Reasoning and Math Problem Solving on BoolQ, COPA, WinoGrande, SVAMP, MAWPS (test)
88.2BoolQ Accuracy
AUSteer-FFN
Updated 4d ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2026.02 | 88.2 | 90.8 | 67.25 | 71.67 | 89.58 | 81.5 | |
2026.02 | 87.83 | 91.2 | 64.01 | 71.67 | 88.45 | 80.63 | |
2026.02 | 87.71 | 95.4 | 65.35 | 76.33 | 91.27 | 83.21 | |
2026.02 | 87.65 | 93.2 | 64.25 | 73 | 85.92 | 80.8 | |
2026.02 | 87.43 | 89 | 63.61 | 68.67 | 84.51 | 78.64 | |
2026.02 | 87.4 | 90.8 | 65.59 | 69.67 | 87.32 | 80.16 | |
2026.02 | 87.25 | 97.6 | 70.88 | 70 | 94.08 | 83.96 | |
2026.02 | 87.03 | 91.6 | 69.61 | 68.67 | 92.39 | 81.86 | |
2026.02 | 86.85 | 89.4 | 68.35 | 68 | 92.96 | 81.11 | |
2026.02 | 86.82 | 88.4 | 68.11 | 69 | 93.52 | 81.17 | |
2026.02 | 86.79 | 92.4 | 69.53 | 68 | 93.52 | 82.05 | |
2026.02 | 86.79 | 91 | 70.72 | 71 | 94.65 | 82.83 | |
2026.02 | 86.64 | 77.4 | 67.25 | 67.67 | 92.11 | 78.21 | |
2026.02 | 76.27 | 75.4 | 52.8 | 37.67 | 56.06 | 59.64 | |
2026.02 | 75.57 | 82.8 | 53.28 | 37 | 58.03 | 61.34 | |
2026.02 | 74.98 | 75.2 | 52.64 | 34.33 | 55.21 | 58.47 | |
2026.02 | 74.35 | 78.8 | 53.04 | 36.33 | 54.93 | 59.49 | |
2026.02 | 74.1 | 77.2 | 52.8 | 36.67 | 54.08 | 58.97 | |
2026.02 | 70.52 | 70.8 | 50.91 | 36 | 51.83 | 56.01 |