Mathematical Reasoning on GSM8K (Accuracy, Attention Recall)
81Accuracy (GSM8K)
Full
Updated 25d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.06 | 81 | 100 | |
2026.06 | 77 | 88.8 | |
2026.06 | 77 | 60.5 | |
2026.06 | 70 | 81.3 |
Full
| Method | Links | ||
|---|---|---|---|
2026.06 | 81 | 100 | |
2026.06 | 77 | 88.8 | |
2026.06 | 77 | 60.5 | |
2026.06 | 70 | 81.3 |