| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Data Analysis | DABStep hard | Accuracy37.04 | 13 | |
| Data Analysis | DABStep easy | Accuracy83.33 | 13 | |
| Data Analysis | DABStep 2025 (hard-level) | Accuracy45.24 | 12 | |
| Data Analysis | DABStep 2025 (easy-level) | Accuracy87.5 | 12 | |
| Multi-step Reasoning over Code Dependencies | DABstep hard | Accuracy24.34 | 6 |