Recent progress in Multimodal Large Language Models (MLLMs) has significantly enhanced the ability of artificial intelligence systems to understand and generate multimodal content. However, the capabilities of existing MLLMs in understanding traditional Chinese culture have not yet been comprehensively explored. To address this gap, we propose the Traditional Chinese Culture understanding Benchmark (TCC-Bench), a bilingual Visual Question Answering (VQA) benchmark designed to assess MLLMs’ performance on culturally grounded visual content. TCC-Bench features culturally rich and visually diverse data, covering museum artifacts, daily life scenes, comics, and other culturally significant contexts across eight cultural domains. Through extensive experiments on a wide range of MLLMs, we find that current models still face substantial challenges in handling traditional Chinese cultural content. Our results highlight the need for more culturally inclusive and context-aware multimodal systems. The code and data can be found at: https://github.com/Morty-Xu/TCC-Bench.