Updated 2026-04-23

The Sports Prediction Transparency Index

Most "sports prediction" providers won't tell you their Expected Calibration Error, keep their methodology secret, or hide pricing behind "contact us" forms. We score 21 real sources on five dimensions anyone can verify. Updated monthly.

Source Total ECE Archive Method API Price
ZenHodl
analytics model
 24/25 █████ █████ ████· █████ █████
FiveThirtyEight (archived)
analytics model
 21/25 ███·· █████ █████ ███·· █████
Manifold Markets
prediction market
 21/25 ██··· █████ ████· █████ █████
Bart Torvik
analytics model
 18/25 ████· ████· ████· █···· █████
MoneyPuck
analytics model
 17/25 ███·· ███·· ████· ██··· █████
PredictIt
prediction market
 15/25 █···· ████· ███·· ███·· ████·
Polymarket
prediction market
 15/25 ····· ███·· ██··· █████ █████
KenPom
analytics model
 13/25 ███·· ██··· ███·· ····· █████
The Odds API
enterprise data
 13/25 ····· █···· ██··· █████ █████
Kalshi
prediction market
 12/25 ····· ██··· ██··· █████ ███··
Massey Ratings
analytics model
 12/25 █···· ███·· ███·· ····· █████
SportsDataIO
enterprise data
 11/25 ····· ····· ██··· █████ ████·
Sportradar
enterprise data
 10/25 ██··· ····· ███·· █████ ·····
Stats Perform
enterprise data
 10/25 ██··· ····· ███·· █████ ·····
OddsJam
odds aggregator
 8/25 ····· ····· █···· ████· ███··
Unabated
odds aggregator
 7/25 ····· ····· ██··· ██··· ███··
BetQL
picks site
 7/25 ····· █···· █···· █···· ████·
SportsLine
picks site
 5/25 ····· ····· █···· ····· ████·
Action Network
picks site
 4/25 ····· ····· ····· █···· ███··
Covers
picks site
 3/25 ····· ····· ····· ····· ███··
Pinnacle (closing lines)
enterprise data
 1/25 ····· ····· █···· ····· ·····
1. ECE
Do they publish Expected Calibration Error on a known holdout?
5 = reliability table per sport · 0 = never mentioned
2. Archive
Can you see every past prediction, including misses?
5 = full auditable ledger · 0 = no archive
3. Method
Is the methodology documented and reproducible?
5 = open-source or detailed paper · 0 = "proprietary AI"
4. API
Programmatic access for developers?
5 = full REST + SDK + docs · 0 = HTML scraping
5. Price
Pricing visible before you contact sales?
5 = tiered pricing published · 0 = "contact us"

Why this index exists

There's no shortage of sites selling sports predictions. There's a chronic shortage of sites willing to tell you how accurate they actually are. We built this scorecard because when we went looking for a benchmark to beat, nothing existed. So we made one.

Where does ZenHodl stand? Near the top by design. We publish Expected Calibration Error per sport (4.39% on 5,345 NCAAMB games), keep every trade on /results, and document our methodology in our blog. We don't score ourselves 5/5 on methodology because we haven't open-sourced the training code — that's honest about where we're not yet.

This index is updated monthly. If you think a score is wrong, tell us — we'll re-verify.

Methodology: Scores are manually curated based on publicly visible homepage / methodology / pricing pages as of the last-updated date. Each competitor is re-verified at least monthly. We do not score internal / commercial claims we can't independently verify. If a source changes materially, we update the score and note the change.
See ZenHodl's pricing →

7-day free trial · no credit card · cancel anytime