Address: 965 Florida Ave NW, Washington DC, 20001 , Rooftop
Objective: Create at least 1 benchmark per 15 cabinet-level Departments: Agriculture, Commerce, Defense, Education, Energy, Health and Human Services, Homeland Security, Housing and Urban Development, Interior, Justice, Labor, State, Transportation, Treasury, and Veterans Affairs.
Why You Should Care: The Federal & state governments are spending $1 billion+ on AI chatbots this year. Every main AI lab is now scrambling to understand how their models perform on government domains–it’s a huge priority. The problem is, they don’t have government expertise. Via GovBench, you will quite literally set the standard for how models are leveraged and evaluated across government(s). The main AI labs and senior government officials are closely watching the outputs of this hackathon…no pressure.