Mathematical Reasoning on GSM8K MATH-500 (test)
92.3Accuracy (GSM8K)
Qwen3
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.03 | 92.3 | 80.2 | 86.3 | |
2026.03 | 91 | 78.4 | 84.7 | |
2026.03 | 90.7 | 73.4 | 82.1 | |
2026.03 | 90.2 | 74.8 | 82.5 | |
2026.03 | 90.1 | 75.2 | 82.7 | |
2026.03 | 89.7 | 71.6 | 80.6 | |
2026.03 | 89.1 | 63.6 | 76.4 | |
2026.03 | 89.1 | 65.8 | 77.4 | |
2026.03 | 88.6 | 77.8 | 83.2 | |
2026.03 | 87.2 | 79.8 | 83.5 | |
2026.03 | 86.7 | 79.2 | 83 | |
2026.03 | 84.6 | 49.4 | 67 | |
2026.03 | 83.3 | 45.6 | 64.4 | |
2026.03 | 82.9 | 78 | 80.4 | |
2026.03 | 82.3 | 77.2 | 79.7 | |
2026.03 | 82.1 | 73 | 77.5 | |
2026.03 | 81.5 | 74.8 | 78.1 | |
2026.03 | 81.5 | 71.6 | 76.5 | |
2026.03 | 81.4 | 75.2 | 78.3 | |
2026.03 | 81 | 69.2 | 75.1 | |
2026.03 | 80.4 | 73.6 | 77 | |
2026.03 | 80.4 | 72.8 | 76.6 | |
2026.03 | 74.8 | 54.2 | 64.5 | |
2026.03 | 74.4 | 55.8 | 65.1 | |
2026.03 | 71.8 | 57.8 | 64.8 | |
2026.03 | 69.7 | 21.4 | 45.5 | |
2026.03 | 69.5 | 59.8 | 64.6 | |
2026.03 | 68.2 | 22.2 | 45.2 | |
2026.03 | 64 | 50.8 | 57.4 | |
2026.03 | 63.6 | 21.6 | 42.6 | |
2026.03 | 63.1 | 46.8 | 54.9 | |
2026.03 | 60.5 | 14.4 | 37.4 | |
2026.03 | 60.1 | 24.8 | 42.4 | |
2026.03 | 59.6 | 20.8 | 40.2 | |
2026.03 | 59.6 | 20 | 39.8 | |
2026.03 | 59.2 | 12.8 | 36 | |
2026.03 | 59.1 | 22 | 40.5 | |
2026.03 | 58.5 | 19 | 38.7 | |
2026.03 | 57.7 | 20.4 | 39 | |
2026.03 | 57.6 | 23.2 | 40.4 | |
2026.03 | 55.5 | 41.8 | 48.7 | |
2026.03 | 55 | 22 | 38.5 | |
2026.03 | 52.2 | 27.2 | 39.7 |