SAKE Benchmark
Explore score history ↗SAKE is a standardized multiple-choice evaluation of software-architecture knowledge in language models, covering eight architectural categories and four context-length levels.
- Released
- 2026-06-28
- Institutions
- University of Southern Denmark
- Evaluates
- Code & Software, Factuality, General AI, cs.SE
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
SAKE paper
No reported scores are on record for this benchmark yet.