Prediction model leaderboard

Every trained model, ranked by how far it beats the benchmark its own market has to clear. Accuracy across different markets is not comparable, because a line that falls one way most of the time hands a model a high score for learning very little. The gap to the benchmark is what ranks here.

2 of 4 beat their baseline by more than a point

Sort byEdge over baseline Accuracy Log loss Sample size

SportAll football basketball tennis

Models ranked by edge over their market baseline
#	Model	Edge	Accuracy	Baseline	Log loss	Sample	Since last train
1	Tennis games over 23.5 tennis · Totals · Always pick the majority class	+9.28	65.08%	55.80%	0.6076	14,562	▲ 0.20
2	Tennis games over 21.5 tennis · Totals · Always pick the majority class	+4.57	59.78%	55.21%	0.6196	14,562	▲ 0.21
3	Tennis games over 19.5 tennis · Totals · Always pick the majority class	+0.75	67.31%	66.56%	0.5820	14,562	▼ 0.03

Edge is accuracy minus the baseline, in percentage points, measured on the held-out test period each model was evaluated against, never on data it trained on. A model with no recorded baseline shows its accuracy but no edge, because there is nothing to say how much of that accuracy is skill.