September 19, 2026
Grok Imagine Image 2.0 joins the generation leaders: 4th place in Text to Image
The model ranked 4th in the Text to Image leaderboard on September 18, 2026. It is the best result among non-OpenAI models and a rise of 14 positions over the previous generation. Grok Imagine Image 2.0 also reached the Pareto frontier for quality and price.
Artificial Analysis
@artificialanlys
xAI's Grok Imagine Image 2.0 ranked 4th in the Artificial Analysis Text to Image Leaderboard. It is the highest-ranked non-OpenAI model, up 14 positions from the previous generation, and has reached the Pareto frontier for quality and price. Grok Imagine Image 2.0 is xAI's latest image model, released in August. It supports text-to-image generation, image editing, and multi-reference generation using up to five input images. Grok Imagine Image 2.0 substantially outperforms the previous generation, grok-imagine-image-quality: it rose from 18th to 4th in Text to Image and from 16th to 10th in Image Editing. Across all Text to Image capabilities and use cases we measure, the gap to the leaders has narrowed. The largest gains came in Knowledge, Text Rendering, and Lighting. Grok Imagine Image 2.0 is available through the xAI API as grok-imagine-image-2.0, in Grok Imagine at http://grok.com and in the Grok apps, as well as through fal and Replicate. Congratulations to @SpaceXAI and @elonmusk on the release! Below, you will find our analysis and examples of Grok Imagine Image 2.0 results in the Artificial Analysis Image Arena 🧵
· 42.6K views
The previous version ranked 18th in Text to Image and 16th in Image Editing. Grok Imagine Image 2.0 climbed to 4th and 10th, while Artificial Analysis recorded the largest gains in Knowledge, Text Rendering, and Lighting.
Where to get it. The model is available through the xAI API as `grok-imagine-image-2.0`, in Grok Imagine at grok.com and in the Grok apps, as well as through fal and Replicate. It creates and edits images and accepts up to five source images for a single generation.
Grok Imagine Image 2.0 is already available through the xAI API, Grok, fal, and Replicate.
