Mathematical Reasoning on GSM8K full (test) (Accuracy, Avg.)
79.8Accuracy
SAE (Global)
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.02 | 79.8 | 48.4 | |
2026.02 | 78.01 | 47.2 | |
2026.02 | 77.48 | 47.8 | |
2026.02 | 74.2 | 46.4 | |
2026.02 | 74.1 | 46.4 | |
2026.02 | 13.7 | 15.7 |
SAE (Global)
| Method | Links | ||
|---|---|---|---|
2026.02 | 79.8 | 48.4 | |
2026.02 | 78.01 | 47.2 | |
2026.02 | 77.48 | 47.8 | |
2026.02 | 74.2 | 46.4 | |
2026.02 | 74.1 | 46.4 | |
2026.02 | 13.7 | 15.7 |