PashtoOCR Benchmark

What is PashtoOCR?

PsOCR is a large-scale synthetic dataset for Optical Character Recognition in low-resource Pashto language. Benchmark Radar tracks PashtoOCR, cited by 1 source…

Released

2025-05-01

Modality

multimodal

Evaluates

多模态, Multimodal, 理解, Understanding, 语言, Language, OCR, NLP, Computer Vision, 多模态模型, VLM, 图像理解, Image Understanding, 语言理解, Comprehension, OCR与文档理解, OCR and Document Understanding, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

PashtoOCR paper, code and dataset

• Paper https://arxiv.org/abs/2505.10055v1
• Code https://github.com/zirak-ai/PashtoOCR
• Dataset https://huggingface.co/datasets/zirak-ai/Pashto-OCR
• Dataset https://huggingface.co/datasets/zirak-ai/PashtoOCR

Which sources cite PashtoOCR?

• PashtoOCR

Related 多模态, Multimodal, 理解, Understanding, 语言, Language, OCR, NLP, Computer Vision, 多模态模型, VLM, 图像理解, Image Understanding, 语言理解, Comprehension, OCR与文档理解, OCR and Document Understanding, 不支持, Unsupported benchmarks

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