Benchmark
UltraG-Bench
What is UltraG-Bench?
Evaluates vision-language models on pixel-level evidence grounding in ultrasound via segmentation, VQA, and report generation tasks.
- Released
- 2026-09-25
- Evaluates
- Biology & Drug Discovery, Multimodal
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
- Reported scores
- 0
Source provenance
- Original evidence https://arxiv.org/abs/2609.30928
UltraG-Bench paper and code
No reported scores are on record for this benchmark yet.