ThaiOCRBench: A Task-Diverse Benchmark for Vision-Language Understanding in Thai

TL;DR

ThaiOCRBench is a comprehensive benchmark designed to evaluate vision-language models on diverse Thai text-rich visual understanding tasks, highlighting performance gaps and challenges in low-resource, script-complex settings.

Contribution

It introduces the first diverse, human-annotated Thai benchmark for vision-language understanding, covering 13 task categories and evaluating multiple models in zero-shot settings.

Findings

Proprietary models outperform open-source models.

Fine-grained text recognition and handwritten content extraction are challenging for open-source models.

Key challenges include language bias, structural mismatch, and hallucinated content.

Abstract

We present ThaiOCRBench, the first comprehensive benchmark for evaluating vision-language models (VLMs) on Thai text-rich visual understanding tasks. Despite recent progress in multimodal modeling, existing benchmarks predominantly focus on high-resource languages, leaving Thai underrepresented, especially in tasks requiring document structure understanding. ThaiOCRBench addresses this gap by offering a diverse, human-annotated dataset comprising 2,808 samples across 13 task categories. We evaluate a wide range of state-of-the-art VLMs in a zero-shot setting, spanning both proprietary and open-source systems. Results show a significant performance gap, with proprietary models (e.g., Gemini 2.5 Pro) outperforming open-source counterparts. Notably, fine-grained text recognition and handwritten content extraction exhibit the steepest performance drops among open-source models. Through detailed error analysis, we identify key challenges such as language bias, structural mismatch, and hallucinated content. ThaiOCRBench provides a standardized framework for assessing VLMs in low-resource, script-complex settings, and provides actionable insights for improving Thai-language document understanding.