# Microsoft's MAI-Image-2.5 pulls even with Google's Nano Banana 2 on benchmarks > Source: > Published: 2026-05-27 18:31:10+00:00 # Microsoft's MAI-Image-2.5 pulls even with Google's Nano Banana 2 on benchmarks **Microsoft shipped an update to its MAI image model.** MAI-Image-2.5 currently sits at number three on [Arena's text-to-image leaderboard](https://arena.ai/leaderboard/text-to-image), according to the MAI team. That puts it on par with [Google's Nano Banana 2](https://the-decoder.com/google-explains-the-differences-between-its-three-nano-banana-image-generation-models/), though still a clear step behind [OpenAI's Image-2](https://the-decoder.com/openais-chatgpt-images-2-0-thinks-before-it-generates-adding-reasoning-and-web-search-to-image-creation/). [Microsoft](https://microsoft.ai/news/mai-image-2-5-launches-at-no-3-on-arena-ai/) calls it the strongest MAI image model yet, with major gains over [MAI-Image-2](https://the-decoder.com/microsofts-superintelligence-team-ships-mai-image-2-a-text-to-image-generator/) in text rendering, stylized illustrations, and commercial visuals. It's also said to follow prompts more closely and produce more consistent lighting, depth, and spatial relationships. Microsoft is pitching it for professional use cases like product photography and brand design. MAI-Image-2.5 is available now on [Arena](https://arena.ai/image) and should roll out to the [MAI Playground and Foundry](https://microsoft.ai/news/mai-image-2-5-launches-at-no-3-on-arena-ai/) within two weeks. ``` AI News Without the Hype – Curated by Humans Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section. Subscribe now ``` Source: