CapProbe Benchmark
Explore score history ↗CapProbe is a full-scene dense QA benchmark for evaluating detailed image captions from Vision-Language Models. It decomposes images into semantic regions and generates multiple-choice questions across 10 semantic categories, with a language judge answering from captions. The benchmark comprises 346 images, 1,868 regions, and 25,650 questions.
- Released
- 2026-08-11
- Institutions
- Huawei Technologies (China)
- Evaluates
- Factuality, General AI, Vision & 3D, cs.CV
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
CapProbe paper
No reported scores are on record for this benchmark yet.