English Français العربية

AI glossary

146 terms explained plainly, in English, French and Arabic.

  • 11 topics
  • English, French and Arabic

6 terms

A

Evaluation Arena Elo A rating built from many people comparing two anonymous model answers side by side and picking the better one.

D

Evaluation Data contamination When benchmark questions or answers appear in a model's training data, inflating its score.

E

Evaluation Evaluation (evals) Systematically testing how well a model or AI application performs on the tasks you care about.

L

Evaluation Leaderboard A public ranking of models on one or more benchmarks. Evaluation LLM as a judge Using a language model to grade other models' outputs against criteria, to evaluate at scale.

S

Evaluation SWE-bench A benchmark that measures whether a model can fix real GitHub issues in open-source projects, verified by the project's own tests.