Vision Language Models (VLMs) have shown great success in general visual tasks, yet they still struggle to deeply understand text within images. In this paper, we introduce **ReViCo** (**Re**al **Vi**sual **Co**rrection), a benchmark designed to evaluate VLM text understanding through a novel task of visual text error correction. ReViCo challenges models with identifying and fixing text errors in real-world images, which requires a deep understanding on visual text. We benchmark various VLMs using two distinct paradigms: prompt-based strategy and targeted model training, both aimed at pushing the limits of current models. Our experiments reveal a striking performance gap between even the best VLMs and human, and further analysis also shows that most models struggle to accurately perceive the visual text, resulting in frequent correction errors. By highlighting these gaps, ReViCo provides a new benchmark foundation for developing more robust and text-aware VLMs.