Mathematical Reasoning on MATH 4-shot (Acc, TPS, Steps, Spd(Lat.))
42.6Accuracy
Baseline
Updated 5d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.05 | 42.6 | 8.4 | 256 | 1 | |
2026.05 | 42.1 | 24.1 | 88 | 2.9 | |
2026.05 | 41.7 | 11.2 | 107 | 1.3 | |
2026.05 | 40 | 31.5 | 63 | 3.7 | |
2026.05 | 38.36 | 7.88 | - | 1 | |
2026.05 | 38.12 | 16.95 | - | 2.15 | |
2026.05 | 37.98 | 19.69 | - | 2.5 | |
2026.05 | 37.7 | 13.6 | 132 | 1.9 | |
2026.05 | 37.34 | 20.44 | - | 2.59 | |
2026.05 | 34.9 | 21.76 | - | 2.42 | |
2026.05 | 34.78 | 7.72 | - | 0.98 | |
2026.05 | 34.58 | 25.68 | - | 2.85 | |
2026.05 | 34.56 | 9.01 | - | 1 | |
2026.05 | 33.98 | 27.47 | - | 3.05 | |
2026.05 | 33.84 | 7.27 | - | 1 | |
2026.05 | 33.7 | 19.35 | - | 2.66 | |
2026.05 | 33.5 | 6.97 | - | 0.96 | |
2026.05 | 33.4 | 8.9 | 256 | 1 | |
2026.05 | 33.1 | 22.3 | 101 | 2.5 | |
2026.05 | 33.04 | 14.63 | - | 2.01 | |
2026.05 | 32.84 | 8.25 | - | 1 | |
2026.05 | 32.8 | 21.82 | - | 2.64 | |
2026.05 | 32.72 | 26.78 | - | 3.68 | |
2026.05 | 32.4 | 27.6 | 73 | 3.1 | |
2026.05 | 32.36 | 28.76 | - | 3.49 | |
2026.05 | 32.3 | 14.7 | 136 | 1.5 | |
2026.05 | 32.1 | 25.03 | - | 3.44 | |
2026.05 | 32 | 13.11 | - | 1.66 | |
2026.05 | 31.96 | 15.62 | - | 1.89 | |
2026.05 | 31.92 | 31.01 | - | 3.76 | |
2026.05 | 31.44 | 21.08 | - | 2.56 | |
2026.05 | 31.1 | 18.16 | - | 2.02 | |
2026.05 | 30.7 | 7.89 | - | 0.88 |