| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Mathematical Reasoning | GSM-Plus | Acc (Original)93.4 | 28 | |
| Mathematical Reasoning | GSM-Plus (test) | Accuracy68.8 | 20 | |
| Mathematical Reasoning | GSM-Plus (mini) | Accuracy52.8 | 8 | |
| Math Word Problem Solving | GSM+ v1 (test) | Accuracy65.7 | 6 |