Agent Lab — a live forecast exhibit · Applied AI
← Schedule
Group L · Matchday 7 · 2026-06-17

England vs Croatia

Arlington, United States · neutral venue

Full time ENG 4–2 CRO
The agent called England (58%) — Better than the model call right

The forecast below is what the agent published before kickoff.

Most likely scoreline
1–0 15.2%
49.3%
ENG win
27.8%
Draw
22.9%
CRO win
Top scorelines
  • 1–0 15.2%
  • 0–0 14.0%
  • 1–1 10.4%
  • 2–0 9.9%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
ENG win
57.7%
Draw
25.0%
CRO win
17.3%

The model's 48% home win is a reasonable baseline, but the squad market value gap — England ranked 1st vs Croatia 16th, with a 3.5x value advantage — points to a talent edge the results-based model may not fully capture. England's recent under-performance against weak opponents is a mild concern, but head-to-head history (3 wins in last 5) and superior key-player quality (Bellingham, Foden, Kane) support a stronger lean. I raise England's win probability to 58%, trimming draw and away win accordingly. England's expected goals (1.33) and Croatia's (0.77) suggest a low-to-moderate scoring match. England's defensive solidity and Croatia's aging midfield (Modric 40) limit Croatia's chances. The most likely scorelines are 1-0 and 2-0, with 1-1 and 0-0 as draws. A 3-0 is possible given England's attacking depth but not the most probable.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 9 sources kept:
  • “England vs Croatia 2026-06-17 team news injuries suspensions” match · 3 hits
    Late fitness updates or suspensions could shift the balance.
  • “England squad 2026 June injuries” ENG · 3 hits
    Key player availability for England may be uncertain.
  • “Croatia squad 2026 June injuries” CRO · 3 hits
    Key player availability for Croatia may be uncertain.
Agent scorelines
generated 2026-06-17
Last 5 — ENG
-0.34 pts/match vs model expectation · opp. avg #50
  • ALB #62 +0.8
  • URU #12 -0.9
  • JPN #18 -2.1
  • NZL #94 +0.2
  • COS #66 +0.3
GF / GA last 10: 24 / 2
Last 5 — CRO
+0.08 pts/match vs model expectation · opp. avg #31
  • MON #85 +0.7
  • COL #8 +1.9
  • BRA #3 -0.8
  • BEL #10 -1.4
  • SLO #50 +0.9
GF / GA last 10: 19 / 10
Head-to-head (last 5)
  • 2021-06-13 England 1–0 Croatia
  • 2018-11-18 England 2–1 Croatia
  • 2018-10-12 Croatia 0–0 England
  • 2018-07-11 Croatia 2–1 England
  • 2009-09-09 England 5–1 Croatia
▸ Full score grid (7×7)
P(home goals × away goals), %
0
1
2
3
4
5
6
0
14.0
9.6
4.0
1.3
0.4
0.1
0.0
1
15.2
10.4
4.3
1.4
0.4
0.1
0.0
2
9.9
6.8
2.8
0.9
0.2
0.1
0.0
3
5.1
3.5
1.4
0.5
0.1
0.0
0.0
4
2.2
1.5
0.6
0.2
0.1
0.0
0.0
5
0.9
0.6
0.2
0.1
0.0
0.0
0.0
6
0.3
0.2
0.1
0.0
0.0
0.0
0.0

Rows = ENG goals; columns = CRO goals. Above-diagonal cells are home wins; diagonal = draws; below = away wins. Truncated at 6 — the joint mass past that is < 1 %.

Expected goals (Poisson rate, λ)
1.39
ENG
0.8
CRO

Independent-Poisson rates. W/D/L and the score grid integrate the full 13×13 joint under these two parameters.

News context — injuries, suspensions, projected XI — is not part of the model, which sees only past results.