← all datasets

RevQA

Emerging

3papers using it

2024first seen

RevQA is a question-answering benchmark designed to evaluate the spatial reasoning abilities of multimodal large language models (MLLMs).

🔎 Find this dataset

Papers using RevQA (3)

Rexvqa: A Large-scale Visual Question Answering Benchmark For Generalist Chest X-ray Understanding2025 · 3 cites

REVISION: Rendering Tools Enable Spatial Fidelity in Vision-Language Models2024

Multimodal Hypothetical Summary for Retrieval-based Multi-image Question Answering2024

RevQA — datasets — multimodal