Tool-use Mathematical Reasoning on Math
22.71Overall ScoreMENTOR
Evaluation Results
| Method | Links | |
|---|---|---|
| MENTORModel=LLaMA-3.1-8B2025.10 | 22.71 | |
| Strict RLModel=LLaMA-3.1-8B2025.10 | 20.78 | |
| Outcome-based RLModel=LLaMA-3.1-8B2025.10 | 20.42 | |
| SFTModel=LLaMA-3.1-8B2025.10 | 18.06 | |
| VanillaModel=LLaMA-3.1-8B2025.10 | 15.84 | |
| MENTORModel=LLaMA-3.2-3B2025.10 | 11.27 | |
| Strict RLModel=LLaMA-3.2-3B2025.10 | 8.46 | |
| Outcome-based RLModel=LLaMA-3.2-3B2025.10 | 8.04 | |
| SFTModel=LLaMA-3.2-3B2025.10 | 5.62 | |
| VanillaModel=LLaMA-3.2-3B2025.10 | 2.85 |