Math Reasoning on AIME 22-24
8.15ScoreQwen3-4B + WeMask(SFT)
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen3-4B + WeMask(SFT)Mask Rate=0.3, Training Setting=SFT, Evaluation Protocol=0-shot2026.05 | 8.15 | |
| Qwen3-4B + SFT + WeMask(TF)Mask Rate=0.3, Training Setting=TF, Evaluation Protocol=0-shot2026.05 | 7.61 | |
| Qwen3-4B + SFT + WeMask(TF)Mask Rate=0.7, Training Setting=TF, Evaluation Protocol=0-shot2026.05 | 7.41 | |
| Qwen3-4B + WeMask(SFT)Mask Rate=0.5, Training Setting=SFT, Evaluation Protocol=0-shot2026.05 | 6.67 | |
| Qwen3-4B + SFT + WeMask(TF)Mask Rate=0.1, Training Setting=TF, Evaluation Protocol=0-shot2026.05 | 6.3 | |
| Qwen3-4B + SFT + WeMask(TF)Mask Rate=0.5, Training Setting=TF, Evaluation Protocol=0-shot2026.05 | 5.93 | |
| Qwen3-4B + SFTMask Rate=-, Training Setting=TF, Evaluation Protocol=0-shot2026.05 | 5.92 | |
| Qwen3-4B + WeMask(SFT)Mask Rate=0.7, Training Setting=SFT, Evaluation Protocol=0-shot2026.05 | 5.92 | |
| Qwen3-4B + WeMask(SFT)Mask Rate=0.1, Training Setting=SFT, Evaluation Protocol=0-shot2026.05 | 4.07 | |
| Qwen3-4B + SFT + WeMask(TF)Mask Rate=1.0, Training Setting=TF, Evaluation Protocol=0-shot2026.05 | 3.33 | |
| Qwen3-4B + WeMask(SFT)Mask Rate=1.0, Training Setting=SFT, Evaluation Protocol=0-shot2026.05 | 1.48 |