Pick 3 tests to cover the most bug-classes.

8 bug-classes, 8 tests, budget 3. Choose for marginal coverage — a second test that hits the same classes as the first adds nothing.

Practice — no rating pressure. Get as close to the optimum as you can; each play teaches the pattern.

Classes covered

0 / 8

0 / 3 picked

The Eval Set — practice the decision, scored against the optimum

What does the The Eval Set puzzle teach?

Pick tests for marginal coverage — a second test hitting the same bug-classes adds nothing.

Why do interviews ask about this?

Choosing a representative eval set is the “how do you measure your model” interview: cover the failure modes with the fewest cases.

How is it scored?

The engine computes the provably-optimal answer for the exact instance you played (dynamic programming, shortest-path, or exhaustive search — never a heuristic) and scores your attempt as a percentage of it. No login needed to see your score.

← Arena

Practice0:00

The Eval Set · D3

Pick 3 tests to cover the most bug-classes.

8 bug-classes, 8 tests, budget 3. Choose for marginal coverage — a second test that hits the same classes as the first adds nothing.

Practice — no rating pressure. Get as close to the optimum as you can; each play teaches the pattern.

Classes covered

0 / 8

0 / 3 picked