SafePyramid Benchmark
Explore score history ↗SafePyramid evaluates in-context policy guardrailing across 1,000 multi-turn conversations and 3,000 application-specific policies containing 61,699 natural-language rules, organized into three hierarchical capability levels (L0, L1, L2). Scoring is based on violated-rule set prediction with metrics RMR and RDR, and the evaluation harness supports any API or local model.
- Released
- 2026-06-29
- Institutions
- The University of Melbourne
- Evaluates
- General AI, Safety, Safety & Trustworthiness
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
SafePyramid paper and code
No reported scores are on record for this benchmark yet.