Benchmark
GroundingSuite Benchmark
What is GroundingSuite?
GroundingSuite is designed to test the localization capabilities of multimodal models. It created 3,720 pixel-level data entries based on COCO Unlabeled…
- Released
- 2025-07-05
- Modality
- multimodal
- Evaluates
- 多模态, Multimodal, 理解, Understanding, 多模态模型, VLM, 图像理解, Image Understanding, 不支持, Unsupported
- Openness
- open
- Importer
- OpenCompass Hub
- Reported scores
- 0
Source provenance
- Original evidence https://hub.opencompass.org.cn/dataset-detail/GroundingSuite
GroundingSuite paper, code and dataset
No reported scores are on record for this benchmark yet.