Numerical Reasoning on RealHitBench
70.31Exact Match (EM)
DeepSeek-R1
Updated 3d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.04 | 70.31 | 72.54 | |
2026.04 | 58.37 | 64.44 | |
| 58.24 | 62.58 | ||
2026.04 | 57.98 | 64.92 | |
2026.03 | 55.51 | 61.98 | |
2025.12 | 55.38 | - | |
2026.04 | 55.38 | 59.16 | |
| 55.25 | 65.74 | ||
2026.04 | 54.6 | 59.06 | |
2026.04 | 54.6 | 64.97 | |
2026.04 | 54.47 | 61.6 | |
2026.04 | 53.05 | 62.31 | |
2025.12 | 52.53 | - | |
2026.04 | 52.4 | 61.33 | |
2026.04 | 50.97 | 60.33 | |
2025.12 | 49.03 | - | |
| 47.47 | 54.25 | ||
2025.12 | 47.34 | - | |
| 47.21 | 58.05 | ||
2026.03 | 47.05 | 50.61 | |
2025.12 | 46.95 | - | |
2025.06 | 45.4 | 53.77 | |
| 44.62 | 48.92 | ||
2026.04 | 44.1 | 50.06 | |
2025.12 | 43.7 | - | |
2026.03 | 42.93 | 49.68 | |
2026.04 | 42.54 | 48.94 | |
2026.04 | 39.82 | 44.42 | |
2025.12 | 39.43 | - | |
2025.12 | 38.91 | - | |
2026.04 | 38.65 | 50.12 | |
2026.04 | 36.58 | 48.99 | |
| 35.8 | 44.36 | ||
2026.04 | 35.54 | 43.74 | |
2026.04 | 34.63 | 39.03 | |
2026.04 | 32.3 | 40.44 | |
2026.04 | 31.26 | 39.77 | |
2025.12 | 31.25 | - | |
2026.04 | 31.13 | 39.14 | |
2026.04 | 29.83 | 38.29 | |
2026.03 | 29.31 | 39.81 | |
2026.04 | 28.66 | 35.76 | |
2026.03 | 27.63 | 36.68 | |
2026.04 | 26.98 | 39.23 | |
2025.12 | 24.9 | - | |
2026.03 | 22.4 | 31.65 | |
2026.03 | 22.05 | 30.13 | |
2025.06 | 17.94 | 33.57 | |
2025.06 | 17.64 | 24.96 | |
2026.04 | 15.69 | 28.36 | |
2025.06 | 15.18 | 24.64 | |
2026.03 | 14.55 | 20.8 | |
2025.12 | 14.53 | - | |
2026.04 | 14.53 | 27.21 | |
2026.03 | 13.75 | 19.01 | |
2025.12 | 13.36 | - | |
2026.04 | 13.36 | 24.76 | |
2025.06 | 11.54 | 24.97 | |
2026.04 | 10.38 | 22.58 | |
2026.03 | 10.25 | 13 | |
2025.06 | 9.34 | 22.88 | |
| 7.13 | 15.74 | ||
2026.04 | 5.32 | 19.75 | |
2026.03 | 4.02 | 5.75 | |
2025.06 | 1.15 | 4.72 | |
2025.12 | 0 | - |