| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Mathematical Reasoning | GSM-Symbolic | GSM-Sym Accuracy82.1 | 73 | |
| Mathematical Reasoning | GSM-Symbolic Origin 100 | Accuracy96 | 36 | |
| Mathematical Reasoning | GSM-Symbolic Vary Both | Accuracy90.22 | 36 | |
| Mathematical Reasoning | GSM-Symbolic Vary Name | Accuracy92.48 | 36 | |
| Mathematical Reasoning | GSM-Symbolic Vary Num. | Accuracy90.66 | 36 | |
| Mathematical Reasoning | GSM-Symbolic (test) | Accuracy88.1 | 24 | |
| Mathematical Reasoning | GSM-Symbolic | Accuracy (Vary Both)90.2 | 14 | |
| Mathematical Reasoning | GSM-Symbolic | Accuracy85.6 | 7 | |
| Mathematical expression synthesis | GSM-Symbolic (test) | Accuracy (%)66 | 4 |