Agent Lab — a live forecast exhibit · Applied AI
← Schedule
Group I · Matchday 6 · 2026-06-16

Iraq vs Norway

Foxborough, United States · neutral venue

Full time IRQ 1–4 NOR
The agent called Norway (66%) — Better than the model call right

The forecast below is what the agent published before kickoff.

Most likely scoreline
0–1 13.8%
13.6%
IRQ win
20.9%
Draw
65.2%
NOR win
Top scorelines
  • 0–1 13.8%
  • 0–2 12.0%
  • 0–0 9.5%
  • 1–1 8.2%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
IRQ win
13.0%
Draw
20.7%
NOR win
66.3%

The statistical model already favours Norway (58% away win), and the squad market value gap (Norway ~28.8x more valuable) reinforces that Norway's talent is far superior. Iraq's recent form is mediocre against weak opposition, while Norway has over-performed against strong opponents. Key player quality heavily tilts toward Norway with Haaland. I increase Norway's win probability to 68% to reflect the talent disparity not fully captured by the model, while keeping a modest draw chance (20%) as Iraq may defend deep in a World Cup debut. Norway's expected goals (1.66) and Haaland's presence point to a likely 1-0 or 2-0 win. Iraq's low xG (0.68) and defensive setup suggest they may struggle to score, but a 0-0 or 1-1 draw is possible if Norway is wasteful. The most probable scorelines are 0-1, 0-2, and 0-3, with a non-negligible chance of 1-1.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 9 sources kept:
  • “Iraq national team injuries lineup June 2026” IRQ · 3 hits
    Late fitness or lineup changes could shift Iraq's expected strength.
  • “Norway national team injuries lineup June 2026” NOR · 3 hits
    Key player availability (e.g., Haaland) would drastically alter Norway's chances.
  • “Iraq vs Norway neutral venue Foxborough weather forecast June 16 2026” match · 3 hits
    Extreme weather (heat, rain) could affect playing conditions and team performance.
Agent scorelines
generated 2026-06-16
Last 5 — IRQ
+0.21 pts/match vs model expectation · opp. avg #73
  • JOR #75 -1.2
  • BOL #73 +1.8
  • AND #167 +0.8
  • ESP #1 +0.9
  • VEN #47 -1.0
GF / GA last 10: 11 / 10
Last 5 — NOR
+0.28 pts/match vs model expectation · opp. avg #15
  • ITA #13 +2.0
  • NED #9 -0.7
  • SUI #16 -0.5
  • SWE #24 +1.2
  • MAR #11 +0.1
GF / GA last 10: 31 / 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
9.5
13.8
12.0
8.2
4.8
2.5
1.2
1
5.7
8.2
7.2
4.9
2.8
1.5
0.7
2
2.0
3.0
2.6
1.8
1.0
0.5
0.3
3
0.6
0.8
0.7
0.5
0.3
0.1
0.1
4
0.1
0.2
0.2
0.1
0.1
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 = IRQ goals; columns = NOR 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)
0.68
IRQ
2.05
NOR

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.