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

Canada vs Qatar

Vancouver, Canada

Most likely scoreline
1–0 11.2%
62.9%
CAN win
20.1%
Draw
16.6%
QAT win
Top scorelines
  • 1–0 11.2%
  • 2–0 10.2%
  • 1–1 8.3%
  • 2–1 7.5%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
CAN win
69.3%
Draw
18.3%
QAT win
12.3%

Canada's recent form (unbeaten in 5) and Qatar's poor run (0 wins in 5) strongly favour the hosts. The head-to-head win and superior squad quality (players at Juventus, Bayern, etc.) reinforce this. However, the news that Alphonso Davies is missing the opener is a notable blow to Canada's defence, slightly reducing their edge. The model's 63% home win is a reasonable prior; given the intel, I increase it to 70% to reflect the overall gap, but not more due to Davies' absence. Draw and away win probabilities are reduced accordingly. Canada's expected goals (2.18) and Qatar's (0.87) from the model suggest a relatively low-scoring match with Canada controlling. The most likely scorelines are 2-0 and 1-0, consistent with Canada's solid defence (Davies absence may allow a Qatar goal, but Qatar's attack is weak). 2-1 and 1-1 are also plausible. The distribution is shifted slightly toward Canada scoring 2-3 goals and Qatar 0-1.

What the agent weighed
What the agent checked on the web
Searched tavily for CAN · QAT — 6 sources kept
Agent scorelines
generated 2026-06-11
Last 5 — CAN
-0.08 pts/match vs model expectation · opp. avg #53
  • VEN #45 +1.6
  • ICE #61 -0.9
  • TUN #43 -0.6
  • UZB #54 +1.3
  • BIH #63 -0.9
GF / GA last 10: 11 / 4
Last 5 — QAT
-1.02 pts/match vs model expectation · opp. avg #85
  • PAL #101 -1.9
  • SYR #93 -0.8
  • TUN #43 -1.0
  • REP #50 -0.7
  • EL #139 -1.2
GF / GA last 10: 7 / 15
Head-to-head (last 5)
  • 2022-09-23 Canada 2–0 Qatar
▸ Full score grid (7×7)
P(home goals × away goals), %
0
1
2
3
4
5
6
0
7.4
5.5
2.4
0.8
0.2
0.1
0.0
1
11.2
8.3
3.7
1.3
0.4
0.1
0.0
2
10.2
7.5
3.3
1.2
0.3
0.1
0.0
3
7.2
5.3
2.4
0.8
0.2
0.1
0.0
4
4.3
3.2
1.4
0.5
0.1
0.0
0.0
5
2.4
1.7
0.8
0.3
0.1
0.0
0.0
6
1.2
0.9
0.4
0.1
0.0
0.0
0.0

Rows = CAN goals; columns = QAT 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)
2.17
CAN
0.87
QAT

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.