MMT-Bench

What is MMT-Bench?

MMT-Bench is designed to assess LVLMs across massive multimodal tasks requiring expert knowledge and deliberate visual recognition, localization, reasoning…

Released

2024-04-24

Modality

multimodal

Evaluates

多模态, Multimodal, 推理, Reasoning, 多模态模型, VLM, 逻辑推理, 不支持, Unsupported

Openness

open

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

MMT-Bench paper, code and dataset

• Paper https://arxiv.org/abs/2404.16006
• Code https://github.com/OpenGVLab/MMT-Bench
• Dataset https://huggingface.co/datasets/Kaining/MMT-Bench

Which sources cite MMT-Bench?

• MMT-Bench

Related 多模态, Multimodal, 推理, Reasoning, 多模态模型, VLM, 逻辑推理, 不支持, Unsupported benchmarks

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