| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Geometry3K | MARS-GPS | Accuracy88.8 | 41 | 1mo ago | |
| Geo3K | Draw2Think BL | Top-1 Accuracy98.2 | 41 | 13d ago | |
| MathVista GPS | DreamPRM (o4-mini) | Accuracy95.7 | 38 | 3mo ago | |
| Geometry3K (test) | Human Expert | Choice Accuracy90.9 | 32 | 3mo ago | |
| GeoQA | Top-1 Acc92.04 | 26 | 3mo ago | ||
| PGPS9K (test) | AutoGPS | Completion75.3 | 18 | 3mo ago | |
| OlympiadBench | GeometryZero-7B | BoN@3 Accuracy45.69 | 17 | 1mo ago | |
| Geomverse | GeometryZero-7B | BoN@3 Accuracy18.23 | 17 | 1mo ago | |
| MathVista | GeometryZero-7B | BoN@3 Accuracy87.15 | 17 | 1mo ago | |
| Formalgeo7k | GeoFocus-7B | Top-1 Accuracy63.5 | 17 | 3mo ago | |
| GeoQA (test) | Human | Choice Accuracy92.3 | 13 | 3mo ago | |
| OlympiadBench | Accuracy75.5 | 12 | 1mo ago | ||
| Geometry3K 1.0 (test) | Overall Score90.9 | 12 | 3mo ago | ||
| UniGeo calculation (test) | Draw2Think CT | Top-1 Accuracy96.9 | 11 | 13d ago | |
| IMP-Geometry3K | Accuracy76 | 10 | 3mo ago | ||
| G-MATH | BBA | Accuracy34.22 | 8 | 3mo ago | |
| Geometry | DAPO | Average Score50.6 | 6 | 1d ago | |
| PGPS9K N=1000 | Draw2Think BL | Top-1 Accuracy94.5 | 6 | 13d ago | |
| UniGeo Prv (test) | GOLD | Accuracy98.5 | 6 | 3mo ago | |
| UniGeo CAL (test) | GOLD | Accuracy75.2 | 6 | 3mo ago | |
| GEOS | Inter-GPS | Accuracy67 | 5 | 3mo ago | |
| GeoCode mini (test) | Accuracy42.16 | 3 | 3mo ago | ||
| IMO 50 2000-2024 (test) | - | - | 0 | 3mo ago |