What is QANTA?

The QANTA project uses trivia competitions to compare computer systems against expert humans in games of question answering. Our goal is to advance question answering — helping computers learn from how trivia experts think, studying human–computer collaboration, and building tools that help humans write challenging questions efficiently. Led by **[Jordan Boyd-Graber](https://users.umiacs.umd.edu/~jbg/)** (University of Maryland), QANTA brings together researchers from computer science, linguistics, and information science at UMD and UC Berkeley.

Explore

2026 Competition

The world's first multimodal Quizbowl competition — text and image clues. Compete, write questions, or build a multimodal AI system.

Coming 2026
Data & Code

Download QANTA datasets and explore open-source code on GitHub.

Open Source

In the News

2025Humans and AI Join Forces
2024Jeopardy! @ UMD: Jordan Boyd-Graber Receives Shout-Out on Jeopardy! Masters

Supported by

Adobe TRAILS

The views and opinions expressed here are those of the authors and do not necessarily reflect those of the sponsors.

Contact

Questions about QANTA? Email qanta@googlegroups.com.