Evidence Package Benchmark
Explore score history ↗Evaluates evidence-bounded mental health reasoning over 1,870 packages from six heterogeneous speech-text sources, scoring diagnosis accuracy and claim violations under modality masks.
- Released
- 2026-08-31
- Evaluates
- Biology & Drug Discovery, Reasoning, Speech & Audio
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-name-audit-deferred
Evidence Package Benchmark paper
No reported scores are on record for this benchmark yet.