Brier score
Mean squared error between the market’s final YES probability and the actual 0/1 outcome. 0 is perfect, 0.25 is a coin flip, 1 is consistently wrong. Lower is better.
Loading dashboard…
Loading dashboard…
Loading accuracy leaderboard…
How well the markets ProbCast tracks have actually called events that resolved. We record each market’s final YES probability and its real outcome at settlement, then score the two against each other — per venue and overall.
ProbCast records each market’s final pre-resolution probability and compares it to the real outcome once the market settles. No venue ranking is shown yet because not enough tracked markets have resolved to score a credible track record — the leaderboard fills in as outcomes accumulate.
A forecast is only as credible as its track record, and that record can only be built forward in time — which is why outcome capture runs from day one. These counts reflect what ProbCast is tracking right now; the numbers above are not a measure of accuracy.
The falsifiable test of the Trust Score: if it means anything, High-trust markets should realize a lower Brier loss than Low-trust ones. Forward-only — scored from markets captured and resolved after tracking began, never backfilled.
Mean squared error between the market’s final YES probability and the actual 0/1 outcome. 0 is perfect, 0.25 is a coin flip, 1 is consistently wrong. Lower is better.
The share of resolved markets where the side the market favored (above 50%) is the side that won. A blunter measure than Brier, but easy to read.
Voided or non-binary settlements are excluded. Samples are small until enough markets resolve, so treat early numbers as directional. See the methodology for how probabilities are derived. ProbCast provides prediction-market data and analytics for informational purposes only. Not financial, trading, betting, investment, legal, or tax advice.