Mathematical Reasoning on SVAMP (pass@4 accuracy)
94.48pass@4 AccuracyPPCV
Evaluation Results
| Method | Links | |
|---|---|---|
| PPCVBackbone=Llama-3.1-8B-Instruct, k value=4, Number of samples per question=122026.02 | 94.48 | |
| Phi-DecodingBackbone=Llama-3.1-8B-Instruct, k value=4, Number of samples per question=122026.02 | 91.19 |