Agent Lab — a live forecast exhibit · Applied AI
← All fixtures
Group E · Matchday 15 · 2026-06-25

Curaçao vs Ivory Coast

Philadelphia, United States · neutral venue

Most likely scoreline
0–1 16.8%
11.6%
CUW win
22.6%
Draw
65.5%
CIV win
Top scorelines
  • 0–1 16.8%
  • 0–2 13.7%
  • 0–0 12.4%
  • 0–3 8.7%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
CUW win
8.7%
Draw
18.3%
CIV win
73.0%

The model already heavily favours Ivory Coast (66% away win), and the supplied intel reinforces that. Curaçao's recent form is poor (1 win in 5), they are missing key attacker Kenji Gorre, and their squad is composed of players from lower-tier clubs, while Ivory Coast boasts multiple top-level talents and recent strong form (4 wins in 5, including a draw with France). The absence of market lines leaves the model as the only prior, but the intel justifies a further shift: away win probability increased to 74%, with draws and home wins reduced accordingly. Ivory Coast's expected goals (1.87) and Curaçao's low xG (0.53) suggest a low-scoring game dominated by Ivory Coast. The most likely scorelines are 0-1, 0-2, and 0-3, consistent with the model but with slightly higher away win probabilities. Curaçao's defensive absences (St Jago) may allow Ivory Coast to score multiple goals, but the moderate wind and heat are not extreme enough to significantly alter scoring rates.

What the agent weighed
What the agent checked on the web
Searched tavily for CUW · CIV — 6 sources kept
Agent scorelines
generated 2026-06-11
Last 5 — CUW
-0.25 pts/match vs model expectation · opp. avg #89
  • JAM #94 +0.1
  • CHI #96 -1.2
  • AUS #28 -0.3
  • SCO #38 -0.3
  • ARU #188 +0.2
GF / GA last 10: 19 / 14
Last 5 — CIV
+1.49 pts/match vs model expectation · opp. avg #37
  • BUR #65 +1.2
  • EGY #39 -1.4
  • KOR #37 +1.6
  • SCO #38 +1.6
  • FRA #5 +2.5
GF / GA last 10: 19 / 8
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
12.4
16.8
13.7
8.7
4.7
2.3
1.1
1
5.9
8.0
6.6
4.2
2.3
1.1
0.5
2
1.7
2.3
1.9
1.2
0.7
0.3
0.1
3
0.4
0.5
0.4
0.3
0.1
0.1
0.0
4
0.1
0.1
0.1
0.1
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 = CUW goals; columns = CIV 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)
0.53
CUW
1.87
CIV

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.