| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Mathematical Reasoning | GeoQA (test) | Accuracy75.07 | 31 | |
| Geometry problem solving | GeoQA | Top-1 Acc92.04 | 26 | |
| Geometry Problem Solving | GeoQA (test) | Choice Accuracy92.3 | 13 | |
| Multimodal Reasoning | GeoQA | Mean@149.2 | 11 | |
| Multimodal Numerical Reasoning | GeoQA (test) | Total Accuracy92.3 | 11 | |
| Multimodal Mathematical Reasoning | GEOQA-8k (test) | Accuracy59.95 | 8 |