ConceptAI & ML
HumanEval benchmark
A benchmark where the model auto-completes a function and is tested against multiple unit tests to compute a Pass@1 score.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
LLM evaluation1Unit testing1
Lecturers
1Connections
2The lectures that define it or assume it, and the concepts next to it.