BizGenEval: A Systematic Benchmark for Commercial Visual Content Generation
2026-03-26 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created BizGenEval, a new test to see how well image-generating models can make professional-looking documents like slides, charts, and posters. They designed this test to check if these models can handle tricky tasks like placing text correctly, controlling layout, matching styles, and understanding content. Using 400 prompts and 8000 questions, they tested 26 popular models and found many still struggle with these real-world tasks. Their work aims to help improve tools that create useful visual content for businesses.
image generationbenchmarkcommercial designlayout controltext renderingattribute bindingknowledge reasoningvisual content creationmodel evaluationdocument types
Authors
Yan Li, Zezi Zeng, Ziwei Zhou, Xin Gao, Muzhao Tian, Yifan Yang, Mingxi Cheng, Qi Dai, Yuqing Yang, Lili Qiu, Zhendong Wang, Zhengyuan Yang, Xue Yang, Lijuan Wang, Ji Li, Chong Luo
Abstract
Recent advances in image generation models have expanded their applications beyond aesthetic imagery toward practical visual content creation. However, existing benchmarks mainly focus on natural image synthesis and fail to systematically evaluate models under the structured and multi-constraint requirements of real-world commercial design tasks. In this work, we introduce BizGenEval, a systematic benchmark for commercial visual content generation. The benchmark spans five representative document types: slides, charts, webpages, posters, and scientific figures, and evaluates four key capability dimensions: text rendering, layout control, attribute binding, and knowledge-based reasoning, forming 20 diverse evaluation tasks. BizGenEval contains 400 carefully curated prompts and 8000 human-verified checklist questions to rigorously assess whether generated images satisfy complex visual and semantic constraints. We conduct large-scale benchmarking on 26 popular image generation systems, including state-of-the-art commercial APIs and leading open-source models. The results reveal substantial capability gaps between current generative models and the requirements of professional visual content creation. We hope BizGenEval serves as a standardized benchmark for real-world commercial visual content generation.