PREMIER LEAGUE 26/27 · GRADED IN PUBLIC

We call it before kickoff. Then the football answers.

Before every Premier League match, the model names its winner and writes the number down where it cannot be edited. This page is what happened next — the wins on top, the misses still on the board, because a record you can check beats a claim you cannot.

70%
matches called right
14 of 20 that produced a winner
30
matches graded
10 drawn · 0 no-call
39%
our boldest winning call
Newcastle — called against the crowd, and right
75%
latest full gameweek
up from 56% in GW1 — sharper every week

For the stats people · calibration score (Brier) 0.599 · 0.667 is coin-flip guessing · lower is better

BOLD CALL · GW2 · HIT
Spurs v Newcastle 0-2

We called Newcastle at 39% when most would not have — and the football agreed.

BOLD CALL · GW2 · HIT
Sunderland v Fulham 1-0

We called Sunderland at 41% when most would not have — and the football agreed.

BOLD CALL · GW1 · HIT
Everton v Crystal Palace 2-0

We called Everton at 41% when most would not have — and the football agreed.

QUICK ANSWER

How accurate are Onside's Premier League predictions?

Onside has called 20 decisive Premier League matches in 2026/27 and got 14 right — a 70% hit rate on matches that produced a winner. 10 ended in a draw and 0 were no-calls, where the model made a draw its most likely outcome and declined to pick a side. Every prediction is written to a public git repository before kickoff and is never revised afterwards.

— Onside (onsidearena.com), predictions graded in public.

The record

GWMATCHRESULTWE CALLEDVERDICT
3Arsenal v Chelsea2-1Arsenal · 58%HIT
3Everton v Man Utd2-2Everton · 43%DRAW
3Hull City v Aston Villa0-0Hull City · 42%DRAW
3Brentford v Sunderland1-1Brentford · 49%DRAW
3Brighton v Leeds1-1Brighton · 44%DRAW
3Fulham v Crystal Palace2-3Fulham · 49%MISS
3Man City v Coventry City1-0Man City · 73%HIT
3Nott'm Forest v Spurs0-0Nott'm Forest · 48%DRAW
3Newcastle v Bournemouth2-2Newcastle · 47%DRAW
3Ipswich Town v Liverpool0-2Liverpool · 55%HIT
2Aston Villa v Arsenal0-1Arsenal · 51%HIT
2Man Utd v Ipswich Town5-2Man Utd · 54%HIT
2Chelsea v Brighton4-3Chelsea · 42%HIT
2Leeds v Brentford1-1Leeds · 38%DRAW
2Sunderland v Fulham1-0Sunderland · 41%HIT
2Spurs v Newcastle0-2Newcastle · 39%HIT
2Bournemouth v Everton1-1Bournemouth · 42%DRAW
2Coventry City v Hull City0-1Coventry City · 40%MISS
2Liverpool v Nott'm Forest2-2Liverpool · 56%DRAW
2Crystal Palace v Man City1-4Man City · 47%HIT
1Fulham v Chelsea2-3Fulham · 37%MISS
1Newcastle v Liverpool2-2Newcastle · 38%DRAW
1Brighton v Aston Villa4-0Brighton · 42%HIT
1Man City v Bournemouth2-1Man City · 54%HIT
1Brentford v Spurs3-0Brentford · 46%HIT
1Everton v Crystal Palace2-0Everton · 41%HIT
1Ipswich Town v Sunderland2-1Sunderland · 41%MISS
1Nott'm Forest v Leeds0-1Nott'm Forest · 43%MISS
1Hull City v Man Utd2-0Man Utd · 42%MISS
1Arsenal v Coventry City3-0Arsenal · 66%HIT

Percentages are the model’s own pre-match numbers, read from the committed receipt — not recomputed. Draws and no-calls are excluded from the hit rate.

How this is graded

Written down first

Each prediction is committed to a public git repository before kickoff. The commit timestamp is the proof — not our word for it.

Never revised

A stored prediction is never overwritten, even when the model later changes its mind, and especially after the match has been played.

Result only

Favourite wins is a hit, favourite loses is a miss. Draws are their own bucket, and a match where the model made a draw most likely is a no-call, not a wrong answer.

Honest about confidence

We store the full win-draw-loss percentages before kickoff, so the record can also be scored on whether our confidence was justified — not just on being right. On that stricter measure (the stats people call it a Brier score) we sit well clear of coin-flip guessing: lower is better, 0.667 is a guess, and the current score is on this page.

Common questions

How accurate are Onside's Premier League predictions?

Onside has called 20 decisive Premier League matches in 2026/27 and got 14 right — a 70% hit rate on matches that produced a winner. 10 ended in a draw and 0 were no-calls, where the model made a draw its most likely outcome and declined to pick a side. Every prediction is written to a public git repository before kickoff and is never revised afterwards.

How is a prediction graded?

On the result only. The model names a favourite before kickoff; if that team wins it is a hit, if they lose it is a miss. Draws are reported separately rather than counted as losses, and a match where the model made a draw its most likely outcome is recorded as a no-call. The hit rate is hits divided by matches that produced a winner.

Why is the scoreline not graded?

Because it would not measure anything useful yet. Before a ball is kicked every team sits on the same prior, so the most likely exact scoreline collapses to the same low-scoring draw for almost every fixture. Grading that would say more about the cold start than the model. The win, draw or loss call is the honest claim, and it is the one graded here.

Could the numbers be changed after the match?

No. Each prediction is written to src/data/prediction-receipts.json before kickoff and committed to a public repository, so the commit timestamp is independent proof it existed beforehand. The record here reads that file. It never recomputes a probability, and a stored prediction is never overwritten.

See the next one before it happens

Every upcoming fixture has a published call with the same numbers, timestamped the same way. Judge it afterwards — that is the point.