| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Mathematical Reasoning | MATH-Vision | Accuracy30.4 | 32 | |
| Mathematical problem solving | MATH-Vision (test) | Accuracy68.8 | 26 | |
| Multimodal Reasoning | MATH-Vision (full) | Accuracy62.7 | 23 | |
| Mathematical Reasoning | MATH-Vision mini (test) | ALG42.11 | 8 | |
| Multimodal Mathematical Reasoning | MATH-Vision (testmini) | Alg Score21.05 | 8 |