Agent Lab — a live forecast exhibit · Applied AI
← All fixtures
Group B · Matchday 3 · 2026-06-13

Qatar vs Switzerland

Santa Clara, United States · neutral venue

Most likely scoreline
0–1 12.2%
12.4%
QAT win
18.6%
Draw
68.4%
SUI win
Top scorelines
  • 0–1 12.2%
  • 0–2 11.5%
  • 0–3 8.5%
  • 0–0 7.7%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
QAT win
13.0%
Draw
20.0%
SUI win
67.0%

The model strongly favours Switzerland (68% away win), and the supplied intel supports that: Qatar's recent form is worse against weaker opponents, and Switzerland's key players are at a higher club level. The head-to-head is a single old result, conditions are neutral, and no injuries affect either side. I keep the prior essentially unchanged, nudging away win slightly to 69% to reflect the form and player quality gap. Switzerland's expected goals (2.31) and Qatar's (0.71) suggest a low-scoring game for Qatar and moderate for Switzerland. The most likely scorelines are 0-1, 0-2, and 0-3, consistent with the model. A draw or Qatar win is less probable given the gap in quality and form.

What the agent weighed
What the agent chose to investigate
Agent scorelines
generated 2026-06-13
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
Last 5 — SUI
-0.42 pts/match vs model expectation · opp. avg #37
  • KOS #56 -0.8
  • GER #7 -1.3
  • NOR #19 -0.2
  • JOR #73 +0.6
  • AUS #28 -0.9
GF / GA last 10: 22 / 8
Head-to-head (last 5)
  • 2018-11-14 Switzerland 0–1 Qatar
▸ Full score grid (7×7)
P(home goals × away goals), %
0
1
2
3
4
5
6
0
7.7
12.2
11.5
8.5
5.4
3.1
1.6
1
4.8
7.6
7.2
5.3
3.3
1.9
1.0
2
1.8
2.8
2.7
2.0
1.2
0.7
0.4
3
0.5
0.8
0.8
0.6
0.4
0.2
0.1
4
0.1
0.2
0.2
0.1
0.1
0.1
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 = QAT goals; columns = SUI 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)
0.71
QAT
2.31
SUI

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.