Mathematical Reasoning on GSM8K (Accuracy Before/After Comparison)
88.1Accuracy (Before GSM8K)
Direct
Updated 8d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.05 | 88.1 | 88.1 | 0 | |
2026.05 | 87.6 | 90.2 | 2.7 | |
2026.05 | 87 | 87 | 0 | |
2026.05 | 75 | 88.1 | 13.1 |
Direct
| Method | Links | |||
|---|---|---|---|---|
2026.05 | 88.1 | 88.1 | 0 | |
2026.05 | 87.6 | 90.2 | 2.7 | |
2026.05 | 87 | 87 | 0 | |
2026.05 | 75 | 88.1 | 13.1 |