← All fixtures

Group K · Matchday 13 · 2026-06-23

Portugal vs Uzbekistan

Houston, United States · neutral venue

Most likely scoreline

1–0 16.5%

63.6%

POR win

23.3%

Draw

12.9%

UZB win

Top scorelines

1–0 16.5%
2–0 13.2%
0–0 12.4%
1–1 8.4%

Total goals

0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat

POR win

70.7%

Draw

19.3%

UZB win

10.0%

The model's prior (64% home win) already reflects Portugal's superiority, but the key players gap is even starker when comparing elite European-based stars to Uzbekistan's modest squad. Recent form (2.2 vs 1.0 pts/game) and the absence of any countervailing factors (no injuries, neutral conditions) justify raising Portugal's win probability to 70% and lowering the draw and away win. Uzbekistan's World Cup debut and lack of top-tier talent make an upset unlikely. Portugal's expected goals (1.82) and Uzbekistan's low xG (0.57) suggest a comfortable win with 2-0 or 1-0 most likely. The model's top scoreline 1-0 (17%) is plausible but I slightly favor 2-0 given Portugal's attacking quality. A 3-0 is possible but not dominant. Low-scoring draws (0-0, 1-1) are less likely due to Portugal's offensive edge.

What the agent weighed

Recent form

Portugal recent form LWDWW (2.2 pts/game) vs Uzbekistan DWDLL (1.0 pts/game). → favours Portugal
Head-to-head

No previous meetings between Portugal and Uzbekistan. → no bearing
Key players

Portugal features elite players like Ronaldo (110G for POR, 7.29 rating recently), Bruno Fernandes (9G/3A recently), Bernardo Silva, Cancelo, João Félix; Uzbekistan's best is Shomurodov (40G for UZB, 6.52 rating recently) and Masharipov (7.4 rating). The quality gap is massive. → favours Portugal
Injuries / availability

No injuries reported for either side; however, news indicates Rafael Leão may miss start due to brawl, but he is not listed among key players and not a starter in this forecast. → no bearing
Recent news

Portugal's Leão could miss start due to brawl (telecomasia.net). Uzbekistan trained in Atlanta for World Cup debut (cbsnews.com). → no bearing on match outcome
Conditions

NRG Stadium has climate-controlled roof, neutralizing weather. → no bearing
Model vs market

Model gives Portugal 64% win, 1.82-0.57 xG. No market lines supplied, so model is the only prior. → model already strongly favours Portugal

What the agent checked on the web

Searched tavily for POR · UZB — 6 sources kept

Agent scorelines

2–0 23%
1–0 20%
3–0 15%
2–1 13%
1–1 11%
0–0 9%

generated 2026-06-11

Last 5 — POR

+0.53 pts/match vs model expectation · opp. avg #45

ARM #102 +0.1
MEX #21 -0.7
USA #33 +1.1
CHI #27 +0.7
NIG #41 +0.6

GF / GA last 10: 26 / 9

Last 5 — UZB

-0.43 pts/match vs model expectation · opp. avg #55

CHI #96 -0.9
GAB #83 +0.9
VEN #45 -0.4
CAN #44 -1.0
NED #9 -0.4

GF / GA last 10: 14 / 9

Head-to-head (last 5)

No prior meetings in the dataset.

▸ Full score grid (7×7)

P(home goals × away goals), %

12.4

6.3

1.9

0.5

0.1

0.0

16.5

8.4

2.6

0.6

0.1

0.0

13.2

6.7

2.1

0.5

0.1

0.0

8.2

4.2

1.3

0.3

0.1

0.0

4.4

2.2

0.7

0.2

0.0

2.1

1.1

0.3

0.1

0.0

0.9

0.5

0.1

0.0

Rows = POR goals; columns = UZB 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)

1.81

POR

0.57

UZB

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.