The cases two tests graded differently, on the cases they share: a
different score, different checks failed, or an answer on one side and
none on the other. Cases the challenger broke come first, then fixed,
then the rest, each in case order. Use it to read where two models
disagree: next to compareRuns, which says by how much.
The cases two tests graded differently, on the cases they share: a different score, different checks failed, or an answer on one side and none on the other. Cases the challenger broke come first, then fixed, then the rest, each in case order. Use it to read where two models disagree: next to
compareRuns, which says by how much.