Sunday 20 Sept, 14:00 · engine xGB Core v1 · graded — published before kickoff, never edited
Full time
5–3✓ called — the MCI win we priced at 66% · RPS 0.066
The claim — frozen at kickoff

Manchester City

84Index88Attack72Defense
LLLWW
66%MCI WIN
2–0
Most likely score

Sunderland

35Index35Attack38Defense
WLDLL
MAN CITY 66%DRAW 21%SUNDERLAND 13%
FT 5–3 — the model called it (RPS 0.066). Graded 2026-09-22 · permanent record at /model.
Over 2.5 goals
60%
Both teams score
54%
Expected goals
2.2 · 0.9
Head to head · 8 league meetings since 2014/15
MCI 71 drawn0 SUN
2025/26SUN0–0MCI2026-01-01
2025/26MCI3–0SUN2025-12-06
2016/17SUN0–2MCI2017-03-05
2016/17MCI2–1SUN2016-08-13
2015/16SUN0–1MCI2016-02-02
Man City — projected scorers
Erling Haaland46%13% astGOAL
Mathis Cherki21%39% astGOAL
Phil Foden24%34% ast—
Antoine Semenyo15%25% astGOAL
Marc Guehi7%7% astAST
Nico O'Reilly8%1% ast—
Sunderland — projected scorers
Enzo Le Fée15%30% astAST
Brian Brobbey16%7% astGOAL
Noah Sadiki10%6% ast—
Wilson Isidor14%0% ast—
Granit Xhaka1%12% ast—
Trai Hume3%8% 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.