Saturday 5 Dec, 12:30 · engine xGB Core v1 · doesn't know lineups or injuries

Chelsea

57Index63Attack50Defense
LWLWW
39%CHE WIN
2–1
Likeliest CHE win · 9%

Liverpool

65Index63Attack64Defense
WLWWL
CHELSEA 39%DRAW 26%LIVERPOOL 36%
Over 2.5 goals
60%
Both teams score
63%
Expected goals
1.6 · 1.5
Why
Head to head · 24 league meetings since 2014/15
CHE 511 drawn8 LIV
2025/26LIV1–1CHE2026-05-09
2025/26CHE2–1LIV2025-10-04
2024/25CHE3–1LIV2025-05-04
2024/25LIV2–1CHE2024-10-20
2023/24LIV4–1CHE2024-01-31
Chelsea — projected scorers
Cole Palmer27%34% ast88'
Morgan Rogers24%19% ast89'
João Pedro14%4% ast33'
Estêvão8%6% ast23'
Maxence Lacroix5%7% ast72'
Pep Chavarría0%10% ast39'
Liverpool — projected scorers
Alexander Isak28%4% ast68'
Florian Wirtz17%18% ast77'
Dominik Szoboszlai8%19% ast40'
Bradley Barcola11%15% ast81'
Cody Gakpo8%14% ast42'
Alexis Mac Allister9%7% ast78'

Projections assume recent minutes patterns — the model doesn’t know lineups.

What the grid implies
Goals
Over 1.5 goals83%
Over 2.5 goals60%
Over 3.5 goals38%
Both teams score63%
Double chance
CHE or draw64%
Draw or LIV61%
CHE or LIVno draw74%
Draw no bet
CHEstake returned on a draw52%
LIV48%
Clean sheets
CHE clean sheet22%
LIV clean sheet20%

Model probabilities, not odds and not advice. Our own leaderboard shows no model here beats the closing market once the bookmaker’s margin is paid.

Every scoreline, priced — tap a cell
CHE↓ LIV→012345
0
1
2
3
4
5
Darker green = likelier. Rows are CHE goals, columns LIV. Scores of six or more each way carry the remaining probability.

Price held steady since first assessment (2026-11-21) — reassessed after every played match, frozen at kickoff.

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.