Mathematical Reasoning on AIME Round 4 2024
0.94Average AccuracyQwen2.5-72B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Qwen2.5-72BBenchmark Version=Original2025.10 | 0.94 | 19,265 | |
| DeepSeek-R1-Distill-Qwen-32BBenchmark Version=Original2025.10 | 0.73 | 9,912.8 | |
| Qwen2.5-72BBenchmark Version=Evolved2025.10 | 0.7167 | 27,283.2 | |
| DeepSeek-R1-Distill-Qwen-7BBenchmark Version=Original2025.10 | 0.5667 | 16,890.5 | |
| DeepSeek-R1-Distill-Qwen-32BBenchmark Version=Evolved2025.10 | 0.5333 | 15,140.4 | |
| DeepSeek-R1-Distill-Qwen-7BBenchmark Version=Evolved2025.10 | 0.3933 | 21,092.7 | |
| DeepSeek-R1-Distill-Qwen-7BBenchmark Version=Delta2025.10 | -0.1734 | 4,202.2 | |
| DeepSeek-R1-Distill-Qwen-32BBenchmark Version=Delta2025.10 | -0.1967 | 5,227.6 | |
| Qwen2.5-72BBenchmark Version=Delta2025.10 | -0.2233 | 8,018.2 |