← Benchmarks
POPE
Polling-based Object Probing Evaluation (POPE) is a benchmark for evaluating object hallucination in Large Vision-Language Models (LVLMs). POPE addresses the problem where LVLMs generate objects inconsistent with target images by using a polling-based query method that asks yes/no questions about object presence in images, providing more stable and flexible evaluation of object hallucination.
id pope · max 1 · 3 models reported
| # | Model | Score |
|---|---|---|
| 1 | LFM2.5-VL-3B Liquid AI · open | 0.89 |
| 2 | Phi-3.5-vision-instruct Microsoft · open | 0.86 |
| 3 | Phi-4-multimodal-instruct Microsoft · open | 0.86 |