Verification on Synthetic Arithmetic
92.47AUROC
CRV
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.10 | 92.47 | 28.92 | 37.09 | |
2025.10 | 76.45 | 5.59 | 73.86 | |
2025.10 | 69.39 | 3.03 | 63.33 | |
2025.10 | 61.87 | 1.81 | 84.98 | |
2025.10 | 60.83 | 1.58 | 85.09 | |
2025.10 | 60.19 | 1.68 | 85.52 | |
2025.10 | 60.03 | 1.52 | 85.4 | |
2025.10 | 59.67 | 1.66 | 86.96 | |
2025.10 | 58.47 | 1.93 | 76.68 | |
2025.10 | 54.41 | 1.3 | 90.98 | |
2025.10 | 54.22 | 1.5 | 91.9 |