Benchmark
DungeonBench
What is DungeonBench?
DungeonBench evaluates tactical reasoning in Dungeons & Dragons combat with two tracks: Encounter for single fights and Day for linked encounters with…
- Released
- 2026-07-31
- Evaluates
- General AI, Language & Knowledge, Reasoning
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
- Reported scores
- 0
Source provenance
- Original evidence https://arxiv.org/abs/2607.29577
DungeonBench paper
No reported scores are on record for this benchmark yet.