Geometry Problem Solving on PyGeoX Medium
57AccuracyProprietary-A
Evaluation Results
| Method | Links | |
|---|---|---|
| Proprietary-AInference=default, Evaluation Protocol=zero-shot2026.06 | 57 | |
| Proprietary-BInference=reasoning, Evaluation Protocol=zero-shot2026.06 | 54 | |
| Qwen3-8B-RLInference=RL-trained, Evaluation Protocol=zero-shot2026.06 | 50 | |
| Proprietary-CInference=reasoning, Evaluation Protocol=zero-shot2026.06 | 49 | |
| DeepSeek-V3.2Inference=default, Evaluation Protocol=zero-shot2026.06 | 39 |