SteerBench-Work
Explore score history ↗SteerBench-Work evaluates agent steering decisions at action boundaries in workplace scenarios across seven domains, with 106 incident-anchored scenarios and evidence-reversed mirrors, scored on correct proceed/hold boundaries.
- Released
- 2026-08-12
- Evaluates
- Agents, Biology & Drug Discovery, Finance, General AI, Language & Knowledge
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
SteerBench-Work paper
No reported scores are on record for this benchmark yet.