Benchmark

MicroVQA Benchmark

What is MicroVQA?

MicroVQA is a benchmark that evaluates LLM reasoning on multiple-choice questions about microscopy images, created by expert biologists.

Released: 2025-03-17
Modality: multimodal
Evaluates: 多模态, Multimodal, 科学智能, AI for Science, 跨模态推理, Cross-modal Reasoning, 科学推理, Scientific Reasoning, 不支持, Unsupported
Openness: open
Importer: OpenCompass Hub
Reported scores: 0

Source provenance

Original evidence https://hub.opencompass.org.cn/dataset-detail/MicroVQA

MicroVQA paper, code and dataset

Paper https://arxiv.org/abs/2503.13399
Code https://github.com/jmhb0/microvqa
Dataset https://huggingface.co/datasets/jmhb/microvqa

No reported scores are on record for this benchmark yet.

Which sources cite MicroVQA?

MicroVQA

Related 多模态, Multimodal, 科学智能, AI for Science, 跨模态推理, Cross-modal Reasoning, 科学推理, Scientific Reasoning, 不支持, Unsupported benchmarks