Saturday 19 Sept, 15:00 · engine xGB Core v1 · graded — published before kickoff, never edited
Full time
3–0✗ missed — the BHA win we priced at 25% · RPS 0.395
The claim — frozen at kickoff

Brighton & Hove Albion

69Index68Attack67Defense
WWLWW
47%ARS WIN
1–1
Most likely score

Arsenal

95Index77Attack99Defense
WWWWW
BRIGHTON 25%DRAW 28%ARSENAL 47%
FT 3–0 — the model missed (RPS 0.395). Graded 2026-09-19 · permanent record at /model.
Over 2.5 goals
51%
Both teams score
55%
Expected goals
1.1 · 1.6
Head to head · 18 league meetings since 2017/18
BHA 55 drawn8 ARS
2025/26BHA0–1ARS2026-03-04
2025/26ARS2–1BHA2025-12-27
2024/25BHA1–1ARS2025-01-04
2024/25ARS1–1BHA2024-08-31
2023/24BHA0–3ARS2024-04-06
Brighton — projected scorers
Maxim De Cuyper11%27% ast—
Pascal Groß11%19% astGOAL
Charalampos Kostoulas11%6% astGOAL
Diego Gómez9%8% astAST
Georginio Rutter2%9% ast—
Ferdi Kadioglu3%7% ast—
Arsenal — projected scorers
Kai Havertz29%18% ast—
Bukayo Saka25%20% ast—
Martin Odegaard7%23% ast—
Riccardo Calafiori12%12% ast—
Viktor Gyokeres15%3% ast—
Gabriel15%1% ast—

These are the projections exactly as published before kickoff — never edited after the fact.

What this is built from
The engine weighs
  • Chance quality created and conceded, both sides, all season
  • Opponent strength and venue
  • Recent play, weighted toward now
It cannot see
  • Confirmed lineups
  • Injuries and suspensions
  • Cup rotation plans

Engine internals are proprietary. The complete performance record — including every miss — is public on the record.