Math Reasoning on Math500 (Score)
45.4ScoreQwen3-4B + WeMask(SFT)
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-4B + WeMask(SFT)Mask Rate=0.3, Training Setting=SFT, Evaluation Protocol=0-shot2026.05 | 45.4 | |
| Qwen3-4B + WeMask(SFT)Mask Rate=0.1, Training Setting=SFT, Evaluation Protocol=0-shot2026.05 | 44.47 | |
| Qwen3-4B + SFT + WeMask(TF)Mask Rate=0.3, Training Setting=TF, Evaluation Protocol=0-shot2026.05 | 43.7 | |
| Qwen3-4B + SFT + WeMask(TF)Mask Rate=0.1, Training Setting=TF, Evaluation Protocol=0-shot2026.05 | 43.6 | |
| Qwen3-4B + SFT + WeMask(TF)Mask Rate=0.5, Training Setting=TF, Evaluation Protocol=0-shot2026.05 | 43.6 | |
| Qwen3-4B + SFTMask Rate=-, Training Setting=TF, Evaluation Protocol=0-shot2026.05 | 43 | |
| Qwen3-4B + WeMask(SFT)Mask Rate=0.7, Training Setting=SFT, Evaluation Protocol=0-shot2026.05 | 42.93 | |
| Qwen3-4B + SFT + WeMask(TF)Mask Rate=0.7, Training Setting=TF, Evaluation Protocol=0-shot2026.05 | 42.87 | |
| Qwen3-4B + WeMask(SFT)Mask Rate=1.0, Training Setting=SFT, Evaluation Protocol=0-shot2026.05 | 42.73 | |
| Qwen3-4B + WeMask(SFT)Mask Rate=0.5, Training Setting=SFT, Evaluation Protocol=0-shot2026.05 | 41.87 | |
| Qwen3-4B + SFT + WeMask(TF)Mask Rate=1.0, Training Setting=TF, Evaluation Protocol=0-shot2026.05 | 38.33 |