Model accuracy, published in the open.
Every prediction model claims it works. This page is where FPL Apex proves it — validated benchmarks against the leading paid tools, a full-season tracker, and a live forward test where predictions are locked before kick-off and scored after. Wins and losses both published.
How Apex compares to the leading paid tools
FPL Review and Solio are the benchmark paid projection tools in the FPL community — the strongest competition we know of. Here is where Apex stands against them, measured on the same players, the same gameweeks, the same data. MAE is mean absolute error: the average size of the miss. Lower is better.
Paired difference +0.038 points, 95% CI [−0.004, +0.085]. The interval spans zero: statistically indistinguishable. We do not claim to beat Review on points — we claim to match a leading paid tool, for free.
Review is genuinely better at predicting minutes. The gap is concentrated in team-news rows — late injury and lineup calls — which is exactly what the 2026/27 news pipeline is built to close. Published because honest beats flattering.
On double-gameweek projections, Apex is the most accurate of the three tools tested. Its second-leg dampener cut the bias on headline double-GW players from +1.47 to +0.63 points per player.
Validated 2026-06-10 · 1,707 player-gameweek sample (Apex_vs_Review_test_v2.xlsx) · uncertainty via cluster bootstrap, 10,000 resamples by gameweek.
2025/26 — match prediction accuracy
Every matchweek of the 2025/26 Premier League season, the model's match goal predictions were scored against what actually happened. The number tracked is MAE — the average size of the miss, in goals per match. Lower is better.
Tracking begins at matchweek 3 — the model holds off until the new season has given it real in-season data to work with.
Live forward test — 2026/27
From GW1 of 2026/27, projections from all three tools are snapshotted before each deadline and scored after the gameweek finishes. Point-in-time honest: predictions are locked in advance, never recomputed, and the results land here weekly — wins and losses both. Each row is the MAE against actual FPL points, on the same set of players.
| GW | Apex MAE | Review MAE | Solio MAE | Closest |
|---|---|---|---|---|
| The forward test starts at GW1 of 2026/27. One row per scored gameweek will appear here — whichever way it goes. | ||||
Scored by scripts/forward_test/forward_log.py — snapshot before the deadline, score after the final whistle, publish either way.
How to read this page
Scoreline vs xG
Most people judge football by results. The scoreline tells you what happened; xG — expected goals — tells you what should have happened, based on the quality of chances created. The difference is luck. Apex is built on xG because performance predicts the future better than results do.
Why MAE
MAE — mean absolute error — is the average size of the miss. Predict 5 points, the player scores 7: that's an error of 2. Average it over every player, every week. Lower is better; zero is impossible. It's the fairest single number because a few lucky calls can't game it.
Why point-in-time matters
Anyone can show you a backtest that works — built after the results were known. A point-in-time record can't be massaged: the prediction is locked before kick-off, then scored against what actually happened. That's the standard betting markets are held to, and the standard this page holds Apex to.