Saturday 31 Oct, 15:00 · engine xGB Core v1 · doesn't know lineups or injuries

Manchester City

87Index89Attack78Defense
WWWWW
51%MCI WIN
2–1
Likeliest MCI win · 10%

Brighton & Hove Albion

70Index67Attack69Defense
WWWDL
MAN CITY 51%DRAW 24%BRIGHTON 25%
Over 2.5 goals
62%
Both teams score
63%
Expected goals
1.9 · 1.3
Why
Head to head · 18 league meetings since 2017/18
MCI 123 drawn3 BHA
2025/26MCI1–1BHA2026-01-07
2025/26BHA2–1MCI2025-08-31
2024/25MCI2–2BHA2025-03-15
2024/25BHA2–1MCI2024-11-09
2023/24BHA0–4MCI2024-04-25
Man City — projected scorers
Erling Haaland47%15% ast88'
Mathis Cherki24%31% ast76'
Antoine Semenyo13%24% ast90'
Josko Gvardiol6%19% ast74'
Phil Foden10%14% ast27'
Marc Guehi8%7% ast90'
Brighton — projected scorers
Maxim De Cuyper13%25% ast84'
Pascal Groß13%22% ast90'
Diego Gómez12%10% ast88'
Charalampos Kostoulas14%4% ast79'
Ferdi Kadioglu1%13% ast85'
Malick Yalcouyé6%7% ast51'

Projections assume recent minutes patterns — the model doesn’t know lineups.

What the grid implies
Goals
Over 1.5 goals84%
Over 2.5 goals62%
Over 3.5 goals40%
Both teams score63%
Double chance
MCI or draw75%
Draw or BHA49%
MCI or BHAno draw76%
Draw no bet
MCIstake returned on a draw68%
BHA33%
Clean sheets
MCI clean sheet27%
BHA clean sheet15%

Model probabilities, not odds and not advice. Our own leaderboard shows no model here beats the closing market once the bookmaker’s margin is paid.

Every scoreline, priced — tap a cell
MCI↓ BHA→012345
0
1
2
3
4
5
Darker green = likelier. Rows are MCI goals, columns BHA. Scores of six or more each way carry the remaining probability.

Price held steady since first assessment (2026-10-17) — reassessed after every played match, frozen at kickoff.

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.