| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Quantity Tagging | Ape clean (test) | Accuracy91.5 | 4 | |
| Target Prediction | Ape clean (test) | MSE0.44 | 4 | |
| Operation Prediction | Ape-clean (test) | Accuracy87 | 4 | |
| Common Attribute Comparison | Ape-clean (test) | Accuracy87 | 4 | |
| Attribute Prediction | Ape clean (test) | Accuracy0.86 | 4 | |
| Number Type Grounding | Ape clean (test) | Accuracy92 | 4 | |
| Number Counting | Ape clean (test) | MSE0.67 | 4 |