WildTableBench: Benchmarking Multimodal Foundation Models on Table Understanding In the Wild
This benchmark fills a gap in evaluating multimodal models on naturally occurring table images, highlighting critical limitations for real-world applications.
WildTableBench introduces a benchmark of 402 real-world table images with 928 QA pairs, finding that only one out of 21 multimodal models exceeds 50% accuracy, with others ranging from 4.1% to 49.9%, revealing persistent weaknesses in structural perception and reasoning.
Using multimodal foundation models to analyze table images is a high-value yet challenging application in consumer and enterprise scenarios. Despite its importance, current evaluations rely largely on structured-text tables or clean rendered images, leaving the visual complexity of in-the-wild table images underexplored. Such images feature varied layouts and diverse domains that demand sophisticated structural perception and numerical reasoning. To bridge this gap, we introduce WildTableBench, the first question-answering benchmark for naturally occurring table images from real-world settings. WildTableBench comprises 402 high-information-density table images collected from online forums and websites across diverse domains, together with 928 manually annotated and verified questions spanning 17 subtypes across five categories. We evaluate 21 frontier proprietary and open-source multimodal foundation models on this benchmark. Only one model exceeds 50% accuracy, while all remaining models range from 4.1% to 49.9%. We further conduct diagnostic analyses to characterize model failures and reveal persistent weaknesses in structural perception and reasoning. These results and analyses provide useful insights into current model capabilities and establish WildTableBench as a valuable diagnostic benchmark for table image understanding.