With the rapid advancements in diffusion models, text-to-image (T2I) models have achieved remarkable progress, demonstrating impressive capabilities in prompt adherence and image generation. Recently released models such as FLUX.1 and Ideogram2.0, alongside others like DALL-E 3 and Stable Diffusion 3, have shown exceptional performance across various complex tasks, sparking discussions about the potential of T2I models to become general-purpose tools. Beyond traditional image generation, these models excel in diverse areas, including controllable generation, image editing, video, audio, 3D, and motion generation, as well as computer vision tasks such as semantic segmentation and depth estimation. However, existing evaluation frameworks fall short in comprehensively assessing their performance across these expanding domains. To address this, we developed the IMAGINE-E to rigorously evaluate six leading models: FLUX.1, Ideogram2.0, Midjourney, DALL-E 3, Stable Diffusion 3, and Jimeng. Our evaluation framework focuses on five critical areas: structured output generation, realism and physical consistency, specific domain generation, challenging scenario generation, and multi-style creation tasks. This in-depth assessment highlights the strengths and weaknesses of each model, with FLUX.1 and Ideogram2.0 excelling in structured and domain-specific tasks, showcasing the growing potential of T2I models as foundational AI tools. This study offers valuable insights into the current capabilities and future development of T2I models as they progress towards general-purpose applicability.