Francesco Piccinno

I'm thrilled about Gemini's MM reasoning capabilities, which can revolutionize how intellectual work is done in society. Gemini aids in extracting and aggregating information from plots/diagrams/infographics etc., also generating novel insights. And it can do this at scale.

I find this example from the report a particularly good illustration of both the multimodal capabilities as well as the reasoning capabilities of Gemini. Given this image as input and the prompt: “Spot a data point that stands out in these charts and what that implicates. Then produce a detailed markdown table for all the data shown” Gemini is able to produce the response shown: “The data point that stands out is the United States’ landfilled plastic waste, which is 73%. This is significantly higher than the other countries and regions shown. This implies that the United States is not doing as much to recycle or incinerate its plastic waste as other countries and regions.” Along with a rendered table version of every data point represented in the bar charts.