| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Mathematical Reasoning | Numina | Accuracy45.5 | 36 | |
| Mathematical Reasoning | Numina | Accuracy (Numina)48.1 | 12 | |
| Response Similarity Evaluation | NUMINA | C-Score1.848 | 9 | |
| Mathematical Reasoning | Numina (test) | Pass@853.1 | 6 | |
| Mathematical reasoning | Numina (val) | Pass@842.41 | 6 |