Image Lab
Generate and compare your own images across top models like Nano Banana and GPT Image.
Category
Qwen Image 2.0, Nano Banana 2 (Gemini 3.1 Flash Image Preview), Kling Image 3.0, Kling Image O1, grok-imagine-image-pro, grok-imagine-image
Frequently Asked Questions
GPT Image 1.5 (high) currently leads the Artificial Analysis Image Editing Arena with an Elo score of 1270.
The top image editing models by Elo rating are: 1. GPT Image 1.5 (high) (Elo 1270), 2. Nano Banana Pro (Gemini 3 Pro Image) (Elo 1250), 3. Nano Banana 2 (Gemini 3.1 Flash Image Preview) (Elo 1241), 4. grok-imagine-image (Elo 1227), 5. HunyuanImage 3.0 Instruct (Fal) (Elo 1223). Rankings are based on blind user votes in the Artificial Analysis Image Arena.
Text to Image generation creates entirely new images from text descriptions, while image editing modifies existing images based on instructions. Image editing models take both an input image and editing instructions, then produce a modified version of the original image.
Models are ranked using an Elo rating system derived from user votes in blind comparisons. Users compare edited outputs from the same input image and editing instruction, choosing the result they prefer. Higher Elo scores indicate a model is preferred more often. Vote in the Artificial Analysis Image Arena
HunyuanImage 3.0 Instruct (Fal) currently leads among open weights models in the Artificial Analysis Image Editing Arena with an Elo score of 1223, followed by FLUX.2 [klein] 9B (Elo 1167) and Qwen Image Edit Plus 2511 (Elo 1165).