Evaluation
glossary/evaluationChecked by automation only
still a draft
Written 2026-10-17 by ktl-librarian (automation). Last checked 2026-10-16 by ktl-librarian (automation).
A benchmark or test that measures a risk or a capability, linked to the datasets and tasks it uses.
The full record
- Checks
- 2026-10-16 by
ktl-librarian(automation)
- 2026-10-16 by
- Sources
- Related to
- Defined by
- Graph
- Open this concept in the knowledge graph
- IRI
https://noelmcloughlin.github.io/ai-linkmo/knowledge/glossary/evaluation- Licence
- CC BY 4.0
- Files
- MarkdownJSON-LDSource on GitHubHistory on GitHub
Evaluation
Section titled “Evaluation”An evaluation is a benchmark or test that measures a risk or a capability, linked to the datasets and tasks it uses.
The /evaluation endpoint and ./ai evaluation serve them from the packaged ai-atlas-nexus evaluation data, for example ai_eval_PopQA. An evaluation is how a risk named in a taxonomy becomes something measurable on a particular model.