JuryBench
Explore score history ↗Evaluates LLM-simulated jurors on controversial U.S. criminal law cases with defendant statements of varying backgrounds and emotional appeal, measuring verdict severity changes.
- Released
- 2026-09-09
- Evaluates
- General AI, Safety & Trustworthiness, cs.CL
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
JuryBench paper and code
No reported scores are on record for this benchmark yet.