MTVQA Benchmark

What is MTVQA?

MTVQA is designed to evaluate LMMs' multilingual text understanding, featuring high-quality human expert annotations across 9 diverse languages.

Released

2024-06-04

Modality

multimodal

Evaluates

多模态, Multimodal, 理解, Understanding, VQA, 多模态模型, VLM, 图像理解, Image Understanding, 不支持, Unsupported

Openness

restricted

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

MTVQA paper, code and dataset

• Paper https://arxiv.org/abs/2405.11985
• Code https://github.com/bytedance/MTVQA
• Dataset https://huggingface.co/datasets/ByteDance/MTVQA

Which sources cite MTVQA?

• MTVQA

Related 多模态, Multimodal, 理解, Understanding, VQA, 多模态模型, VLM, 图像理解, Image Understanding, 不支持, Unsupported benchmarks

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