Every applicable check passed. Failed calls count as not passing.
How long one answer takes on this model.
Of cases run more than once, the share whose all-pass result was the same every time. Low: the model is inconsistent on these cases.
What one answer costs on this model, reused or not.
What this run spent: reused outputs cost nothing.
OptionalfailureThe error most failed answers share (runner).
OptionaljudgeWhat grading's judge spent, apart from the model under test (runner).
OptionalmeasuresPer check, the mean of each measure its answers carried (brier, logLoss, …), and, where answers carried a confidence, the calibration error. Only checks with measures appear.
Partial credit summed over answers (e.g. items right of items expected), where the suite gives it; the headline when present.
A test's numbers: answers right, partial credit, each check's pass rate, consistency, cost, time, and reuse.