Hallucination Evaluation on POPE Popular v1.0 (test)
90.34AccuracyResDec
Evaluation results
| Method | Links | ||
|---|---|---|---|
| ResDecModel=Qwen2.5-VL2026.02 | 90.34 | 89.83 | |
| ONLYModel=Qwen2.5-VL2026.02 | 89.23 | 88.21 | |
| OPERAModel=Qwen2.5-VL2026.02 | 88.89 | 87.05 | |
| VISTAModel=Qwen2.5-VL2026.02 | 87.92 | 88.95 | |
| VCDModel=Qwen2.5-VL2026.02 | 87.84 | 85.78 | |
| ICDModel=Qwen2.5-VL2026.02 | 87.84 | 85.78 | |
| DoLaModel=Qwen2.5-VL2026.02 | 87.01 | 85.28 | |
| ResDecModel=LLaVA-1.52026.02 | 86.97 | 87.22 | |
| MemVRModel=LLaVA-1.52026.02 | 86.35 | 86.14 | |
| RegularModel=Qwen2.5-VL2026.02 | 86.03 | 84.56 | |
| VISTAModel=LLaVA-1.52026.02 | 85.97 | 85.87 | |
| OA-VCDModel=LLaVA-v1.5 (7B)2026.02 | 85.7 | 85.1 | |
| AGLAModel=LLaVA-1.52026.02 | 85.14 | 84.68 | |
| AGLAModel=LLaVA-v1.5 (7B)2026.02 | 85.1 | 84.6 | |
| OPERAModel=LLaVA-1.52026.02 | 84.21 | 83.5 | |
| VCDModel=LLaVA-v1.5 (7B)2026.02 | 83 | 82.9 | |
| VCDModel=LLaVA-1.52026.02 | 82.65 | 83.37 | |
| ResDecModel=InstructBLIP2026.02 | 82.01 | 83.42 | |
| AGLAModel=InstructBLIP2026.02 | 81.86 | 82.58 | |
| VISTAModel=InstructBLIP2026.02 | 81.34 | 80.94 | |
| ICDModel=LLaVA-1.52026.02 | 81.08 | 80.74 | |
| RegularModel=LLaVA-v1.5 (7B)2026.02 | 80.8 | 79.9 | |
| ONLYModel=InstructBLIP2026.02 | 80.43 | 82.07 | |
| RegularModel=LLaVA-1.52026.02 | 79.98 | 79.34 | |
| VCDModel=InstructBLIP2026.02 | 79.94 | 80.8 | |
| DoLaModel=LLaVA-1.52026.02 | 79.75 | 80.61 | |
| ONLYModel=LLaVA-1.52026.02 | 79.68 | 82.27 | |
| DoLaModel=InstructBLIP2026.02 | 78.99 | 79.85 | |
| OPERAModel=InstructBLIP2026.02 | 78.33 | 80.2 | |
| ICDModel=InstructBLIP2026.02 | 78.13 | 79.12 | |
| RegularModel=InstructBLIP2026.02 | 76.09 | 77.65 |