Mathematical Reasoning on MATH (test) (Pass@1, RGR)
83.8Pass@1W2SR-P
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| W2SR-PStudent=Qwen2.5 32B, Teacher=Qwen2.5-14B (R), Training=Weak-to-Strong with Preference2025.05 | 83.8 | 200 | |
| W2SRStudent=Qwen2.5 32B, Teacher=Qwen2.5-14B (R), Training=Weak-to-Strong2025.05 | 83.6 | 187.5 | |
| W2SR-PStudent=Qwen2.5 32B, Teacher=Qwen2.5-7B (R), Training=Weak-to-Strong with Preference2025.05 | 82.4 | 104.55 | |
| GRPOStudent=Qwen2.5 32B, Teacher=None, Training=Reinforcement Learning2025.05 | 82.2 | — | |
| W2SRStudent=Qwen2.5 32B, Teacher=Qwen2.5-7B (R), Training=Weak-to-Strong2025.05 | 81.6 | 86.36 | |
| W2SR-PStudent=Qwen2.5 14B, Teacher=Qwen2.5-7B (R), Training=Weak-to-Strong with Preference2025.05 | 80.8 | 107.14 | |
| GRPOStudent=Qwen2.5 14B, Teacher=None, Training=Reinforcement Learning2025.05 | 80.6 | — | |
| Qwen2.5-14B (R)Student=None, Teacher=Qwen2.5-14B (R), Training=Standalone Teacher2025.05 | 80.6 | — | |
| GRPOStudent=Qwen2.5 Math-7B, Teacher=None, Training=Reinforcement Learning2025.05 | 80.2 | — | |
| W2SRStudent=Qwen2.5 14B, Teacher=Qwen2.5-7B (R), Training=Weak-to-Strong2025.05 | 80 | 78.57 | |
| W2SR-PStudent=Qwen2.5 Math-7B, Teacher=Qwen2.5-1.5B (R), Training=Weak-to-Strong with Preference2025.05 | 79 | 94.34 | |
| Qwen2.5-7B (R)Student=None, Teacher=Qwen2.5-7B (R), Training=Standalone Teacher2025.05 | 77.8 | — | |
| W2SR-PStudent=Qwen2.5 14B, Teacher=Qwen2.5-1.5B (R), Training=Weak-to-Strong with Preference2025.05 | 76 | 78.7 | |
| W2SR-PStudent=Qwen2.5 32B, Teacher=Qwen2.5-1.5B (R), Training=Weak-to-Strong with Preference2025.05 | 76 | 73.28 | |
| LIMOStudent=Qwen2.5 14B, Teacher=None, Training=SFT2025.05 | 75.6 | — | |
| LIMOStudent=Qwen2.5 32B, Teacher=None, Training=SFT2025.05 | 75.4 | — | |
| W2SRStudent=Qwen2.5 Math-7B, Teacher=Qwen2.5-1.5B (R), Training=Weak-to-Strong2025.05 | 71.2 | 57.55 | |
| LIMOStudent=Qwen2.5 Math-7B, Teacher=None, Training=SFT2025.05 | 70.4 | — | |
| W2SRStudent=Qwen2.5 14B, Teacher=Qwen2.5-1.5B (R), Training=Weak-to-Strong2025.05 | 70.2 | 51.85 | |
| W2SRStudent=Qwen2.5 32B, Teacher=Qwen2.5-1.5B (R), Training=Weak-to-Strong2025.05 | 70.2 | 48.28 | |
| W2SR-PStudent=Qwen2.5 Math-7B, Teacher=Qwen2.5-0.5B (R), Training=Weak-to-Strong with Preference2025.05 | 69.2 | 77.08 | |
| VanillaStudent=Qwen2.5 14B, Teacher=None, Training=Zero-shot standalone2025.05 | 62.2 | — | |
| VanillaStudent=Qwen2.5 32B, Teacher=None, Training=Zero-shot standalone2025.05 | 60.4 | — | |
| VanillaStudent=Qwen2.5 Math-7B, Teacher=None, Training=Zero-shot standalone2025.05 | 60.2 | — | |
| Qwen2.5-1.5B (R)Student=None, Teacher=Qwen2.5-1.5B (R), Training=Standalone Teacher2025.05 | 59 | — | |
| W2SRStudent=Qwen2.5 Math-7B, Teacher=Qwen2.5-0.5B (R), Training=Weak-to-Strong2025.05 | 52 | 41.25 | |
| Qwen2.5-0.5B (R)Student=None, Teacher=Qwen2.5-0.5B (R), Training=Standalone Teacher2025.05 | 32.2 | — |