Agent Lab — a live forecast exhibit · Applied AI
← Schedule
Group I · Matchday 16 · 2026-06-26

Norway vs France

Foxborough, United States · neutral venue

Full time NOR 1–4 FRA
The agent called France (54%) — Worse than the model call right

The forecast below is what the agent published before kickoff.

Most likely scoreline
0–1 12.4%
21.5%
NOR win
23.5%
Draw
54.8%
FRA win
Top scorelines
  • 0–1 12.4%
  • 0–2 9.7%
  • 1–1 9.6%
  • 0–0 9.5%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
NOR win
20.7%
Draw
25.0%
FRA win
54.3%

The model's prior (53% France win) is supported by France's superior squad value (2nd vs 11th), a lopsided recent head-to-head (4-0 in 2014), and deeper key-player talent (Mbappé, Olise, Dembélé). Norway's recent form overperformance (+0.84 pts/match) is notable but came against weaker opponents (avg rank #30), and conditions are neutral. I nudge France down slightly to 55% because Norway's overperformance and Haaland's threat create some upset potential, but the structural talent gap keeps France as clear favourites. The model expects 1.68 goals for France and 0.92 for Norway, with 0-1 as the top scoreline (13%). France's defensive solidity and Norway's reliance on Haaland for goals suggest a low-scoring affair; 0-1, 1-1, and 0-2 are the most likely outcomes. I keep the scoreline distribution close to the model, as no factor pushes scoring higher or lower.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 9 sources kept:
  • “Norway vs France 2026-06-26 team news injuries suspensions” match · 3 hits
    Late fitness or lineup changes could significantly alter match outcome.
  • “Norway football manager 2026” NOR · 3 hits
    A recent manager change could affect tactics and team morale.
  • “France football injuries 2026 June” FRA · 3 hits
    Key player absences like Mbappé or Griezmann would shift forecast.
Agent scorelines
generated 2026-06-26
Last 5 — NOR
+0.86 pts/match vs model expectation · opp. avg #30
  • SUI #16 -0.5
  • SWE #24 +1.2
  • MAR #11 +0.1
  • IRQ #80 +0.7
  • SEN #21 +1.6
GF / GA last 10: 26 / 10
Last 5 — FRA
+0.29 pts/match vs model expectation · opp. avg #40
  • COL #8 +1.5
  • CIV #26 -2.3
  • NOR #65 +0.4
  • SEN #21 +1.1
  • IRQ #80 +0.4
GF / GA last 10: 27 / 9
Head-to-head (last 5)
  • 2014-05-27 France 4–0 Norway
  • 2010-08-11 Norway 2–1 France
  • 1998-02-25 France 3–3 Norway
  • 1995-07-22 Norway 0–0 France
  • 1989-09-05 Norway 1–1 France
▸ Full score grid (7×7)
P(home goals × away goals), %
0
1
2
3
4
5
6
0
9.5
12.4
9.7
5.9
3.1
1.4
0.6
1
7.4
9.6
7.5
4.6
2.4
1.1
0.5
2
3.4
4.5
3.5
2.1
1.1
0.5
0.2
3
1.2
1.6
1.3
0.8
0.4
0.2
0.1
4
0.4
0.5
0.4
0.2
0.1
0.1
0.0
5
0.1
0.1
0.1
0.1
0.0
0.0
0.0
6
0.0
0.0
0.0
0.0
0.0
0.0
0.0

Rows = NOR goals; columns = FRA 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)
0.92
NOR
1.76
FRA

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.