Agent Lab — a live forecast exhibit · Applied AI
← All fixtures
Group F · Matchday 4 · 2026-06-14

Sweden vs Tunisia

Guadalupe, Mexico · neutral venue

Most likely scoreline
0–0 15.1%
41.3%
SWE win
29.6%
Draw
29.1%
TUN win
Top scorelines
  • 0–0 15.1%
  • 1–0 14.3%
  • 0–1 11.6%
  • 1–1 11.0%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
SWE win
44.0%
Draw
30.0%
TUN win
26.0%

The model's prior (41% home win) already reflects Sweden's advantage, but the key players factor — Sweden's attackers at elite clubs vs Tunisia's at mid-level — and recent form (Sweden holding its own against stronger opponents while Tunisia underperforms against weaker ones) justify a slight upward adjustment to 45% for Sweden. The draw remains plausible (30%) given the model's draw probability and Tunisia's defensive resilience, while Tunisia's away win is lowered to 25% due to the quality gap. No other factor (H2H, conditions, news) provides a reason to move further. Sweden's expected goals (1.18) and Tunisia's (0.91) suggest a low-scoring match. The most likely scoreline is 1-0 (14%), reflecting Sweden's superior attack and Tunisia's likely defensive setup. 2-0 (12%) is next if Sweden's quality tells. Draws (0-0 10%, 1-1 11%) are plausible given Tunisia's ability to frustrate. A 0-1 Tunisia win is less likely (8%) due to their underperformance and weaker squad.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 8 sources kept:
  • “Sweden vs Tunisia 2026-06-15 lineup injuries” match · 3 hits
    Late fitness or lineup news could significantly alter match forecast.
  • “Sweden squad 2026 World Cup injuries suspensions” SWE · 3 hits
    Key player availability for Sweden is unknown and could change forecast.
  • “Tunisia squad 2026 World Cup injuries suspensions” TUN · 2 hits
    Key player availability for Tunisia is unknown and could change forecast.
Agent scorelines
generated 2026-06-13
Last 5 — SWE
-0.11 pts/match vs model expectation · opp. avg #34
  • SLO #51 -0.9
  • UKR #29 +1.6
  • POL #34 +1.2
  • NOR #19 -1.0
  • GRE #36 -0.7
GF / GA last 10: 13 / 20
Last 5 — TUN
-0.36 pts/match vs model expectation · opp. avg #44
  • MAL #48 -0.3
  • HAI #95 +0.9
  • CAN #44 -0.1
  • AUT #22 -0.9
  • BEL #10 -0.6
GF / GA last 10: 13 / 14
Head-to-head (last 5)
  • 2003-02-12 Tunisia 1–0 Sweden
  • 1999-02-10 Tunisia 0–1 Sweden
  • 1992-04-22 Tunisia 0–1 Sweden
  • 1976-02-28 Tunisia 1–1 Sweden
▸ Full score grid (7×7)
P(home goals × away goals), %
0
1
2
3
4
5
6
0
15.1
11.6
5.4
1.9
0.6
0.2
0.0
1
14.3
11.0
5.1
1.8
0.6
0.2
0.0
2
8.2
6.3
2.9
1.0
0.3
0.1
0.0
3
3.6
2.8
1.3
0.5
0.1
0.0
0.0
4
1.4
1.1
0.5
0.2
0.1
0.0
0.0
5
0.5
0.4
0.2
0.1
0.0
0.0
0.0
6
0.2
0.1
0.1
0.0
0.0
0.0
0.0

Rows = SWE goals; columns = TUN 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)
1.18
SWE
0.91
TUN

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.