Mathematical Reasoning on GSM8K (Accuracy, Performance Gain)
96.81Accuracy
l2-guided Selection
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.06 | 96.81 | 0.38 | |
2026.06 | 96.44 | - | |
2026.06 | 96.36 | 0.24 | |
2026.06 | 96.2 | 0.83 | |
2026.06 | 96.13 | - | |
2026.06 | 96.06 | 0.16 | |
2026.06 | 95.91 | - | |
2026.06 | 95.41 | - | |
2026.06 | 95.14 | 0.88 | |
2026.06 | 94.31 | - | |
2026.06 | 91.21 | 1.31 | |
2026.06 | 90.82 | 2.81 | |
2026.06 | 90.03 | - | |
2026.06 | 88.34 | - |