system-one-bench ES·EN v2.10.0
View 5 · comparator

Compare two configurations

McNemar's test compares two models on the same cases and only counts the cases where they disagree: b = cases only A gets right, c = cases only B gets right. With p < 0.05 the difference is unlikely to be chance. Here a hit only counts if it is exact (no half points).

Loading…

Only A right (b)Both rightOnly B right (c)

Cases where they disagree