Benchmark
POPE
Polling-based Object Probing Evaluation (POPE) is a benchmark for evaluating object hallucination in Large Vision-Language Models (LVLMs). POPE addresses…
- Modality
- multimodal
- Categories
- multimodal, safety, vision
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 3
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| LFM2.5-VL-3B | Liquid AI | 0.887 | 2026-08-12 | evidence |
| Phi-3.5-vision-instruct | Microsoft | 0.861 | 2024-08-23 | evidence |
| Phi-4-multimodal-instruct | Microsoft | 0.856 | 2025-02-01 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.