Hallucination Evaluation on VRIPT-HAL (test)
52.9F1 Score
SmartSight
Updated 3d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.12 | 52.9 | 43 | 69.7 | |
2025.12 | 51.3 | 40.3 | 71.8 | |
2025.12 | 50 | 38.5 | 73.8 | |
2025.12 | 49.7 | 38.1 | 72.9 | |
2025.12 | 49.3 | 37.6 | 72.9 | |
2025.12 | 49.2 | 37.8 | 71.3 | |
2025.12 | 48.7 | 36 | 75.4 | |
2025.12 | 47.9 | 35.6 | 75 | |
2025.12 | 47.3 | 35 | 75.9 | |
2025.12 | 45.8 | 33.4 | 76.2 | |
2025.12 | 36.8 | 26 | 67.6 | |
2025.12 | 35 | 24.3 | 66.6 | |
2025.12 | 34.3 | 23.2 | 69.2 | |
2025.12 | 33.3 | 22.5 | 68.7 | |
2025.12 | 32.9 | 22 | 69 |