Saturday 12 Sept, 20:00 · engine xGB Core v1 · graded — published before kickoff, never edited
Full time
0–2✓ called — the ARS win we priced at 60% · RPS 0.090
The claim — frozen at kickoff

Sunderland

39Index36Attack44Defense
LLLDW
60%ARS WIN
0–1
Most likely score

Arsenal

99Index81Attack99Defense
WLWWW
SUNDERLAND 14%DRAW 26%ARSENAL 60%
FT 0–2 — the model called it (RPS 0.090). Graded 2026-09-13 · permanent record at /model.
Over 2.5 goals
46%
Both teams score
45%
Expected goals
0.8 · 1.8
Head to head · 8 league meetings since 2014/15
SUN 03 drawn5 ARS
2025/26ARS3–0SUN2026-02-07
2025/26SUN2–2ARS2025-11-08
2016/17ARS2–0SUN2017-05-16
2016/17SUN1–4ARS2016-10-29
2015/16SUN0–0ARS2016-04-24
Sunderland — projected scorers
Enzo Le Fée10%27% ast—
Brian Brobbey16%5% ast—
Noah Sadiki9%5% ast—
Trai Hume3%10% ast—
Wilson Isidor12%0% ast—
Granit Xhaka2%7% ast—
Arsenal — projected scorers
Kai Havertz36%19% ast—
Bukayo Saka19%22% astGOAL
Martin Odegaard7%20% ast—
Riccardo Calafiori11%13% ast—
Viktor Gyokeres17%3% ast—
Gabriel16%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.