GEO-Bench
Explore score history ↗GEO-Bench evaluates ranking manipulation attacks in generative engine optimization under a unified protocol, measuring effectiveness and stealth across five datasets against a fixed ranker, with open-source attack implementations.
- Released
- 2026-05-27
- Institutions
- University of Southern California · Arizona State University
- Evaluates
- Robot manipulation, Robotics, Robotics & Embodied AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
GEO-Bench paper
No reported scores are on record for this benchmark yet.