See what 4 builders are making with Gemini 3.8 Flash

Gemini 3.8 Flash is our most intelligent workhorse model, delivering significant improvements from 3.7 Flash across software engineering, agentic tasks, and critical, multistep reasoning in specialized domains. These performance gains stem from a core design choice: 3.8 Flash works harder. On complex tasks, it exhibits greater diligence — executing extra reasoning steps and calling tools iteratively to land a more accurate output.

Builders have been creating with Gemini 3.8 Flash since we launched it and new audio models this month. From developing simulations to testing visual reasoning, check out some of the coolest builds and experiments from the community so far.

Create a model rocket simulation.

Ashutosh Shrivastava (@ai_for_success on X) used Gemini 3.8 Flash and Google Antigravity to map the live paths of satellites, space stations, and orbital rockets.

Animate an ink painting.

Noctus (@noctus91 on X) used Gemini 3.8 Flash’s multimodal capabilities to transform Seigaiha waves — a traditional Japanese pattern — into what looks like a moving ink painting.

Create a 3D dinosaur skeleton.

Gemini 3.8 Flash delivers substantial gains on multistep reasoning in STEM and other fields. Emily (@IamEmily2050 on X) pushed these capabilities, asking the model to create a T. rex skeleton with a four-phase prompt, complete with strict requirements, banned shortcuts, and accuracy checks.

Build an automatic transmission simulation from scratch.

Hakm (@hakmgpt on X) gave Gemini 3.8 Flash an engineering challenge: Build an interactive model of an automatic transmission. His prototype involves 10 camera views, four display modes, smart labels, and a side panel that teaches you more about any transmission part you click on.

Gemini 3.8 Flash delivers substantial gains from 3.7 Flash, often approaching the performance of higher-cost frontier models. Try it across Google products and tools, including Google Antigravity and Google AI Studio.