Mathematical Reasoning on MGSM (test)
75.6Accuracy (MGSM)
CodeLlama-7B (+ Soft-SC (ICE-Score))
Updated 3d ago
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 75.6 | - | - | - | - | - | - | - | - | ||
| 71.2 | - | - | - | - | - | - | - | - | ||
2025.02 | 62.8 | - | - | - | - | - | - | - | - | |
2025.12 | 62.1 | - | - | - | - | 56.8 | - | 60.4 | 69.2 | |
| 61.1 | - | - | - | - | - | - | - | - | ||
2025.12 | 58.3 | - | - | - | - | 50.4 | - | 58.4 | 66 | |
2025.02 | 57.2 | - | - | - | - | - | - | - | - | |
| 56.6 | - | - | - | - | - | - | - | - | ||
2025.02 | 56.3 | - | - | - | - | - | - | - | - | |
2025.02 | 54.1 | - | - | - | - | - | - | - | - | |
2025.02 | 49.9 | - | - | - | - | - | - | - | - | |
2025.02 | 49 | - | - | - | - | - | - | - | - | |
2025.02 | 48.3 | - | - | - | - | - | - | - | - | |
2025.02 | 46.7 | - | - | - | - | - | - | - | - | |
2025.12 | 45.1 | - | - | - | - | 40.8 | - | 45.2 | 49.2 | |
2025.02 | 44.6 | - | - | - | - | - | - | - | - | |
2024.10 | 42 | - | - | - | - | - | - | - | - | |
2025.12 | 40.5 | - | - | - | - | 34.4 | - | 41.6 | 45.6 | |
2025.02 | 39.2 | - | - | - | - | - | - | - | - | |
| 38.6 | - | - | - | - | - | - | - | - | ||
2024.10 | 38 | - | - | - | - | - | - | - | - | |
2025.12 | 37.6 | - | - | - | - | 33.2 | - | 37.6 | 42 | |
2024.10 | 33 | - | - | - | - | - | - | - | - | |
2025.12 | 28.7 | - | - | - | - | 20.8 | - | 28.4 | 36.8 | |
2025.12 | 26.5 | - | - | - | - | 21.6 | - | 21.6 | 36.4 | |
2025.12 | 13.9 | - | - | - | - | 12.8 | - | 10.4 | 18.4 | |
2025.12 | 10.1 | - | - | - | - | 8.4 | - | 4.4 | 17.6 | |
2024.10 | 7 | - | - | - | - | - | - | - | - | |
2024.10 | 3 | - | - | - | - | - | - | - | - | |
2023.05 | - | 72 | - | - | - | - | - | - | - | |
2023.05 | - | 45.9 | 57.9 | - | - | - | - | - | - | |
2023.05 | - | 72.2 | 87 | - | - | - | - | - | - | |
2023.05 | - | 75.9 | 85.8 | - | - | - | - | - | - | |
2026.01 | - | - | - | - | 82 | 74 | 78 | - | - | |
2026.01 | - | - | - | - | 92.4 | 84 | 88.2 | - | - | |
2026.01 | - | - | - | - | 89.6 | 85.6 | 87.6 | - | - | |
2026.01 | - | - | - | - | 92.4 | 84.4 | 88.4 | - | - | |
2026.01 | - | - | - | - | 91.2 | 86 | 88.6 | - | - | |
2026.01 | - | - | - | - | 90 | 84.8 | 87.4 | - | - | |
2026.01 | - | - | - | - | 87.6 | 74.8 | 81.2 | - | - | |
2026.01 | - | - | - | - | 88.4 | 79.6 | 84 | - | - | |
2026.01 | - | - | - | - | 88.4 | 75.6 | 82 | - | - | |
2026.01 | - | - | - | - | 88.8 | 74.8 | 81.8 | - | - | |
2026.01 | - | - | - | - | 90.4 | 79.6 | 85 | - | - |