Mathematical Reasoning on MMLU-Pro Math
89.79Accuracy
MAC
Updated 21d ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2025.07 | 89.79 | 91.52 | 93.47 | 99 | 88.77 | |
2025.07 | 86.75 | 88.19 | 89.92 | 98.69 | 85.38 | |
2025.07 | 85.12 | 89.24 | 93.81 | 98.59 | 84.06 | |
2025.07 | 84.9 | 88.45 | 92.4 | 98.56 | 83.69 | |
2025.07 | 84.83 | 88.34 | 92.31 | 98.55 | 83.6 | |
2025.07 | 79.42 | 80.9 | 82.79 | 97.95 | 77.28 | |
2026.02 | 77.6 | - | - | - | - | |
2026.02 | 77.6 | - | - | - | - | |
2025.07 | 76.68 | 77.88 | 79.37 | 97.67 | 74.2 | |
2025.07 | 73.95 | 75.07 | 76.6 | 97.39 | 71.17 | |
2026.02 | 38.5 | - | - | - | - | |
2026.02 | 36.9 | - | - | - | - | |
2026.02 | 36.2 | - | - | - | - | |
2026.02 | 36.2 | - | - | - | - | |
2026.02 | 35.7 | - | - | - | - | |
2026.02 | 35.7 | - | - | - | - | |
2026.02 | 35.3 | - | - | - | - | |
2026.02 | 35.3 | - | - | - | - | |
2026.02 | 35.2 | - | - | - | - | |
2026.02 | 35.2 | - | - | - | - | |
2026.02 | 34.8 | - | - | - | - | |
2026.02 | 34.8 | - | - | - | - | |
2026.02 | 34.4 | - | - | - | - | |
2026.02 | 34.4 | - | - | - | - | |
2026.02 | 32.6 | - | - | - | - | |
2026.02 | 32.6 | - | - | - | - |