Mathematical Reasoning on GSM8K, MATH500, AMC, Olympiad Bench, AIME (test)
85.3GSM8K Accuracy
InFamilySteer
Updated 5d ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2026.05 | 85.3 | 59.8 | 37.5 | 20 | 0 | 61.4 | |
2026.05 | 84.8 | 64.6 | 42.5 | 20.7 | 10 | 62.5 | |
2026.05 | 83.7 | 61.6 | 37.5 | 21 | 6.7 | 61.3 | |
2026.05 | 83.6 | 63 | 42.5 | 20 | 0 | 61.2 | |
2026.05 | 82.5 | 49.8 | 25 | 12.7 | 0 | 55.9 | |
2026.05 | 82.2 | 60.4 | 30 | 20.6 | 6.7 | 60 | |
2026.05 | 80.9 | 44.4 | 25 | 10.5 | 6.7 | 53.5 | |
2026.05 | 79.9 | 58.6 | 30 | 18.1 | 6.7 | 57.8 | |
2026.05 | 79.7 | 43.4 | 25 | 10.5 | 6.7 | 52.7 | |
2026.05 | 79 | 46 | 15 | 9.78 | 10 | 52.5 | |
2026.05 | 78.7 | 51.6 | 25 | 12.3 | 3.3 | 54.2 | |
2026.05 | 77.4 | 48.8 | 20 | 12.7 | 6.7 | 53.1 | |
2026.05 | 77.3 | 40.6 | 17.5 | 9.2 | 3.3 | 50.4 | |
2026.05 | 77 | 46.6 | 20 | 11.6 | 3.3 | 52.1 | |
2026.05 | 72.3 | 36.2 | 10 | 9.5 | 0 | 43.3 | |
2026.05 | 70.8 | 50 | 27.5 | 12.4 | 3.3 | 46.9 | |
2026.05 | 68.9 | 45.2 | 20 | 11.6 | 3.3 | 44.6 | |
2026.05 | 65.1 | 41.4 | 32.5 | 10.8 | 0 | 42 | |
2026.05 | 63.1 | 40 | 30 | 11.6 | 0 | 41 | |
2026.05 | 49.2 | 33.4 | 7.5 | 7.4 | 0 | 31.7 | |
2026.05 | 44.8 | 15.6 | 2.5 | 4.1 | 0 | 24.7 | |
2026.05 | 44.3 | 14.2 | 0 | 2.8 | 0 | 23.7 | |
2026.05 | 43.1 | 18.4 | 2.5 | 2.2 | 3.3 | 24 | |
2026.05 | 42.4 | 32.6 | 30 | 9.3 | 3.3 | 29.5 | |
2026.05 | 42.3 | 28.6 | 2.5 | 5.5 | 0 | 26.9 | |
| 31.3 | 19.6 | 20 | 5.3 | 3.3 | 21.7 | ||
| 20 | 32.8 | 30 | 9.8 | 6.7 | 19.8 | ||
2026.05 | 3.9 | 1 | 2.5 | 2.1 | 3.3 | 2.7 |