General Reasoning on Aggregate (AIME, MATH-500, GPQA-D, LCB)
52Average ScoreOPD
Evaluation Results
| Method | Links | |
|---|---|---|
| OPDTeacher-Student Setting=DeepSeek-R1 -> DeepSeek-R1-Distill-Qwen-7B2026.06 | 52 | |
| CDMTeacher-Student Setting=DeepSeek-R1 -> DeepSeek-R1-Distill-Qwen-7B2026.06 | 49.6 | |
| ALMTeacher-Student Setting=DeepSeek-R1 -> DeepSeek-R1-Distill-Qwen-7B2026.06 | 49.3 | |
| SFTTeacher-Student Setting=DeepSeek-R1 -> DeepSeek-R1-Distill-Qwen-7B2026.06 | 48.8 | |
| OPDTeacher-Student Setting=Qwen3-8B -> Llama3.1-8B-SFT2026.06 | 40.7 | |
| CDMTeacher-Student Setting=Qwen3-8B -> Llama3.1-8B-SFT2026.06 | 35.9 | |
| ALMTeacher-Student Setting=Qwen3-8B -> Llama3.1-8B-SFT2026.06 | 35.7 | |
| SFTTeacher-Student Setting=Qwen3-8B -> Llama3.1-8B-SFT2026.06 | 35.1 |