Arena 新增图像编辑细分榜单，GPT Image 2 领跑
想挑最好的文生图或修图模型？Arena 新出的细分榜单能帮你一眼看出每个模型的强项，GPT Image 2 全类别第一，文本渲染最突出。
Text-to-Image Arena 推出 Single 和 Multi-Image Edit 两个新竞技场，每个竞技场均包含写实、肖像、卡通、艺术、3D 建模、商业设计和文本渲染七个类别。
GPT Image 2 在这七个类别中均位列第一，尤其擅长文本渲染。Mai Image 2.
5 和 Muse Image 在单图编辑中表现接近，仅次于 GPT Image 2。在多图编辑中，Seedream 5.
0 Pro 和 Muse Image 在文本渲染、肖像、写实等类别上差距不大，但在 3D 建模和卡通方面有更明显的区分。
Text-to-Image Arena helps you find image generation models with granular categories. Now, we’re bringing that same level of detail to image editing by launching categories in Single and Multi-Image Edit Arenas. With millions of real user comparisons, Arena can show not just which model wins overall—but what each model does best. Single Image Edit and Multi-Image Edit have the same seven categories as Text-to-Image: photorealistic, portraits, cartoon, art, 3D modeling, commercial design, and text rendering. - GPT Image 2 is #1 in all seven categories, with a particular strength in Text Rendering. - Mai Image 2.5 and Muse Image are comparable in Single-Image Edit, ranking behind GPT Image 2 - Similarly, for Multi-Image Edit, Seedream 5.0 Pro and Muse Image are very close across categories including Text Rendering, Portraits and Photorealistic, with more differentiation around 3D Modeling and Cartoon.📊 11 ⚡
This report is categorized under AITOP's "Products" desk. Key entities and technical topics under continuous tracking include GPT Image 2, Mai Image 2.5, Seedream 5.0 Pro, 文生图.
Source attribution: curated from lmarena.ai (@lmarena_ai).
