Mathematical Reasoning and Coding on Polaris
48.79Peak Accuracy@8
balanced-agg
Updated 27d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.04 | 48.79 | 60.94 | 46.4 | 55.5 | |
2026.04 | 48.42 | 60.53 | 43.49 | 55.57 | |
2026.04 | 48.12 | 59.5 | 46.14 | 57.3 | |
2026.04 | 35.39 | 47.68 | 32.92 | 45.27 | |
2026.04 | 34.23 | 47.5 | 33.19 | 44.43 | |
2026.04 | 34.05 | 46.97 | 31.72 | 43.6 |