Microsoft has unveiled MAI-Image-1, its first in-house developed image generation model, set to be available on Copilot and Bing Image Creator soon, and is currently available for testing on LMArena.
On LMArena’s text-to-image leaderboard, MAI-Image-1 achieved a score of 1,096 points, ranking ninth. For comparison, Google’s Gemini-2.5-Flash scored 1,154 points, securing the second rank, while OpenAI’s model scored 1,123 points, ranking seventh. The leaderboard is currently led by Hunyuan-image-3.0, developed by the Chinese tech company Hunyuan.
Microsoft’s development team focused on enhancing MAI-Image-1 by avoiding repetitive or generically stylized outputs. “For example, we prioritised rigorous data selection and nuanced evaluation focused on tasks that closely mirror real-world creative use cases,” the company explained, adding that it incorporated feedback from professionals in creative industries.
The model excels at generating landscapes and photorealistic imagery, accurately capturing details such as lighting, shadows, and reflections, particularly when compared to “many larger, slower models.”
Microsoft has also developed other internal models, including MAI-Voice-1 for natural speech generation and the Phi series of small language models for efficient reasoning tasks. This development occurs alongside the company’s continued financial and infrastructural support for OpenAI.
The field of AI image generation is currently experiencing significant activity. OpenAI’s model recently gained attention for its ability to imitate the Studio Ghibli art style, while Google’s “Nano-Banana” was recognized for its advanced editing capabilities.
A comparison conducted on LMArena tested MAI-Image-1, Google’s Gemini-2.5-Flash, and OpenAI’s GPT-image-1 using a prompt depicting two people in a café by a window during the late afternoon. The evaluation focused on how each model handled mixed lighting, reflections, and the realism of shadows. Users can visit LMArena to test these models with similar prompts.
