Benchmark
InfographicsQA
vision
multimodal
multimodal
InfographicVQA dataset with 5,485 infographic images and over 30,000 questions requiring joint reasoning over document layout, textual content, graphical elements, and data visualizations with elementary reasoning and arithmetic skills
语言EN
满分1
参评模型1
模型排名
| 名次 | 模型 | 机构 | 分数 | 来源 |
|---|---|---|---|---|
| 1 | Llama 3.2 90B Instruct | Meta | 56.8 | 来源 ↗ |