Math Reasoning on AIME 2025 (avg@32 and pass@32)
38.44Avg Score @32SG-OPD
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SG-OPDSetting=Strong-to-weak, Teacher=Qwen3-4B-Non-Thinking-RL-Math, Student=Qwen3-1.7B, Training steps=5002026.06 | 38.44 | 66.67 | |
| OPDSetting=Strong-to-weak, Teacher=Qwen3-4B-Non-Thinking-RL-Math, Student=Qwen3-1.7B, Training steps=5002026.06 | 33.44 | 50 | |
| ExOPDSetting=Strong-to-weak, Teacher=Qwen3-4B-Non-Thinking-RL-Math, Student=Qwen3-1.7B, Training steps=5002026.06 | 33.12 | 53.33 | |
| GKDSetting=Strong-to-weak, Teacher=Qwen3-4B-Non-Thinking-RL-Math, Student=Qwen3-1.7B, Training steps=5002026.06 | 32.19 | 50 | |
| SeqKDSetting=Strong-to-weak, Teacher=Qwen3-4B-Non-Thinking-RL-Math, Student=Qwen3-1.7B, Training steps=5002026.06 | 26.46 | 36.67 | |
| SFTSetting=Strong-to-weak, Teacher=Qwen3-4B-Non-Thinking-RL-Math, Student=Qwen3-1.7B, Training steps=5002026.06 | 25.62 | 33.67 |