| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| HallusionBench | Accuracy76.6 | 120 | 2d ago | ||
| MSCOCO | M3ID | CHAIR_i18.2 | 104 | 3mo ago | |
| POPE MS-COCO Adversarial sampling (val) | RVCD | Accuracy85.48 | 39 | 3mo ago | |
| POPE (average) | CRG | F1 Score88.93 | 14 | 8d ago | |
| HallusionBench visual questions | GPT-4V | Accuracy65.8 | 10 | 3mo ago | |
| POPE MS-COCO Popular sampling (val) | InstructBLIP-14B | Accuracy82.77 | 6 | 3mo ago | |
| POPE MS-COCO Random sampling (val) | InstructBLIP-14B | Accuracy88.57 | 6 | 3mo ago |