Vera-Bench
Explore score history ↗Vera-Bench is an executable safety benchmark for tool-using agents, with deterministic, artifact-grounded verification across diverse risks and execution settings.
- Released
- 2026-07-02
- Institutions
- Zhejiang University · Fudan University · Alibaba Group (China)
- Evaluates
- Agents, Safety, Safety & Trustworthiness, Software & AI Compute
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
Vera-Bench paper and code
No reported scores are on record for this benchmark yet.