Suitability violation and drift analysis on Extended cross-model comparison evaluation dataset
92.6SVRs
Claude Sonnet 4.6
Updated 4mo ago
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
2026.03 | 92.6 | 64.8 | 1.652 | 38.4 | 0.893 | 17 | 1 | |
2026.03 | 90 | 59.1 | 1.596 | 40.4 | 0.922 | 14.2 | 1.095 | |
2026.03 | 88.3 | 60.4 | 1.574 | 40.2 | 0.845 | 16.1 | 1.046 | |
2026.03 | 87.4 | 55.2 | 1.609 | 39.9 | 0.885 | 22.6 | 1.249 | |
2026.03 | 80 | 49.6 | 1.491 | 30.1 | 0.743 | 11.6 | 1.115 | |
2026.03 | 67.8 | 39.1 | 1.057 | 67 | 1.197 | 45.7 | 0.988 | |
2026.03 | 64.8 | 34.3 | 1.122 | 26.7 | 1.781 | 27.1 | 1.029 |