Mathematical Reasoning on GSM8K original and paraphrased (train)
33.4S_ref
Qwen-Math
Updated 12d ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2026.05 | 33.4 | 45.8 | - | - | - | 1 | |
2026.05 | 33.4 | 42 | - | - | - | 0.996 | |
2026.05 | 33.2 | - | 45.8 | - | - | 1 | |
2026.05 | 33.2 | - | 41.8 | - | - | 0.997 | |
2026.05 | 22.2 | 29.8 | - | - | - | 0.989 | |
2026.05 | 22.2 | 27.6 | - | - | - | 0.951 | |
2026.05 | 21.6 | - | 30 | - | - | 0.997 | |
2026.05 | 21.6 | - | 26.6 | - | - | 0.92 | |
2026.05 | 0.488 | - | - | 0.532 | - | 0.962 | |
2026.05 | 0.488 | - | - | 0.532 | - | 0.94 | |
2026.05 | 0.412 | - | - | - | 0.511 | 0.998 | |
2026.05 | 0.412 | - | - | - | 0.498 | 0.998 | |
2026.05 | 0.38 | - | - | 0.463 | - | 0.998 | |
2026.05 | 0.38 | - | - | 0.459 | - | 0.998 | |
2026.05 | 0.285 | - | - | - | 0.395 | 0.998 | |
2026.05 | 0.285 | - | - | - | 0.381 | 0.998 |