Mathematical Reasoning on OlympicBench (test)
50.07Pass@1W2SR-P
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| W2SR-PStudent=Qwen2.5 32B, Teacher=Qwen2.5-14B (R)2025.05 | 50.07 | 240.09 | |
| W2SRStudent=Qwen2.5 32B, Teacher=Qwen2.5-14B (R)2025.05 | 48 | 146.85 | |
| W2SRStudent=Qwen2.5 32B, Teacher=Qwen2.5-7B (R)2025.05 | 47.41 | 108.69 | |
| LIMOStudent=Qwen2.5 32B2025.05 | 47.11 | — | |
| GRPOStudent=Qwen2.5 32B2025.05 | 46.96 | — | |
| W2SR-PStudent=Qwen2.5 32B, Teacher=Qwen2.5-7B (R)2025.05 | 46.96 | 100 | |
| GRPOStudent=Qwen2.5 14B2025.05 | 44.74 | — | |
| Qwen2.5-14B (R)Role=Standalone Teacher2025.05 | 44.74 | — | |
| LIMOStudent=Qwen2.5 14B2025.05 | 43.85 | — | |
| W2SR-PStudent=Qwen2.5 14B, Teacher=Qwen2.5-7B (R)2025.05 | 43.56 | 60.14 | |
| GRPOStudent=Qwen2.5 Math-7B2025.05 | 42.37 | — | |
| W2SRStudent=Qwen2.5 14B, Teacher=Qwen2.5-7B (R)2025.05 | 42.07 | 9.8 | |
| Qwen2.5-7B (R)Role=Standalone Teacher2025.05 | 41.78 | — | |
| W2SR-PStudent=Qwen2.5 Math-7B, Teacher=Qwen2.5-1.5B (R)2025.05 | 39.26 | 85.62 | |
| W2SR-PStudent=Qwen2.5 32B, Teacher=Qwen2.5-1.5B (R)2025.05 | 37.19 | 62.74 | |
| W2SR-PStudent=Qwen2.5 14B, Teacher=Qwen2.5-1.5B (R)2025.05 | 36.15 | 64.21 | |
| W2SRStudent=Qwen2.5 Math-7B, Teacher=Qwen2.5-1.5B (R)2025.05 | 34.81 | 65.05 | |
| LIMOStudent=Qwen2.5 Math-7B2025.05 | 34.07 | — | |
| W2SRStudent=Qwen2.5 14B, Teacher=Qwen2.5-1.5B (R)2025.05 | 32.89 | 50.63 | |
| W2SRStudent=Qwen2.5 32B, Teacher=Qwen2.5-1.5B (R)2025.05 | 31.85 | 42.37 | |
| W2SR-PStudent=Qwen2.5 Math-7B, Teacher=Qwen2.5-0.5B (R)2025.05 | 29.33 | 59.99 | |
| VanillaStudent=Qwen2.5 32B2025.05 | 26.81 | — | |
| VanillaStudent=Qwen2.5 14B2025.05 | 25.78 | — | |
| VanillaStudent=Qwen2.5 Math-7B2025.05 | 25.63 | — | |
| Qwen2.5-1.5B (R)Role=Standalone Teacher2025.05 | 20.74 | — | |
| W2SRStudent=Qwen2.5 Math-7B, Teacher=Qwen2.5-0.5B (R)2025.05 | 16.3 | 20.01 | |
| Qwen2.5-0.5B (R)Role=Standalone Teacher2025.05 | 9.78 | — |