MRAG-Bench

What is MRAG-Bench?

MRAG-Bench consists of 16,130 images and 1,353 human-annotated multiple-choice questions across 9 distinct scenarios, providing a robust and systematic…

Released

2024-10-10

Modality

multimodal

Evaluates

多模态, Multimodal, VQA, 多模态模型, VLM, 跨模态推理, Cross-modal Reasoning, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/MRAG-Bench

MRAG-Bench paper, code and dataset

• Paper https://arxiv.org/abs/2410.08182
• Code https://github.com/mragbench/MRAG-Bench
• Dataset https://huggingface.co/datasets/uclanlp/MRAG-Bench

Which sources cite MRAG-Bench?

• MRAG-Bench

Related 多模态, Multimodal, VQA, 多模态模型, VLM, 跨模态推理, Cross-modal Reasoning, 不支持, Unsupported benchmarks

• 3DCodeBench
• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• ActiveFly-Bench
• Ada-LEval
• AECBench