Mathematical Reasoning on Math500 (ACC, Tokens)
92.35Accuracy
QwQ-32B
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.08 | 92.35 | 5,955.39 | |
2025.08 | 91.75 | 3,978.06 | |
2025.08 | 91.37 | 7,138.49 | |
2025.08 | 91.13 | 5,209.24 | |
2025.08 | 88.17 | 3,703.83 | |
2025.08 | 88.17 | 2,604.23 | |
2025.08 | 84.37 | 2,853.73 | |
2025.08 | 82.16 | 1,980.97 | |
2025.08 | -1.6 | -9.8 | |
2025.08 | -3.2 | -20.3 | |
2025.08 | -3.2 | -35 | |
2025.08 | -5.2 | -11.1 | |
2025.08 | -6.4 | -11.1 | |
2025.08 | -10.6 | -48.4 |