CivBench
Explore score history ↗Evaluates language model agents in long-horizon, tool-mediated Civilization VI gameplay via 76 MCP tools.
- Released
- 2026-09-02
- Institutions
- University of Oxford · Imperial College London
- Evaluates
- General AI, Language & Knowledge, cs.AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-name-audit-deferred
CivBench paper and code
No reported scores are on record for this benchmark yet.