Build a shortlist

Use this order. Each step removes benchmarks that cannot support your decision. 1. Reject tasks that do not match the decision. 2. Reject graders that cannot tell apart the failures that matter. 3. Check that the data licence and access terms allow your run. 4. Prefer benchmarks with room below the…

The rest of this lesson is for learners enrolled in the course. See how Choose and run an AI benchmark for a model decision works