Knowledge gap detection on GSM8K
83.6Accuracy
GRADEpos
Updated 13d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.04 | 83.6 | 89.3 | |
2026.04 | 77.6 | 82.1 | |
2026.04 | 74.5 | 78.3 | |
2026.04 | 73.9 | 79.4 | |
2026.04 | 72.7 | 77.6 | |
2026.04 | 71.9 | 77.2 | |
2026.04 | 71.4 | 76.7 | |
2026.04 | 69.9 | 82.8 | |
2026.04 | 69.2 | 76.6 | |
2026.04 | 64.5 | 66.9 | |
2026.04 | 64.3 | 49.6 | |
2026.04 | 63.9 | - | |
2026.04 | 62.7 | 54.1 | |
2026.04 | 60.3 | 63.7 | |
2026.04 | 51.8 | 63.9 | |
2026.04 | 51.3 | - | |
2026.04 | 50.7 | 54.1 | |
2026.04 | 47.1 | - |