Geometry Problem Solving on PyGeoX Easy
62AccuracyQwen3-8B-RL
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-8B-RLInference=RL-trained, Evaluation Protocol=zero-shot2026.06 | 62 | |
| Proprietary-CInference=reasoning, Evaluation Protocol=zero-shot2026.06 | 61 | |
| Proprietary-BInference=reasoning, Evaluation Protocol=zero-shot2026.06 | 55 | |
| Proprietary-AInference=default, Evaluation Protocol=zero-shot2026.06 | 53 | |
| DeepSeek-V3.2Inference=default, Evaluation Protocol=zero-shot2026.06 | 52 |