Saturday 10 Oct, 12:30 · engine xGB Core v1 · graded — published before kickoff, never edited
Full time
2–1✓ called — the ARS win we priced at 61% · RPS 0.089
The claim — frozen at kickoff

Arsenal

95Index77Attack99Defense
WWWWW
61%ARS WIN
1–1
Most likely score

Leeds United

54Index46Attack62Defense
WLDDL
ARSENAL 61%DRAW 24%LEEDS 15%
FT 2–1 — the model called it (RPS 0.089). Graded 2026-10-10 · permanent record at /model.
Over 2.5 goals
53%
Both teams score
51%
Expected goals
1.9 · 0.9
Head to head · 8 league meetings since 2020/21
ARS 71 drawn0 LEE
2025/26LEE0–4ARS2026-01-31
2025/26ARS5–0LEE2025-08-23
2022/23ARS4–1LEE2023-04-01
2022/23LEE0–1ARS2022-10-16
2021/22ARS2–1LEE2022-05-08
Arsenal — projected scorers
Bukayo Saka41%30% ast—
Kai Havertz26%23% ast—
Martin Odegaard11%26% ast—
Riccardo Calafiori16%17% astGOAL
Gabriel21%1% ast—
Christos Tzolis2%12% ast—
Leeds — projected scorers
Dominic Calvert-Lewin29%2% ast—
James Justin2%13% astGOAL
Jayden Bogle7%6% ast—
Anton Stach8%5% ast—
Ao Tanaka4%6% ast—
Noah Okafor5%2% 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.