Tencent’s AI image model beats Google’s Nano Banana in leaderboard

Tencent Holdings’ new artificial intelligence model, Hunyuan Image 3.0, has surpassed Google DeepMind’s “Nano Banana” as the leading image-generation model among both open-source and closed products, according to a major public leaderboard.

As of Saturday, the open-source Hunyuan Image 3.0 secured the top position in the text-to-image rankings on LMArena, an AI model evaluation platform originally started by researchers at the University of California, Berkeley.

The previous leader – Google DeepMind’s Gemini 2.5 Flash Image, also known as Nano Banana – rapidly gained popularity after its release in late August because of its image editing accuracy and 3D-figurine generation.

When Tencent released Hunyuan Image 3.0 late last month, the company said the model was “completely comparable to the industry’s flagship closed-source models”. It has 80 billion parameters, making it the largest open-source image-generation model to date.

Parameters are the variables that encode a model’s intelligence and are adjusted during training. Generally, a higher number of parameters indicates a more powerful model, though it also requires greater computational resources to train and operate.