Agent Lab — a live forecast exhibit · Applied AI
← Schedule
Group F · Matchday 10 · 2026-06-20

Netherlands vs Sweden

Houston, United States · neutral venue

Most likely scoreline
1–0 10.8%
51.6%
NED win
23.1%
Draw
25.1%
SWE win
Top scorelines
  • 1–0 10.8%
  • 1–1 9.6%
  • 2–0 8.5%
  • 0–0 8.3%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
NED win
55.0%
Draw
23.3%
SWE win
21.7%

The model's prior (53% home win) is a reasonable starting point. Head-to-head history and key player analysis both favour Netherlands, but the gap is not overwhelming. Sweden's attack is potent with Gyökeres and Isak, which prevents a large shift. I slightly increase home win probability to 55% and reduce away win to 22%, reflecting the mild edge from H2H and squad depth. The draw stays near the model's estimate. Netherlands are expected to control possession and create more chances, leading to a likely 1-0 or 2-0 win. However, Sweden's counter-attacking threat means a 1-1 draw or even a 0-0 is plausible. The most probable scorelines cluster around low-scoring outcomes because both defenses are solid and the match is a World Cup opener, often cautious.

What the agent weighed
What the agent checked on the web
Searched tavily for NED · SWE — 6 sources kept
Agent scorelines
generated 2026-06-11
Last 5 — NED
-0.55 pts/match vs model expectation · opp. avg #27
  • NOR #19 +1.0
  • ECU #17 -0.8
  • ALG #29 -2.2
  • UZB #54 +0.6
  • JPN #18 -0.7
GF / GA last 10: 23 / 9
Last 5 — SWE
+0.29 pts/match vs model expectation · opp. avg #33
  • UKR #31 +1.5
  • POL #33 +1.2
  • NOR #19 -1.0
  • GRE #36 -0.8
  • TUN #48 +1.3
GF / GA last 10: 16 / 19
Head-to-head (last 5)
  • 2017-10-10 Netherlands 2–0 Sweden
  • 2016-09-06 Sweden 1–1 Netherlands
  • 2011-10-11 Sweden 3–2 Netherlands
  • 2010-10-12 Netherlands 4–1 Sweden
  • 2008-11-19 Netherlands 3–1 Sweden
▸ Full score grid (7×7)
P(home goals × away goals), %
0
1
2
3
4
5
6
0
8.3
7.4
3.9
1.6
0.6
0.2
0.1
1
10.8
9.6
5.1
2.1
0.7
0.2
0.1
2
8.5
7.5
4.0
1.7
0.6
0.2
0.1
3
5.2
4.6
2.4
1.0
0.4
0.1
0.0
4
2.7
2.4
1.3
0.5
0.2
0.1
0.0
5
1.3
1.1
0.6
0.2
0.1
0.0
0.0
6
0.6
0.5
0.3
0.1
0.0
0.0
0.0

Rows = NED goals; columns = SWE 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)
1.77
NED
1.08
SWE

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.