Hallucination Evaluation on POPE Random v1.0 (test)
91.17AccuracyResDec
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ResDecModel=Qwen2.5-VL2026.02 | 91.17 | 91.62 | |
| ONLYModel=Qwen2.5-VL2026.02 | 90.94 | 90.62 | |
| VISTAModel=Qwen2.5-VL2026.02 | 90.53 | 90.77 | |
| ResDecModel=LLaVA-1.52026.02 | 90.21 | 89.87 | |
| OPERAModel=Qwen2.5-VL2026.02 | 89.97 | 90.32 | |
| MemVRModel=LLaVA-1.52026.02 | 89.73 | 89.16 | |
| VISTAModel=LLaVA-1.52026.02 | 89.64 | 89.03 | |
| OA-VCDModel=LLaVA-v1.5 (7B)2026.02 | 89.5 | 88.5 | |
| VCDModel=Qwen2.5-VL2026.02 | 88.67 | 88.21 | |
| ICDModel=Qwen2.5-VL2026.02 | 88.67 | 88.21 | |
| AGLAModel=LLaVA-1.52026.02 | 88.54 | 87.71 | |
| ResDecModel=InstructBLIP2026.02 | 88.32 | 89.11 | |
| AGLAModel=LLaVA-v1.5 (7B)2026.02 | 88 | 86.9 | |
| DoLaModel=Qwen2.5-VL2026.02 | 87.98 | 87.71 | |
| VCDModel=LLaVA-v1.5 (7B)2026.02 | 87.6 | 86.5 | |
| OPERAModel=LLaVA-1.52026.02 | 87.53 | 86.45 | |
| ONLYModel=LLaVA-1.52026.02 | 87.49 | 88.02 | |
| VISTAModel=InstructBLIP2026.02 | 87.45 | 87.66 | |
| RegularModel=Qwen2.5-VL2026.02 | 87.39 | 86.31 | |
| AGLAModel=InstructBLIP2026.02 | 87.3 | 87.07 | |
| ONLYModel=InstructBLIP2026.02 | 87.18 | 88.15 | |
| VCDModel=LLaVA-1.52026.02 | 86.84 | 86.83 | |
| ICDModel=LLaVA-1.52026.02 | 85.11 | 84.18 | |
| OPERAModel=InstructBLIP2026.02 | 85.07 | 84.39 | |
| DoLaModel=LLaVA-1.52026.02 | 84.78 | 84.19 | |
| RegularModel=LLaVA-v1.5 (7B)2026.02 | 84.7 | 83.2 | |
| VCDModel=InstructBLIP2026.02 | 84.11 | 84.13 | |
| RegularModel=LLaVA-1.52026.02 | 83.49 | 82.28 | |
| DoLaModel=InstructBLIP2026.02 | 83 | 83 | |
| ICDModel=InstructBLIP2026.02 | 82.37 | 83.32 | |
| RegularModel=InstructBLIP2026.02 | 80.42 | 80.94 |