| MMHal-Bench | VLI | MMHal Score4.32 | | 174 | 3d ago |
| CHAIR | M3ID | CHAIR_s72.8 | | 166 | 3d ago |
| POPE | MIRROR(ours) | Accuracy94.42 | | 132 | 2d ago |
| HallusionBench | | Average Score93.1 | | 93 | 2d ago |
| AMBER | OmniLMM + RLAIF-V | F1 Score90.9 | | 71 | 2d ago |
| CHAIR MSCOCO 2014 (val) | Dola | CHAIRi26.2 | | 39 | 3d ago |
| MSCOCO (val) | SparseVLM | CHAIR_i23.04 | | 36 | 3d ago |
| POPE Adversarial v1.0 (test) | ResDec | Accuracy88.96 | | 31 | 3d ago |
| POPE Popular v1.0 (test) | ResDec | Accuracy90.34 | | 31 | 3d ago |
| POPE Random v1.0 (test) | ResDec | Accuracy91.17 | | 31 | 3d ago |
| Object HalBench | baseline | CHAIR Score (s)52.7 | | 28 | 3d ago |
| MME hallucination (test) | VASparse | Existence Score180 | | 24 | 3d ago |
| CRPE relation | InternVL2.5-26B | Accuracy79.1 | | 23 | 2d ago |
| MOH | baseline | HR^D69.5 | | 21 | 3d ago |
| MMLU-Pro Law (test) | | HALL%12.1 | | 21 | 3d ago |
| HallB | SAIL | Score54.2 | | 19 | 3d ago |
| MME Hallucination | CoFi-Dec | Existence Score190.26 | | 18 | 3d ago |
| MMHal | | Score4 | | 18 | 2d ago |
| POPE MSCOCO, A-OKVQA, GQA average (Adversarial) | | Accuracy84.11 | | 15 | 3d ago |
| POPE Popular MSCOCO, A-OKVQA, GQA average | | Accuracy88.48 | | 15 | 3d ago |
| POPE MSCOCO, A-OKVQA, GQA average (Random) | | Accuracy93.24 | | 15 | 3d ago |
| EventHallusion binary QA (test) | SmartSight | Accuracy0.655 | | 15 | 3d ago |
| VRIPT-HAL (test) | SmartSight | F1 Score52.9 | | 15 | 3d ago |
| MCEval HaluEval 8K (test) | Act | Accuracy82.2 | | 14 | 3d ago |
| POPE COCO 2014 (Adversarial) | VEGAS | Accuracy81.43 | | 13 | 3d ago |