# MBZUAI benchmark tests spatial reasoning in 3D medical AI > MBZUAI’s CT-SpatialVQA benchmark tests how medical AI models identify spatial relationships in CT scans. - Canonical URL: https://newsverum.com/en/news/mbzuai-ct-spatialvqa-3d-medical-ai-benchmark-2026 - Publisher: Newsverum - Section: Technology - Country: United Arab Emirates - Published: 2026-10-20T14:20:10+00:00 - Updated: 2026-10-20T14:20:10+00:00 - Event / data period: 2026-10-19 - Other editions: [Türkçe](https://newsverum.com/tr/news/mbzuai-ct-spatialvqa-3d-medical-ai-benchmark-2026.md), [العربية](https://newsverum.com/ar/news/mbzuai-ct-spatialvqa-3d-medical-ai-benchmark-2026.md), [Français](https://newsverum.com/fr/news/mbzuai-ct-spatialvqa-3d-medical-ai-benchmark-2026.md), [Español](https://newsverum.com/es/news/mbzuai-ct-spatialvqa-3d-medical-ai-benchmark-2026.md), [Deutsch](https://newsverum.com/de/news/mbzuai-ct-spatialvqa-3d-medical-ai-benchmark-2026.md), [Português](https://newsverum.com/pt/news/mbzuai-ct-spatialvqa-3d-medical-ai-benchmark-2026.md) Researchers at MBZUAI developed CT-SpatialVQA, a benchmark for testing whether 3D medical AI systems can track the spatial relationships of anatomy and abnormalities across computed tomography (CT) volumes. In a 19 October university report, the dataset comprised 9,077 spatial question-and-answer pairs derived from 1,601 chest CT scans and radiology reports. The researchers evaluated eight vision-language models in a zero-shot setting. None reached 50% accuracy, and the average across the eight was 34.08%. CT-Chat scored 43.69%, MedEvalKit 40.16%, MedGemma-1.5 38.24% and VILA-M3 28.20%. The work was accepted as an oral presentation at MICCAI 2026. These are results from a particular research benchmark; they do not establish clinical competence or validated use in patient care. ## Data ### CT-SpatialVQA model accuracy results Selected results and overall mean from the university’s evaluation of eight models. Methodology: These are zero-shot accuracy results on the CT-SpatialVQA benchmark. The mean covers eight models; the table lists four models reported individually in the source and the mean. Results are not clinical validation. | Model | Accuracy | Unit | |---|---|---| | CT-Chat | 43.69 | percent | | MedEvalKit | 40.16 | percent | | MedGemma-1.5 | 38.24 | percent | | VILA-M3 | 28.2 | percent | | Average across eight models | 34.08 | percent | Sources: · Download data: [JSON](https://newsverum.com/api/v1/articles/mbzuai-ct-spatialvqa-3d-medical-ai-benchmark-2026/data/ct-spatialvqa-model-accuracies?lang=en&format=json) · [CSV](https://newsverum.com/api/v1/articles/mbzuai-ct-spatialvqa-3d-medical-ai-benchmark-2026/data/ct-spatialvqa-model-accuracies?lang=en&format=csv) ### CT-SpatialVQA dataset Question and scan coverage in the research benchmark. Methodology: Counts describe the researchers’ test benchmark, not a patient population, diagnostic performance or clinical outcome. The source says the 9,077 questions were derived from 1,601 chest CT scans and radiology reports in the test set. | Component | Count | Unit | |---|---|---| | Spatial question-answer pairs | 9077 | count | | Chest CT scans | 1601 | count | Sources: · Download data: [JSON](https://newsverum.com/api/v1/articles/mbzuai-ct-spatialvqa-3d-medical-ai-benchmark-2026/data/ct-spatialvqa-dataset-size?lang=en&format=json) · [CSV](https://newsverum.com/api/v1/articles/mbzuai-ct-spatialvqa-3d-medical-ai-benchmark-2026/data/ct-spatialvqa-dataset-size?lang=en&format=csv) ## Sources - [Mohamed bin Zayed University of Artificial Intelligence]() (Source checked: 2026-10-20; Published: 2026-10-19) --- Cite the canonical URL above. [Editorial standards and corrections](https://newsverum.com/en/editorial)