Brighton
vs
Arsenal
Premier League prediction
Our model says: Brighton 1–0 Arsenal
The model makes it 38% Brighton, 31% draw, 31% Arsenal — fair odds of 2.63, 3.23 and 3.23. Fair odds are simply 100 ÷ the probability; they are the model's own number, not a bookmaker's price.
Most likely scoreline: 1-0.
Expected goals: Brighton 1.22, Arsenal 1.01.
Both teams to score: 46%. Over 2.5 goals: 39%, under 2.5: 61%.
Model confidence: Low.
Published · updated
Live win probability
From kick-offThese update every few seconds once the match kicks off, as the model re-reads the score, the clock and any red cards. The second figure is fair odds — 100 ÷ probability, the price with no margin in it.
Model insights: Brighton vs Arsenal
Every scoreline the model considered
| 0 | 1 | 2 | 3 | 4 | 5 | |
|---|---|---|---|---|---|---|
| 0 | 11 | 10 | 5 | 2 | ||
| 1 | 12 | 14 | 7 | 2 | ||
| 2 | 8 | 8 | 4 | 1 | ||
| 3 | 3 | 3 | 2 | |||
| 4 | 1 | |||||
| 5 |
Each cell is one exact result, shaded against the likeliest one; figures below 1% are left blank rather than rounded to zero. Blue cells are Brighton wins, grey are draws, red are Arsenal wins — the three shaded areas ARE the 1/X/2 split above, which is the sum of the cells in each. The most likely scoreline is simply the darkest cell inside whichever area the model favours.
Has the model earned this number?
It puts Brighton at 38% here. Across 2437 settled matches, 1728 forecasts have landed in the 30–40% band; those outcomes actually happened 33.4% of the time, against an average forecast of 33.7%. In this range the two line up, so the figure above can be read literally.
Every settled prediction on this site is scored against an uninformed baseline, band by band, and published whether or not it flatters the model — see the full record.
Form going into Brighton vs Arsenal
Brighton
- W5-0away to Coventry13 September 2026
- D1-1Leeds5 September 2026
- L3-4away to Chelsea30 August 2026
- W4-0Aston Villa23 August 2026
Arsenal
- W2-0away to Sunderland12 September 2026
- W2-1Chelsea6 September 2026
- W1-0away to Aston Villa31 August 2026
- W3-0Coventry21 August 2026
Up to 5 matches before kick-off, most recent first. The model works from each side's rolling expected-goals ratings rather than from these results directly, so read them as context — how the ratings are built.
Premier League table
| # | Team | P | W | D | L | GF | GA | GD | Pts |
|---|---|---|---|---|---|---|---|---|---|
| 5 | Brighton | 4 | 2 | 1 | 1 | 13 | 5 | +8 | 7 |
| 1 | Arsenal | 4 | 4 | 0 | 0 | 8 | 1 | +7 | 12 |
Where the two sides stand. Full table
Head-to-head: Brighton vs Arsenal
- 4 March 2026Brighton 0–1 ArsenalPremier League
- 27 December 2025Arsenal 2–1 BrightonPremier League
- 29 October 2025Arsenal 2–0 BrightonLeague Cup
- 4 January 2025Brighton 1–1 ArsenalPremier League
- 31 August 2024Arsenal 1–1 BrightonPremier League
- 6 April 2024Brighton 0–3 ArsenalPremier League
Leading scorers: Brighton and Arsenal
Brighton
- M. Yalcouyé2 goals
Arsenal
- B. Saka3 goals
- M. Ødegaard2 goals
- K. Havertz2 goals
Top 3 by league goals this season. Player availability is not part of the model — injuries and suspensions are a planned improvement.
Two sides the ratings cannot separate
Brighton carry a model rating of 7.09 against 7.16 for Arsenal. The scale is anchored so that an average side in one of Europe's big five leagues sits at 6.85, and it is adjusted for the strength of each team's league, so the two numbers are comparable even across borders.
A gap that small is inside the noise of the rating itself — treat the two as level.
What the model expects
Under the hood the model expects 1.22 goals for Brighton and 1.01 for Arsenal. Those two numbers, not the scoreline, are what the model actually estimates; everything else is derived from them.
Brighton rate 1.21 in attack and 0.75 in defence, where 1 is league average and a lower defensive number is better; Arsenal rate 1.12 and 0.62.
Where the model differs from the table
The table and the model disagree here: the standings favour Arsenal, while our numbers lean the other way. The model weights recent expected goals rather than results already banked, so it moves before the table does.
How this was produced
Publicly tracked record so far: 1151 correct results out of 2437 settled predictions (47%), with 230 exact scorelines (9%). That log is updated automatically after every match and is never edited.
Full method: how the model works.
From the first whistle this page keeps going: the win probabilities at the top are recalculated as the match plays out, reading the score, the clock and any sendings-off. The same model, asked how many goals are left rather than how many there will be.
Team comparison
Bars show each side's share of the two-team total, based on the model's attack/defence ratings and expected goals for this fixture.
Why the model favours this side
The model gives Brighton the highest probability at 38%, based on each side's rolling attack and defence ratings estimated from recent match data. The model projects 1.22 expected goals for Brighton against 1.01 for Arsenal. Brighton's attack/defence rating is 1.21/0.75 versus the league average (1.00 = average), compared with 1.12/0.62 for Arsenal.