Agent Lab — a live forecast exhibit · Applied AI
← All fixtures
Group A · Matchday 8 · 2026-06-18

Mexico vs South Korea

Zapopan, Mexico

Most likely scoreline
1–0 13.8%
48.2%
MEX win
26.8%
Draw
25.0%
KOR win
Top scorelines
  • 1–0 13.8%
  • 0–0 12.4%
  • 1–1 10.5%
  • 0–1 9.4%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
MEX win
50.0%
Draw
27.0%
KOR win
23.0%

The model's prior (48% home win) is already reasonable, but the supplied intel strengthens Mexico's case slightly: recent form shows Mexico on a three-win streak, head-to-head history favours Mexico (3W-1D-1L), and key player analysis indicates Mexico has superior depth (Jimenez, Alvarez, Montes) versus South Korea's reliance on Son. The altitude (1551m) adds a minor home advantage. I nudge Mexico's win probability up to 50% and reduce away win to 23%, keeping draw at 27% as both teams are solid. Mexico's expected goals (1.44) and South Korea's (0.90) from the model suggest a low-scoring match. Mexico's defensive solidity (Montes) and South Korea's attacking threat (Son) make 1-0 and 2-1 the most likely scorelines. The historical head-to-head average of 2.4 goals per game supports a modest total, but I keep the top scorelines close to the model's distribution.

What the agent weighed
What the agent checked on the web
Searched tavily for MEX · KOR — 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 — KOR
+0.53 pts/match vs model expectation · opp. avg #75
  • CIV #32 -1.3
  • AUT #22 -1.0
  • TRI #141 +0.5
  • EL #139 +0.4
  • CZE #40 +1.6
GF / GA last 10: 15 / 13
Head-to-head (last 5)
  • 2025-09-09 Mexico 2–2 South Korea
  • 2020-11-14 Mexico 3–2 South Korea
  • 2018-06-23 South Korea 1–2 Mexico
  • 2014-01-29 Mexico 4–0 South Korea
  • 2006-02-15 Mexico 0–1 South Korea
▸ Full score grid (7×7)
P(home goals × away goals), %
0
1
2
3
4
5
6
0
12.4
9.4
4.3
1.5
0.5
0.1
0.0
1
13.8
10.5
4.8
1.7
0.5
0.1
0.0
2
9.3
7.0
3.2
1.1
0.3
0.1
0.0
3
4.8
3.7
1.7
0.6
0.2
0.0
0.0
4
2.2
1.6
0.8
0.3
0.1
0.0
0.0
5
0.9
0.7
0.3
0.1
0.0
0.0
0.0
6
0.3
0.2
0.1
0.0
0.0
0.0
0.0

Rows = MEX goals; columns = KOR 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)
1.44
MEX
0.9
KOR

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.