DBA-Bench
Explore score history ↗A production-fidelity benchmark for LLM-based database operations agents, using instrumented PostgreSQL environments with active workloads and outcome-first evaluation across 106 scenarios.
- Released
- 2026-07-24
- Institutions
- University of Electronic Science and Technology of China
- Evaluates
- General AI, Language & Knowledge, cs.DB
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
DBA-Bench paper
No reported scores are on record for this benchmark yet.