Benchmark
CivBench
What is CivBench?
Evaluates language model agents in long-horizon, tool-mediated Civilization VI gameplay via 76 MCP tools. Benchmark Radar tracks CivBench, cited by 1 source…
- Released
- 2026-09-02
- Evaluates
- General AI, Language & Knowledge, cs.AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-name-audit-deferred
- Reported scores
- 0
Source provenance
- Original evidence https://arxiv.org/abs/2609.02459
CivBench paper and code
No reported scores are on record for this benchmark yet.