Math Reasoning on AIME 2024 (avg@32, pass@32)
41.35Average 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 | 41.35 | 76.67 | |
| ExOPDSetting=Strong-to-weak, Teacher=Qwen3-4B-Non-Thinking-RL-Math, Student=Qwen3-1.7B, Training steps=5002026.06 | 40.83 | 70 | |
| OPDSetting=Strong-to-weak, Teacher=Qwen3-4B-Non-Thinking-RL-Math, Student=Qwen3-1.7B, Training steps=5002026.06 | 38.96 | 70 | |
| GKDSetting=Strong-to-weak, Teacher=Qwen3-4B-Non-Thinking-RL-Math, Student=Qwen3-1.7B, Training steps=5002026.06 | 37.71 | 66.67 | |
| SeqKDSetting=Strong-to-weak, Teacher=Qwen3-4B-Non-Thinking-RL-Math, Student=Qwen3-1.7B, Training steps=5002026.06 | 31.88 | 50 | |
| SFTSetting=Strong-to-weak, Teacher=Qwen3-4B-Non-Thinking-RL-Math, Student=Qwen3-1.7B, Training steps=5002026.06 | 30.93 | 48.33 |