Benchmark
Hallusion Bench
vision
reasoning
multimodal
A comprehensive benchmark designed to evaluate image-context reasoning in large visual-language models (LVLMs) by challenging models with 346 images and 1,129 carefully crafted questions to assess language hallucination and visual illusion
语言EN
满分1
参评模型2
模型排名
| 名次 | 模型 | 机构 | 分数 | 来源 |
|---|---|---|---|---|
| 1 | Qwen2.5 VL 72B Instruct | Alibaba Cloud / Qwen Team | 55.2 | 来源 ↗ |
| 2 | Qwen2.5 VL 7B Instruct | Alibaba Cloud / Qwen Team | 52.9 | 来源 ↗ |