Agent Lab — a live forecast exhibit · Applied AI
← All fixtures
Group G · Matchday 5 · 2026-06-15

Iran vs New Zealand

Inglewood, United States · neutral venue

Most likely scoreline
1–0 18.9%
56.5%
IRN win
28.1%
Draw
15.3%
NZL win
Top scorelines
  • 1–0 18.9%
  • 0–0 16.9%
  • 2–0 12.7%
  • 1–1 9.2%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
IRN win
60.0%
Draw
25.7%
NZL win
14.3%

The model already favours Iran (56% win), and the supplied intel reinforces that: Iran's recent form is strong (+0.63 over-performance) against weaker opponents, while New Zealand is in poor form (-0.15) against stronger opponents. The key player quality gap is clear—Iran's attackers play at higher club levels and have better recent ratings than New Zealand's. The head-to-head, though sparse, is undefeated for Iran. No injuries or conditions alter the picture. I nudge the home win probability up to 60%, keeping the draw around 25% and away win at 15%. Iran's expected goals (1.44) and New Zealand's (0.54) suggest a low-scoring match with Iran controlling. The most likely scoreline is 1-0 (18%), followed by 2-0 (14%) and 1-1 (10%). The 0-0 draw (9%) is still plausible given New Zealand's defensive setup, but Iran's attacking quality makes a clean sheet for Iran likely.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 9 sources kept:
  • “Iran vs New Zealand 2026 World Cup lineup news” match · 3 hits
    Late fitness or lineup changes could significantly affect the match outcome.
  • “Iran national team injuries suspensions June 2026” IRN · 3 hits
    Key player absences would alter Iran's strength.
  • “New Zealand national team injuries suspensions June 2026” NZL · 3 hits
    Key player absences would alter New Zealand's strength.
Agent scorelines
generated 2026-06-13
Last 5 — IRN
+0.63 pts/match vs model expectation · opp. avg #60
  • UZB #54 -0.6
  • NIG #41 -1.5
  • COS #66 +1.2
  • GAM #89 +0.8
  • MAL #48 +1.3
GF / GA last 10: 17 / 6
Last 5 — NZL
-0.15 pts/match vs model expectation · opp. avg #42
  • ECU #16 -0.5
  • FIN #69 -1.3
  • CHI #27 +2.2
  • HAI #95 -1.2
  • ENG #4 -0.2
GF / GA last 10: 7 / 18
Head-to-head (last 5)
  • 2003-10-12 Iran 3–0 New Zealand
  • 1973-08-12 New Zealand 0–0 Iran
▸ Full score grid (7×7)
P(home goals × away goals), %
0
1
2
3
4
5
6
0
16.9
8.2
2.4
0.5
0.1
0.0
0.0
1
18.9
9.2
2.7
0.6
0.1
0.0
0.0
2
12.7
6.2
1.8
0.4
0.1
0.0
0.0
3
6.6
3.2
0.9
0.2
0.0
0.0
0.0
4
3.0
1.4
0.4
0.1
0.0
0.0
0.0
5
1.2
0.6
0.2
0.0
0.0
0.0
0.0
6
0.4
0.2
0.1
0.0
0.0
0.0
0.0

Rows = IRN goals; columns = NZL 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)
1.44
IRN
0.54
NZL

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.