KOR 1-0 SKB · 53% BRA 1-2 BOD · 57% SCP 1-2 189 · 58% MOD 1-1 EMP · 51% DIN 1-1 FAR · 53% SAN 1-1 BOC · 54% PAN 0-2 PAO · 63% LEC 2-0 RAD · 59% ACM 2-0 LEC · 66% MAR 1-2 PAR · 60% VAL 1-1 REA · 58% COR 1-0 FLU · 52% VIT 1-1 CRU · 50% LEG 1-0 GRA · 53% KOR 1-0 SKB · 53% BRA 1-2 BOD · 57% SCP 1-2 189 · 58% MOD 1-1 EMP · 51% DIN 1-1 FAR · 53% SAN 1-1 BOC · 54% PAN 0-2 PAO · 63% LEC 2-0 RAD · 59% ACM 2-0 LEC · 66% MAR 1-2 PAR · 60% VAL 1-1 REA · 58% COR 1-0 FLU · 52% VIT 1-1 CRU · 50% LEG 1-0 GRA · 53%
Premier League · Regular Season - 5 Sep 13, 2026 · 15:30 · UTC Old Trafford, Manchester Match Finished · 90'

Manchester United
vs
Manchester City.

Quick answer

Who will win Manchester United vs Manchester City?

Final score: Manchester United 0–1 Manchester City. Before kickoff, 5 of 12 AI models pick Manchester City to win (42%); the consensus was right.

Consensus of independent AI models on TuringStats, updated before kickoff. Not betting advice.

Head-to-head history → Manchester United form Manchester City form

12 AI models read this match. The plurality on 1X2 leans toward Manchester City (5 of 12 models). The mean predicted score (rounded from all models) is 1–2 at 57% mean confidence (Medium band) — see the strip and table below.

Who do you think will win?

Vote before kick-off and compare with AI

10 AI models · council in session Live match data · Pro

Still not sure? Ask 10 AIs at once:
“Will Manchester United beat Manchester City in their upcoming match?”

Every model votes yes or no and defends it in a sentence or two. Attach this match's last-5 form, head-to-head and the picks above so they argue from real data — then keep asking the same council follow-ups.

Ask the Council Free today · sign in with Google to convene the council
— Consensus

Where the panel lands.

Vote share across models. Read this strip first, then the line-by-line table.

Manchester United win 25%

3 / 12 models

Draw 33%

4 / 12 models

Manchester City win 42%

5 / 12 models

— Model breakdown

12 picks. Receipts attached.

Line-by-line comparison of each system’s call.

#
Model
Pick
Score
Conf.
Reasoning
01
GPT-5.6 Luna
Manchester City win
1–2
62%
Manchester City has shown stronger recent form and consistency, while Manchester United has struggled defensively at home.
02
Claude Sonnet 5
Manchester City win
1–2
52%
Derby is unpredictable with recent H2H split evenly, but City's overall quality edge and Old Trafford derby volatility favor a narrow away win.
03
Gemini 3.8 Flash
Draw
1–1
45%
Manchester derbies are often tightly contested. Recent H2H shows mixed results, including draws and narrow wins. A 1-1 draw reflects the balance between United's home advantage and City's overall quality.
04
Grok 4.6
Draw
1–1
48%
Tight Manchester derby at Old Trafford; recent H2H features draws and narrow results suggesting a low-scoring stalemate.
05
DeepSeek V4 Pro
Manchester City win
1–2
65%
City’s superior recent form and attacking quality edges United despite home advantage.
06
Qwen 3.8 Max
Draw
1–1
62%
Recent history shows balanced encounters; both teams strong defensively and offensively, likely to cancel each other out at Old Trafford.
07
Mistral Medium 3.5
Manchester United win
2–1
60%
Recent H2H shows United competitive; home advantage at Old Trafford and City’s slight defensive fragility in derbies.
08
Llama 3.1 70B Instruct
Draw
1–1
62%
Historical head-to-heads show mixed results; recent form and strong home venue for Manchester United balanced by Manchester City's quality and away performances.
09
Kimi K3
Manchester City win
1–2
58%
Manchester derby at Old Trafford; City's superior squad depth and recent dominance in this fixture give them the edge, though United's home support keeps it competitive and tight.
10
GLM 5.3
Manchester City win
1–2
55%
Derby at Old Trafford, but City's superior squad depth and control typically edge these fixtures; United competitive at home, so a narrow away win with both scoring fits best.
11
Cohere Command R+ (08-2024)
Manchester United win
1–0
62%
United's new-look lineup has gelled, outscoring City 4-0 in 2026. City's attack is less clinical; they drew blank at Old Trafford last time.
12
MiMo V2.5 Pro
Manchester United win
2–1
55%
Old Trafford home edge; recent H2H win for United, but derbies often see both teams score, suggesting a close home victory.
— Scoreline frequency

How often each scoreline showed up.

5 of 12 models settled on 1–2. The rest of the list shows where dissent still lives before kickoff.

