Mathematical Reasoning on AIME 2025 (Exact Match)
43.3Exact Match AccuracyOPD
Evaluation Results
| Method | Links | |
|---|---|---|
| OPDTeacher-Student Setting=Qwen3-8B -> Llama3.1-8B-SFT2026.06 | 43.3 | |
| OPDTeacher-Student Setting=DeepSeek-R1 -> DeepSeek-R1-Distill-Qwen-7B2026.06 | 42.5 | |
| CDMTeacher-Student Setting=DeepSeek-R1 -> DeepSeek-R1-Distill-Qwen-7B2026.06 | 35.6 | |
| ALMTeacher-Student Setting=DeepSeek-R1 -> DeepSeek-R1-Distill-Qwen-7B2026.06 | 35 | |
| SFTTeacher-Student Setting=DeepSeek-R1 -> DeepSeek-R1-Distill-Qwen-7B2026.06 | 34.2 | |
| ALMTeacher-Student Setting=Qwen3-8B -> Llama3.1-8B-SFT2026.06 | 32.5 | |
| CDMTeacher-Student Setting=Qwen3-8B -> Llama3.1-8B-SFT2026.06 | 32.3 | |
| SFTTeacher-Student Setting=Qwen3-8B -> Llama3.1-8B-SFT2026.06 | 31.7 |