Everyone who calls elections, scored

The one metric they all share is win-call Brier (a pollster's win probability is derived from its margin; forecasters publish one directly). A Bayesian two-way model adjusts for race difficulty, the bar is each entity's 90% credible interval (wide = few races), and the board is ranked by a conservative estimate so thin coverage can't top it. Pick an office; lower (left) is better. Sharp forecaster probabilities lead here — switch to pollster ratings for the margin-accuracy view.

Polymarketis included as a market model using our timestamp-matched, resolved race archive. The displayed sample is scoreable overlap, not Polymarket's lifetime coverage. Kalshi is evaluated the same way using its archived pre-election candlesticks. Their uncertainty bars reflect limited matched coverage; unresolved 2026 prices are never treated as scoring data.

VotePredictor+ is a meta-forecaster: it stacks our own model with the published expert consensus, leaning on the human shops where they've historically been sharper (the House) and on the model where it has (Senate, President), with the blend weight fit on prior cycles only. It is ranked in place like everything else, but read it knowing it ensembles the very forecasters it sits beside — an advantage none of them have. The like-for-like entry, and the one to judge the model itself by, is plain VotePredictor Elections.

VotePredictor+ensemble goes one further and folds in the pollster consensus too — but it trails VotePredictor+, and that's the interesting part: the poll signal is already inside the model, which de-biases and recency-weights the same polls far better than a raw pollster average. Adding that average back is redundant and adds no lift — evidence that the gains live in the forecasters' judgment, not in re-counting the polls.