Response Harmfulness Classification on WildGuard (test)
79.48F1 (Total)
GuardReasoner-VL 7B
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.02 | 79.48 | - | - | |
2026.02 | 78.83 | - | - | |
2026.02 | 78.2 | - | - | |
2026.02 | 78.06 | - | - | |
2026.02 | 77.89 | - | - | |
2026.02 | 77.57 | - | - | |
2024.06 | 77.3 | 73.6 | 81.3 | |
2024.06 | 76.8 | 67.7 | 85 | |
2026.02 | 76.8 | - | - | |
2026.02 | 76.4 | - | - | |
2026.02 | 76.12 | - | - | |
2024.06 | 75.4 | 68.4 | 81.5 | |
2026.02 | 75.4 | - | - | |
2026.02 | 70.8 | - | - | |
2024.06 | 66.5 | 47.9 | 78.2 | |
2026.02 | 66.39 | - | - | |
2024.06 | 63.4 | 51.2 | 74.3 | |
2026.02 | 63.4 | - | - | |
2024.06 | 63.2 | 61.7 | 64.2 | |
2024.06 | 60.1 | 51.8 | 70.3 | |
2026.02 | 60.1 | - | - | |
2024.06 | 56.4 | 49 | 62.4 | |
2026.02 | 56.4 | - | - | |
2024.06 | 50.5 | 25.8 | 66.7 | |
2024.06 | 49.1 | 40.4 | 57.6 | |
2026.02 | 49.1 | - | - | |
2026.02 | 47 | - | - | |
2024.06 | 45.7 | 41.9 | 50.2 | |
2026.02 | 45.7 | - | - | |
2024.06 | 16.9 | 14.7 | 18.8 |