Read the leaderboard as three questions, not one score.
Three bars per system, dark to light: overall, held-out, stress set. Every system holds up on held-out questions, then drops sharply on the eight-question stress set.
Overall is the share of all 88 tasks correct. Held-out is the generalization number that matters most. Stressis the diagnostic probe. Two systems tie for the highest overall accuracy, so “best” is a judgement call, not a ranking.
— click any row there to see exactly which questions that system missed.