Friday 21 Aug, 20:00 · engine xGB Core v1 · graded — published before kickoff, never edited
Full time
30✓ called — the ARS win we priced at 83% · RPS 0.015
The claim — frozen at kickoff

Arsenal

99Index77Attack99Defense
WWWWW
83%ARS WIN
20
Most likely score

Coventry City

33Index3Attack73Defense
LL
ARSENAL 83%DRAW 13%COVENTRY 4%
FT 30 — the model called it (RPS 0.015). Graded 2026-08-22 · permanent record at /model.
Over 2.5 goals
65%
Both teams score
41%
Expected goals
2.8 · 0.6
Arsenal — projected scorers
Viktor Gyokeres46%11% ast
Kai Havertz38%16% astGOAL
Bukayo Saka7%27% astGOAL
Gabriel18%11% ast
Declan Rice2%25% ast
Noni Madueke4%20% ast
Coventry — projected scorers

No qualified projections yet.

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

Thin evidence: the engine has seen little recent top-flight data on Coventry — this assessment leans on conservative defaults more than usual.

Engine internals are proprietary. The complete performance record — including every miss — is public on the record.