Mathematical Reasoning on MATH-500 (Acc, Len, Red.)
85.5Accuracy (MATH-500)OPSDC
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| OPSDCBase Model=Qwen3-14B, Token Budget=8,192 tokens2026.03 | 85.5 | 1,066 | 67.6 | |
| OPSDCBase Model=Qwen3-8B, Token Budget=8,192 tokens2026.03 | 85.1 | 1,199 | 68.9 | |
| Concise promptBase Model=Qwen3-14B, Token Budget=8,192 tokens2026.03 | 81.8 | 2,059 | 37.3 | |
| Concise promptBase Model=Qwen3-8B, Token Budget=8,192 tokens2026.03 | 78.1 | 2,514 | 34.9 | |
| Base ModelBase Model=Qwen3-8B, Token Budget=8,192 tokens2026.03 | 69.4 | 3,860 | — | |
| Base ModelBase Model=Qwen3-14B, Token Budget=8,192 tokens2026.03 | 64.3 | 3,285 | — |