Type=P_first2026.05 | 0.305 | — | — | 40 | — | 0.998 | |
| Qwen-MathData Variant=Original, Metric Type=P_all2026.05 | 0.277 | — | — | — | 42.6 | 0.998 | |
| Qwen-MathData Variant=Paraphrased, Metric Type=P_all2026.05 | 0.277 | — | — | — | 38.8 | 0.998 | |
| DeepSeek-MathData Variant=Original, Metric Type=P_first2026.05 | 0.251 | — | — | 40.3 | — | 0.998 | |
| DeepSeek-MathData Variant=Paraphrased, Metric Type=P_first2026.05 | 0.251 | — | — | 32.7 | — | 0.998 | |
| DeepSeek-MathData Variant=Original, Metric Type=P_all2026.05 | 0.185 | — | — | — | 34.7 | 0.998 | |
| DeepSeek-MathData Variant=Paraphrased, Metric Type=P_all2026.05 | 0.185 | — | — | — | 28.4 | 0.998 |