Financial Reasoning on FinQA
77.6Accuracy
GPT-5 mini-high
Updated 8d ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2026.03 | 77.6 | 77.1 | - | - | - | - | |
2025.12 | 77.1 | 86.2 | - | - | - | - | |
2026.03 | 73.3 | 74.6 | - | - | - | - | |
2026.03 | 72.4 | 72.5 | - | - | - | - | |
2026.03 | 72.4 | 74.7 | - | - | - | - | |
2025.12 | 72.2 | 83.82 | - | - | - | - | |
2026.03 | 72.2 | 71.5 | - | - | - | - | |
2026.04 | 72.1 | - | - | - | 4.8 | - | |
2026.03 | 72 | 67.7 | - | - | - | - | |
2026.04 | 72 | - | - | - | 4.5 | - | |
2026.04 | 72 | - | - | - | 6.1 | - | |
2026.04 | 71.9 | - | - | - | 3.9 | - | |
2026.04 | 71.9 | - | - | - | 3.9 | - | |
2026.04 | 70.4 | - | - | - | 6.9 | - | |
2026.04 | 70.4 | - | - | - | 9.1 | - | |
2026.03 | 69.8 | 72.1 | - | - | - | - | |
2025.12 | 68.3 | 81.47 | - | - | - | - | |
2026.03 | 67.7 | 61.4 | - | - | - | - | |
2026.02 | 67.3 | - | - | - | - | - | |
2026.03 | 67.2 | 70.3 | - | - | - | - | |
2026.02 | 67.1 | - | - | - | - | - | |
| 66.7 | - | - | - | - | - | ||
2025.12 | 65.6 | 75.88 | - | - | - | - | |
2025.12 | 65.5 | 82.56 | - | - | - | - | |
2026.03 | 64.6 | 68 | - | - | - | - | |
2026.02 | 64.2 | - | - | - | - | - | |
2026.02 | 64.2 | - | - | - | - | - | |
2025.12 | 63.5 | 82.61 | - | - | - | - | |
2026.02 | 60.1 | - | - | - | - | - | |
2026.03 | 57.6 | 56.9 | - | - | - | - | |
2025.12 | 56.7 | 71.85 | - | - | - | - | |
2026.03 | 52.4 | 47.8 | - | - | - | - | |
2026.02 | 51.6 | - | - | - | - | - | |
2026.02 | 51.3 | - | - | - | - | - | |
| 51.1 | - | - | - | - | - | ||
2026.02 | 49.8 | - | - | - | - | - | |
2026.02 | 49.2 | - | - | - | - | - | |
2026.02 | 48.6 | - | - | - | - | - | |
2026.05 | 48.5 | - | - | - | - | - | |
2026.05 | 40.16 | - | - | - | - | - | |
2026.05 | 39.65 | - | - | - | - | - | |
2026.05 | 38.19 | - | - | - | - | - | |
2026.05 | 37.31 | - | - | - | - | - | |
2026.05 | 34.69 | - | - | - | - | - | |
2026.05 | 29.06 | - | - | - | - | - | |
2026.05 | 28.95 | - | - | - | - | - | |
2026.05 | 28.9 | - | - | - | - | - | |
2026.05 | 27.29 | - | - | - | - | - | |
2026.05 | 26.88 | - | - | - | - | - | |
2026.05 | 26.17 | - | - | - | - | - | |
2026.05 | 25.94 | - | - | - | - | - | |
2026.05 | 25.82 | - | - | - | - | - | |
2026.05 | 24.93 | - | - | - | - | - | |
2026.03 | 23.4 | 36.7 | - | - | - | - | |
2026.05 | 21.37 | - | - | - | - | - | |
2026.05 | 20.09 | - | - | - | - | - | |
2026.05 | 18.97 | - | - | - | - | - | |
2026.05 | 18.66 | - | - | - | - | - | |
2026.05 | 16.72 | - | - | - | - | - | |
2026.05 | 16.47 | - | - | - | - | - | |
2026.05 | 16.04 | - | - | - | - | - | |
2026.05 | 11.24 | - | - | - | - | - | |
2026.05 | 10.55 | - | - | - | - | - | |
2026.05 | 8.55 | - | - | - | - | - | |
2026.05 | 8.49 | - | - | - | - | - | |
2026.05 | 7.89 | - | - | - | - | - | |
2026.05 | 7.65 | - | - | - | - | - | |
2026.05 | 5.93 | - | - | - | - | - | |
2026.03 | 5.5 | 36.2 | - | - | - | - | |
| - | - | 57.87 | 60.02 | - | - | ||
| - | - | 58.49 | 60.96 | - | - | ||
| - | - | 59.7 | 62.11 | - | - | ||
| - | - | 60.54 | 63.48 | - | - | ||
| - | - | 56.49 | 58.33 | - | - | ||
| - | - | 56.75 | 58.81 | - | - | ||
| - | - | 53.95 | 55.76 | - | - | ||
| - | - | 54.64 | 56.97 | - | - | ||
| - | - | 49.53 | 52.08 | - | - | ||
| - | - | 48.77 | 50.9 | - | - | ||
2026.05 | - | - | - | - | - | 58 | |
2026.05 | - | - | - | - | - | 60.87 | |
2026.05 | - | - | - | - | - | 67.5 | |
2026.05 | - | - | - | - | - | 69 | |
2026.05 | - | - | 1.33 | 3.67 | - | - | |
2026.05 | - | - | 3.33 | 6.33 | - | - | |
2026.05 | - | - | 3.33 | 8.67 | - | - | |
2026.05 | - | - | 1.33 | 4.33 | - | - | |
2026.05 | - | - | 4.67 | 8.33 | - | - | |
2026.05 | - | - | 8.67 | 16 | - | - | |
2026.05 | - | - | 7 | 11.33 | - | - | |
2026.05 | - | - | 11.33 | 15.67 | - | - |