Multimodal Understanding on MM-Vet benign queries
54.5Recognition ScoreVLGuard
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| VLGuardModel=Qwen3-VL-8B2026.03 | 54.5 | 63.2 | 40.8 | 42.6 | 57.5 | 28.5 | 51.7 | 8.95 | |
| VSFAModel=Qwen3-VL-8B2026.03 | 53.2 | 62.8 | 39.5 | 41.2 | 59.5 | 27.2 | 51 | 2.62 | |
| VLGuardModel=Qwen2.5-VL-7B2026.03 | 50.2 | 60.8 | 37.1 | 39.5 | 56.3 | 25.8 | 48.6 | 10.82 | |
| VSFAModel=Qwen2.5-VL-7B2026.03 | 49.5 | 61.2 | 36.5 | 38.8 | 58.5 | 24.5 | 48.5 | 3.45 | |
| AdaShieldModel=Qwen3-VL-8B2026.03 | 46.2 | 60.5 | 28.8 | 33.5 | 57.9 | 14.2 | 44.8 | 24.82 | |
| AdaShieldModel=Qwen2.5-VL-7B2026.03 | 43.7 | 58.6 | 25.6 | 31.1 | 58.1 | 12.5 | 42.7 | 26.15 | |
| VSFAModel=LLaVA-v1.6-7B2026.03 | 40.2 | 29.5 | 18.8 | 20.8 | 31.5 | 18.5 | 29.9 | 2.35 | |
| VLGuardModel=LLaVA-v1.6-7B2026.03 | 39.5 | 30.2 | 20.2 | 21.5 | 30.8 | 17.2 | 30 | 13.28 | |
| VSFAModel=LLaVA-1.5-7B2026.03 | 35.5 | 19.2 | 15.2 | 18.2 | 24.8 | 14.2 | 24.3 | 1.82 | |
| VLGuardModel=LLaVA-1.5-7B2026.03 | 34.2 | 19.8 | 15.5 | 18.5 | 24.3 | 12.8 | 23.9 | 12.65 | |
| AdaShieldModel=LLaVA-v1.6-7B2026.03 | 33.2 | 19.5 | 15.5 | 21.8 | 27.5 | 9.8 | 24.2 | 30.85 | |
| AdaShieldModel=LLaVA-1.5-7B2026.03 | 29.9 | 13.5 | 12.9 | 19.8 | 22.7 | 8.2 | 20.5 | 29.36 |