Sunday 6 Sept, 16:30 · engine xGB Core v1 · graded — published before kickoff, never edited
Full time
2–1✓ called — the ARS win we priced at 63% · RPS 0.080
The claim — frozen at kickoff

Arsenal

99Index81Attack99Defense
WLWWW
63%ARS WIN
2–0
Most likely score

Chelsea

54Index64Attack44Defense
WLDLW
ARSENAL 63%DRAW 22%CHELSEA 15%
FT 2–1 — the model called it (RPS 0.080). Graded 2026-09-06 · permanent record at /model.
Over 2.5 goals
58%
Both teams score
54%
Expected goals
2.1 · 0.9
Head to head · 24 league meetings since 2014/15
ARS 107 drawn7 CHE
2025/26ARS2–1CHE2026-03-01
2025/26CHE1–1ARS2025-11-30
2024/25ARS1–0CHE2025-03-16
2024/25CHE1–1ARS2024-11-10
2023/24ARS5–0CHE2024-04-23
Arsenal — projected scorers
Kai Havertz37%17% astGOAL
Bukayo Saka20%26% ast—
Riccardo Calafiori9%16% ast—
Viktor Gyokeres20%4% ast—
Gabriel15%1% ast—
Martin Odegaard3%12% astGOAL
Chelsea — projected scorers
Cole Palmer17%10% ast—
Enzo Fernández9%12% ast—
João Pedro14%5% ast—
Romeo Lavia6%3% ast—
Malo Gusto0%8% ast—
Jorrel Hato0%7% astAST

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.