Mathematical Problem Solving on Aggregated OOD Math Benchmarks (MATH500, AIME24, Minerva-Math, AMC23)
91.8MATH500 Score
DFPO
Updated 3d ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2026.02 | 91.8 | 56.67 | 32.35 | 88.33 | 67.29 | 40.25 | |
2026.02 | 89.6 | 43.33 | 29.04 | 82.5 | 61.12 | 36.45 | |
2026.02 | 89.6 | 50 | 31.62 | 86.67 | 64.47 | 38.37 | |
2026.02 | 89.4 | 50 | 30.51 | 83.33 | 63.31 | 37.72 | |
2026.02 | 88.6 | 48.33 | 27.21 | 80 | 61.04 | 36.25 | |
2026.02 | 88.4 | 50 | 31.25 | 80.83 | 62.62 | 37.18 | |
2026.02 | 87.4 | 45 | 27.21 | 83.33 | 60.74 | 36.23 | |
2026.02 | 87.2 | 46.67 | 30.15 | 82.5 | 61.63 | 36.62 | |
2026.02 | 87 | 51.67 | 29.41 | 85 | 63.27 | 37.34 | |
2026.02 | 86.8 | 45 | 26.84 | 82.5 | 60.29 | 35.77 | |
2026.02 | 84.4 | 60 | 26.84 | 82.5 | 63.44 | 37.71 |