| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| POPE | MIRROR | Accuracy94.42 | 2,056 | 25d ago | |
| POPE | SPOT-E | Accuracy92 | 259 | 25d ago | |
| MS-COCO (POPE Adversarial) | SIRA | Accuracy87.83 | 205 | 25d ago | |
| POPE Adversarial | SFT + VIGIL | Accuracy89.8 | 174 | 22d ago | |
| CHAIR | CHAIRi Score57 | 174 | 25d ago | ||
| MS-COCO POPE (Popular) | AVISC | Accuracy90.76 | 158 | 1mo ago | |
| POPE Random | R-CoV | Accuracy94 | 152 | 29d ago | |
| POPE | CDPruner | Accuracy (POPE)87.6 | 137 | 16d ago | |
| POPE (test) | Accuracy90.6 | 123 | 1mo ago | ||
| MS-COCO POPE Random | AVISC | Accuracy92.36 | 121 | 1mo ago | |
| POPE MSCOCO | MHSA | F1 Score93.97 | 114 | 25d ago | |
| POPE (popular) | R-CoV | Accuracy92 | 100 | 22d ago | |
| A-OKVQA POPE (Popular) | SECOND | Accuracy90.3 | 91 | 25d ago | |
| POPE GQA | Accuracy91.03 | 86 | 25d ago | ||
| POPE Adversarial offline | F1 Score68.96 | 84 | 4mo ago | ||
| POPE Popular offline | OPERA | F1 Score84.43 | 84 | 4mo ago | |
| POPE Random offline | F1 Score73.6 | 84 | 4mo ago | ||
| POPE A-OKVQA | FADE | Accuracy91.2 | 83 | 25d ago | |
| MSCOCO 2014 (val) | VDD-None | CHAIRs56.8 | 81 | 1mo ago | |
| A-OKVQA POPE (Random) | SIRA | Accuracy92.1 | 75 | 25d ago | |
| MSCOCO POPE | DAC | Random Accuracy91.63 | 71 | 1mo ago | |
| POPE GQA Popular | SECOND | Accuracy89.4 | 70 | 1mo ago | |
| A-OKVQA POPE SEEM-annotated | Accuracy91.6 | 60 | 29d ago | ||
| MSCOCO POPE SEEM-annotated | DCLA | Accuracy91.07 | 60 | 29d ago | |
| POPE | MS-Resampler | Average Accuracy100.43 | 53 | 24d ago |