Agent Lab — a live forecast exhibit · Applied AI
← All fixtures
Group A · Matchday 14 · 2026-06-24

Mexico vs Czech Republic

Mexico City, Mexico

Most likely scoreline
1–0 12.9%
50.5%
MEX win
25.3%
Draw
24.1%
CZE win
Top scorelines
  • 1–0 12.9%
  • 0–0 10.8%
  • 1–1 10.2%
  • 2–0 9.3%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
MEX win
55.0%
Draw
25.0%
CZE win
20.0%

The model's prior (49% home win) already gives Mexico a slight edge, but the supplied intel reveals a key factor not fully priced in: the 2240m altitude of Estadio Azteca. Mexico is acclimated to high-altitude conditions, while Czech Republic is not, which historically provides a meaningful home advantage. I increase Mexico's win probability to 55%, drawing from draw (25%) and away (20%) to reflect this environmental edge. No other factor (form, head-to-head, injuries, key players, news) justifies a further move. The model expects a low-scoring match (Mexico 1.54 xG, Czech 0.95 xG). The altitude may suppress Czech attacking output further, making 1-0 the most likely scoreline. I keep the scoreline distribution close to the model's top lines, slightly shifting probability from 0-0 and 1-1 toward 1-0 and 2-0 to account for Mexico's altitude advantage.

What the agent weighed
What the agent checked on the web
Searched tavily for MEX · CZE — 6 sources kept
Agent scorelines
generated 2026-06-11
Last 5 — MEX
+1.06 pts/match vs model expectation · opp. avg #38
  • BEL #10 +0.0
  • GHA #59 +0.9
  • AUS #28 +1.6
  • SER #31 +1.2
  • RSA #64 +0.9
GF / GA last 10: 18 / 4
Last 5 — CZE
-0.13 pts/match vs model expectation · opp. avg #51
  • REP #50 -0.7
  • DEN #14 -0.1
  • KOS #56 +1.1
  • GUA #100 +0.5
  • KOR #37 -1.3
GF / GA last 10: 19 / 11
Head-to-head (last 5)
  • 2000-02-08 Mexico 1–2 Czech Republic
▸ Full score grid (7×7)
P(home goals × away goals), %
0
1
2
3
4
5
6
0
10.8
8.5
4.0
1.5
0.5
0.1
0.0
1
12.9
10.2
4.8
1.8
0.6
0.2
0.0
2
9.3
7.3
3.5
1.3
0.4
0.1
0.0
3
5.2
4.1
1.9
0.7
0.2
0.1
0.0
4
2.5
2.0
0.9
0.3
0.1
0.0
0.0
5
1.1
0.8
0.4
0.1
0.0
0.0
0.0
6
0.4
0.3
0.2
0.1
0.0
0.0
0.0

Rows = MEX goals; columns = CZE 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)
1.58
MEX
0.93
CZE

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.