Q-Bench

What is Q-Bench?

Q-Bench/Q-Bench+ is a benchmark for general-purpose foundation models on low-level vision. Benchmark Radar tracks Q-Bench, cited by 1 source documents, with…

Released

2024-08-16

Evaluates

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

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

Q-Bench paper, code and dataset

• Paper https://arxiv.org/abs/2309.14181
• Code https://github.com/Q-Future/Q-Bench
• Dataset https://huggingface.co/datasets/teowu/LLVisionQA-QBench

Which sources cite Q-Bench?

• Q-Bench

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

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• Ada-LEval
• AECBench
• AFQMC
• AgentBoard