Math Reasoning on MATH lighteval
98.4During-task Accuracy
Cloud LLM Cluster
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.01 | 98.4 | 98.4 | - | |
| 84.5 | 75.5 | 10.7 | ||
| 80.7 | 74.8 | 7.3 | ||
| 78.1 | 68.5 | 12.3 | ||
| 77.4 | 69.9 | 9.7 | ||
| 77.2 | 67.7 | 12.3 | ||
| 73.5 | 59.8 | 18.6 | ||
2026.01 | 73.1 | 61.3 | 16.1 | |
| 72.7 | 63.1 | 13.2 | ||
| 72.2 | 66.5 | 7.9 | ||
| 70.3 | 63.2 | 10.1 | ||
2026.01 | 70.3 | 63.1 | 10.2 | |
2026.01 | 68.3 | 60.6 | 11.3 | |
| 67.8 | 59.2 | 12.7 | ||
2026.01 | 64.7 | 52.5 | 18.9 | |
| 63.8 | 58.5 | 8.3 | ||
2026.01 | 62.2 | 55.4 | 10.9 | |
| 62 | 54.2 | 12.6 | ||
| 61.9 | 53.4 | 13.7 | ||
| 59 | 53.7 | 9 | ||
2026.01 | 58.7 | 49.6 | 15.5 | |
| 56 | 48.1 | 14.1 | ||
2026.01 | 55.3 | 44.4 | 19.7 | |
2026.01 | 55.3 | 44.4 | 19.7 | |
2026.01 | 55.2 | 44.5 | 19.4 | |
| 53.1 | 43.7 | 17.7 | ||
2026.01 | 51.6 | 33.2 | 35.7 | |
2026.01 | 51.6 | 33.2 | 35.7 | |
2026.01 | 50.3 | 32.8 | 34.8 |