| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Geometric Reasoning | Geometry3K | Accuracy@169.1 | 42 | |
| Geometry problem solving | Geometry3K | Accuracy88.8 | 36 | |
| Geometry Problem Solving | Geometry3K (test) | Choice Accuracy90.9 | 32 | |
| Mathematical Reasoning | Geometry3k | Accuracy79.9 | 26 | |
| Geometric Reasoning | Geometry3K (test) | Accuracy40.93 | 22 | |
| Geometry Reasoning | Geometry3K (val) | Accuracy28.12 | 12 | |
| Geometry Problem Solving | Geometry3K 1.0 (test) | Overall Score90.9 | 12 | |
| Geometric Reasoning | Geometry3K | Avg@8 Accuracy44.11 | 10 | |
| Geometry Problem Solving | IMP-Geometry3K | Accuracy76 | 10 | |
| Geometry reasoning | Geometry3k (test) | Test Score48.11 | 8 | |
| Geometry reasoning | Geometry3K | Geometry Score66.7 | 7 | |
| Geometric Reasoning | Geometry3K mid-school level | Accuracy81.03 | 6 | |
| Visual Reasoning | Geometry3K (test) | Pass@1 Accuracy56.18 | 5 | |
| Multi-step theorem prediction | Geometry3K | Accuracy95.16 | 3 | |
| Math | Geometry3K | Accuracy39 | 2 |