@realmadhuguru
Gemini can now reason and use code to complete vision tasks. The model can turn a table of data into high quality charts, analyze infographics, understand image contents and draw bounding boxes, visually sort things by size etc. Try it out and tell us your use cases! Google AI Developers: Try 👁 Agentic Vision with Gemini 3 Flash in @GoogleAIStudio or Vertex AI. This new capability enables the model to effectively use code and reasoning to improve performance for common vision tasks. See Agentic Vision in action: http://goo.gle/3Z05KxK
View on X