| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Error Correction | MathChat-EC (test) | Accuracy84.7 | 10 | |
| Follow-up Question Answering | MathChat-FQA 1st turn | Accuracy83.4 | 10 | |
| Mathematical dialogue | MathChat | Normalized Score77.87 | 5 | |
| Dialogue-based Mathematical Problem Solving | MathChat | R189.7 | 2 |