Mathematical Reasoning on GSM8K (Knowledge Recall, Skill Accuracy)
78Knowledge Recall
CorDA
Updated 8d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 78 | 41.24 | |
2026.05 | 69.6 | 35.37 | |
2026.05 | 66.8 | 41.4 | |
2026.05 | 66.4 | 25.02 | |
2026.05 | 65.6 | 46.17 | |
2026.05 | 65.6 | 46.93 | |
2026.05 | 65.2 | 23.96 | |
2026.05 | 64.5 | 44.58 | |
2026.05 | 63.9 | 39.27 | |
2026.05 | 63 | 39.12 | |
2026.05 | 63 | 41.7 | |
2026.05 | 63 | 46.4 | |
2026.05 | 60 | 42.99 | |
2026.05 | 56.8 | 42.38 | |
2026.05 | 52.7 | 40.11 | |
2026.05 | 52 | 42 |