Mathematical Reasoning on AIME 24 (Accuracy, Pass@4)
71.66AccuracyASLEC-CASL
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ASLEC-CASLBase Model=Qwen 4B-Instruct2026.04 | 71.66 | 90 | |
| ASLEC-DROPBase Model=Qwen 4B-Instruct2026.04 | 69.16 | 83.33 | |
| Local LPBase Model=Qwen 4B-Instruct2026.04 | 61.66 | 80 | |
| GRACEBase Model=Qwen 4B-Instruct2026.04 | 59.16 | 73.33 | |
| ASLEC-CASLBase Model=Qwen 8B-Base2026.04 | 45 | 66.66 | |
| ASLEC-DROPBase Model=Qwen 8B-Base2026.04 | 41.66 | 66.66 | |
| Local LPBase Model=Qwen 8B-Base2026.04 | 34.16 | 53.33 | |
| ASLEC-CASLBase Model=Qwen 4B-Base2026.04 | 31.66 | 53.33 | |
| GRACEBase Model=Qwen 8B-Base2026.04 | 30.83 | 53.33 | |
| ASLEC-DROPBase Model=Qwen 4B-Base2026.04 | 30 | 50 | |
| ASLEC-CASLBase Model=Qwen 7B-Instruct2026.04 | 28.33 | 46.66 | |
| ASLEC-DROPBase Model=Qwen 7B-Instruct2026.04 | 24.16 | 40 | |
| Local LPBase Model=Qwen 4B-Base2026.04 | 19.16 | 36.66 | |
| GRACEBase Model=Qwen 7B-Instruct2026.04 | 17.5 | 26.66 | |
| Local LPBase Model=Qwen 7B-Instruct2026.04 | 17.5 | 30 | |
| GRACEBase Model=Qwen 4B-Base2026.04 | 16.66 | 30 |