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

Contact

Questions about QANTA? Email qanta@googlegroups.com.