Sunday 30 Aug, 14:00 · engine xGB Core v1 · graded — published before kickoff, never edited
Full time
4–3✓ called — the CHE win we priced at 43% · RPS 0.216
The claim — frozen at kickoff

Chelsea

61Index68Attack49Defense
WWLWD
43%CHE WIN
1–1
Most likely score

Brighton & Hove Albion

61Index56Attack61Defense
LWLLW
CHELSEA 43%DRAW 25%BRIGHTON 32%
FT 4–3 — the model called it (RPS 0.216). Graded 2026-08-30 · permanent record at /model.
Over 2.5 goals
63%
Both teams score
65%
Expected goals
1.8 · 1.5
Head to head · 18 league meetings since 2017/18
CHE 94 drawn5 BHA
2025/26BHA3–0CHE2026-04-21
2025/26CHE1–3BHA2025-09-27
2024/25BHA3–0CHE2025-02-14
2024/25CHE4–2BHA2024-09-28
2023/24BHA1–2CHE2024-05-15
Chelsea — projected scorers
Cole Palmer32%22% astGOAL
Enzo Fernández21%27% ast—
João Pedro25%9% astGOAL
Malo Gusto1%16% ast—
Romeo Lavia7%6% astGOAL
Moisés Caicedo3%9% ast—
Brighton — projected scorers
Jack Hinshelwood35%15% ast—
Maxim De Cuyper16%26% ast—
Pascal Groß5%20% astGOAL
Yankuba Minteh11%14% ast—
Georginio Rutter5%19% ast—
Diego Gómez8%7% 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.