Mathematical Reasoning on OpenMathInstruct
1,578Avg Reasoning TokensDeepSeek-R1-Distill-Qwen-7B
Evaluation results
| Method | Links | ||
|---|---|---|---|
| DeepSeek-R1-Distill-Qwen-7BEvaluating Model=DeepSeek-R1-Distill-Qwen-7B2025.03 | 1,578 | — | |
| Qwen2.5-Math-72B-InstructEvaluating Model=Qwen2.5-Math-72B-Instruct2025.03 | — | 63.3 |