GISAgentBench
Explore score history ↗GISAgentBench evaluates LLM agents on multi-step GIS tasks from practitioner sources, with 349 tasks and executable reference trajectories.
- Released
- 2026-08-03
- Institutions
- University of Florida
- Evaluates
- General AI, Language & Knowledge, cs.AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
GISAgentBench paper
No reported scores are on record for this benchmark yet.