LongText-Bench is a text understanding benchmark dataset released by Tencent in 2025. The related paper results are "X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again", which aims to evaluate the model's ability to accurately understand long Chinese and English texts. The dataset contains 160 prompts for evaluating long text rendering tasks, covering 8 different scenarios (road signs, labeled objects, printed materials, web pages, slides, posters, headlines, and dialogues).

Dataset features:

• Cross-language coverage
• Text length
• Gradient Design

Citation

@article{geng2025xomni,
author       = {Zigang Geng, Yibing Wang, Yeyao Ma, Chen Li, Yongming Rao, Shuyang Gu, Zhao Zhong, Qinglin Lu, Han Hu, Xiaosong Zhang, Linus, Di Wang and Jie Jiang},
title        = {X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again},
journal      = {CoRR},
volume       = {abs/2507.22058},
year         = {2025},
}