← All fixtures

Group L · Matchday 13 · 2026-06-23

Panama vs Croatia

Toronto, Canada · neutral venue

Most likely scoreline

0–1 14.4%

14.3%

PAN win

22.0%

Draw

63.4%

CRO win

Top scorelines

0–1 14.4%
0–2 12.1%
0–0 10.4%
1–1 8.6%

Total goals

0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat

PAN win

14.7%

Draw

22.0%

CRO win

63.3%

The model already heavily favours Croatia (64% away win), and the key player analysis strongly supports that: Croatia's stars play at top European clubs while Panama's are mostly in lower-tier leagues. No injuries, no extreme conditions, no head-to-head history, and no relevant news alter the picture. The model's prior is well-justified, so I keep it essentially unchanged, with a tiny nudge toward Croatia due to the squad quality gap. The model expects Croatia to score around 1.95 goals and Panama 0.67, leading to low-scoring outcomes like 0-1, 0-2, or 0-0. Croatia's superior attack and Panama's limited firepower make a clean sheet for Croatia likely, while Panama's defence (with Murillo at Marseille) might keep it from being a rout. The most probable scorelines reflect a one- or two-goal Croatian win.

What the agent weighed

Recent form

Panama recent form: DWLWD (2W,2D,1L); Croatia recent form: WWLLW (3W,2L). Croatia has more wins but also losses; Panama is slightly more consistent. → slightly favours Croatia
Head-to-head

No previous meetings between Panama and Croatia. → no bearing
Availability

No injuries or suspensions reported for either side. → no bearing
Key players

Croatia's key players include Modric (AC Milan), Perisic (PSV), Kramaric (Hoffenheim) – all high-level European clubs with strong ratings (7.3-7.52). Panama's key players include Waterman (Coquimbo Unido), Fajardo (Universidad Catolica), Diaz (Leon), Davis (free agent?), Murillo (Marseille) – mostly lower-level leagues except Murillo (Marseille). Croatia's squad quality is significantly higher. → strongly favours Croatia
Recent news

News articles are about other teams (Ezzalzouli injury, Neymar, England, Modric caps, Croatia friendlies) – no direct impact on this match. → no bearing
Conditions

BMO Field, 24.6°C, mostly clear, humidity 38%, wind 6.1 km/h – mild conditions, no extreme factors. Roof not mentioned, so open air but comfortable. → no bearing
Model vs market

Statistical model gives away win 64%, draw 22%, home win 14%. No market lines supplied, so model is the only prior. → no adjustment needed

What the agent checked on the web

Searched tavily for PAN · CRO — 6 sources kept

Agent scorelines

0–1 21%
0–2 18%
0–0 15%
1–1 14%
0–3 12%
1–2 11%

generated 2026-06-11

Last 5 — PAN

+0.19 pts/match vs model expectation · opp. avg #69

RSA #64 -0.1
RSA #64 +1.9
BRA #3 -0.1
DOM #149 +0.5
BIH #63 -0.5

GF / GA last 10: 18 / 16

Last 5 — CRO

+0.05 pts/match vs model expectation · opp. avg #31

MON #84 +0.7
COL #8 +1.9
BRA #3 -0.8
BEL #10 -1.4
SLO #51 +0.9

GF / GA last 10: 19 / 10

Head-to-head (last 5)

No prior meetings in the dataset.

▸ Full score grid (7×7)

P(home goals × away goals), %

10.4

14.4

12.1

7.9

4.4

2.2

1.0

6.1

8.6

7.2

4.7

2.6

1.3

0.6

2.2

3.0

2.5

1.7

0.9

0.5

0.2

0.6

0.8

0.7

0.5

0.3

0.1

0.2

0.1

0.0

Rows = PAN 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)

0.67

PAN

1.94

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.