SABER Benchmark
Explore score history ↗SABER evaluates operational safety of LLM coding agents in stateful project workspaces. Agents perform realistic tasks, and safety is scored from the final environment state after action sequences. Violations are categorized by cause, enabling model-specific safety profile analysis.
- Released
- 2026-05-31
- Evaluates
- Agents, Agents & Tool Use, General AI, Safety
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
SABER paper and code
No reported scores are on record for this benchmark yet.