Agent Lab — a live forecast exhibit · Applied AI
← Schedule
Group G · Matchday 16 · 2026-06-26

New Zealand vs Belgium

Vancouver, Canada · neutral venue

Most likely scoreline
0–1 15.1%
8.5%
NZL win
18.4%
Draw
72.5%
BEL win
Top scorelines
  • 0–1 15.1%
  • 0–2 14.1%
  • 0–3 10.2%
  • 0–0 9.7%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
NZL win
8.0%
Draw
19.0%
BEL win
73.0%

The model already prices Belgium as heavy favourites (73%) and no supplied intel contradicts that. Belgium's recent form (WWDWW) and star-studded squad (De Bruyne, Lukaku, Tielemans) dwarf New Zealand's modest attack (Wood, Barbarouses) and poor form (LLWLL). The lack of head-to-head or injury news leaves the prior intact. I keep the model's probabilities unchanged. Belgium's expected goals (2.24) and New Zealand's (0.46) suggest a low-scoring match for the underdog. The most likely scorelines are 0-1, 0-2, 0-3, consistent with a Belgium clean sheet. New Zealand's best hope is a 0-0 draw (10%) or a 1-1 (7%) if they catch Belgium off guard.

What the agent weighed
What the agent checked on the web
Searched tavily for NZL · BEL — 6 sources kept
Agent scorelines
generated 2026-06-11
Last 5 — NZL
+0.00 pts/match vs model expectation · opp. avg #45
  • FIN #70 -1.3
  • CHI #28 +2.2
  • HAI #97 -1.3
  • ENG #4 -0.2
  • IRN #26 +0.3
GF / GA last 10: 9 / 19
Last 5 — BEL
+0.20 pts/match vs model expectation · opp. avg #31
  • USA #35 +1.2
  • MEX #21 -0.8
  • CRO #15 +1.7
  • TUN #48 +0.7
  • EGY #37 -0.9
GF / GA last 10: 32 / 7
Head-to-head (last 5)

No prior meetings in the dataset.

▸ Full score grid (7×7)
P(home goals × away goals), %
0
1
2
3
4
5
6
0
9.7
15.1
14.1
10.2
6.4
3.6
1.9
1
4.3
6.7
6.3
4.6
2.8
1.6
0.8
2
1.2
1.8
1.7
1.2
0.8
0.4
0.2
3
0.2
0.4
0.4
0.3
0.2
0.1
0.0
4
0.0
0.1
0.1
0.0
0.0
0.0
0.0
5
0.0
0.0
0.0
0.0
0.0
0.0
0.0
6
0.0
0.0
0.0
0.0
0.0
0.0
0.0

Rows = NZL goals; columns = BEL 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)
0.49
NZL
2.26
BEL

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.