Mathematical Reasoning on SVAMP (Pass@20)
0.9733Pass@20Entropy-Tree
Evaluation results
| Method | Links | |
|---|---|---|
| Entropy-TreeModel=Qwen2.5-14B-Instruct2026.01 | 0.9733 | |
| Multi-chainModel=Qwen2.5-14B-Instruct2026.01 | 0.97 | |
| Entropy-TreeModel=Qwen2.5-7B-Instruct2026.01 | 0.96 | |
| Multi-chainModel=Qwen2.5-32B-Instruct2026.01 | 0.96 | |
| Entropy-TreeModel=Qwen2.5-32B-Instruct2026.01 | 0.96 | |
| Multi-chainModel=Qwen2.5-7B-Instruct2026.01 | 0.9567 |