  • 1–2
    5 models
  • 1–1
    4 models
  • 2–1
    2 models
  • 1–0
    1 model

Match overview

Looking for a today prediction on Manchester United vs Manchester City in Premier League? TuringStats aggregates multiple AI scorelines into one readable page so you can see who the models favor, the mean predicted score shown in the hero (1 - 2; the frequency chart below lists the most common exact scorelines), and implied splits before kickoff.

This prediction hub is written for readers comparing betting tips-style language with transparent model votes — not a single black-box call. The headline read is Manchester City win, with vote shares roughly 25% / 33% / 42% home, draw, and away (rounded).

If you are asking who will win Manchester United vs Manchester City, start with the consensus strip and model table, then cross-check form and injuries in Match context further down — that order keeps the strongest signals first.

— Aggregated insights

What’s moving the panel.

01
Consensus favors Manchester City

42% of models lean away — the clearest cluster on this fixture before kickoff.

02
Medium confidence

Mean 57% across the panel with real dispersion — compare unanimous calls vs split tickets in the model table.

03
xG tilt 1.17 vs 1.33

Derived from predicted scorelines (model means), not live match data — useful for pace vs vote-share sanity checks.

04
Match context

Expected-goals tilt and home-field rhythm (see xG on this page) usually explain whether the game stays open or compresses late.

Match stats forecast

Corners, cards and shots from each side's last 10 matches at this venue, blended with the league average. Pure statistics, not an AI vote.

No AI
Metric Manchester United Manchester City Expected total Lean
Corners 5.7 6.8 12.5 Under 12.5 52% Ask AI
Yellow cards 1.9 2.0 3.9 Over 3.5 54% Ask AI
Shots 16.2 15.9 32.1 Under 32.5 54% Ask AI
Shots on target 6.6 4.9 11.5 Under 11.5 52% Ask AI

Sample: 10 matches per side. Probabilities are Poisson estimates for information only.

Ask the Council about this match

Pro

10 AI models vote yes or no with this match's last-5 form, head-to-head, live status and the model picks above attached — not from memory. Then keep asking the same council follow-ups.

Confidence trend

Cumulative average confidence in table order.

First model Last model
Result check

Actual Manchester City win · AI Manchester City win

1X2: Miss Score: Off
— Match context

Form, history, team news.

Manchester United
Last 5
L L D W L
9 GF · 10 GA
Recent fixtures
  • Brighton 2-3 L
  • Manchester City 0-1 L
  • Everton 2-2 D
  • Ipswich 5-2 W
  • Hull City 2-0 L
Team news

No major injury updates in the current API snapshot.

Manchester City
Last 5
W W W W W
13 GF · 2 GA
Recent fixtures
  • Norwich 5-0 W
  • Manchester United 0-1 W
  • Coventry 1-0 W
  • Crystal Palace 1-4 W
  • Bournemouth 2-1 W
Team news

No major injury updates in the current API snapshot.

— Head to head

Last five meetings.

MAN 2 · D 1 · MAN 2

MAN VS MAN
0-1
AWAY WIN
Sep 13, 2026
MAN VS MAN
2-0
HOME WIN
Jan 17, 2026
MAN VS MAN
3-0
HOME WIN
Sep 14, 2025
MAN VS MAN
0-0
DRAW
Apr 6, 2025
MAN VS MAN
1-2
AWAY WIN
Dec 15, 2024

Betting tips (AI-signal view)

Educational only — not financial advice. We summarize how the AI picks cluster so you can cross-check with your own staking plan.

  • Lean with the plurality: when 25% of models side with Manchester United, treat that as the default script unless late team news breaks the assumptions.
  • Watch the draw lane at 33% — tight Premier League games often compress toward stalemates when both midfields win the second-ball.
  • If you chase “best bets today” narratives, require alignment between the headline pick and the score-frequency table; conflicting signals usually mean thinner edge.

Odds & analysis (implied probabilities)

Implied fair percentages from the model vote share (normalized to 100%) approximate how a balanced market might price the 1X2 if it mirrored this panel — useful for odds analysis homework even though we do not quote sportsbook ticks here.

Manchester United
~25%
implied lean
Draw
~33%
implied lean
Manchester City
~42%
implied lean

Over / under prediction (totals)

Model-derived xG sums to 2.50 goals in expectation. A notional totals line near 2.8 is consistent with that pace (rounded for readability). If your sportsbook posts a similar number, compare juice and live team news before deciding either side of the total.

Handicap prediction (spread-style read)

When Manchester United is priced as the stronger side in the model vote, a −1 handicap narrative only clears if the most common scorelines include multi-goal wins. Cross-check the score-frequency list: if tight one-goal wins dominate, Asian handicaps near pick’em or −0.5 / −0.75 splits often fit the story better than a full −1.5 sell.

BTTS prediction (both teams to score)

With combined offensive weight near 2.50 xG, a heuristic “both teams score” prior lands around 55% yes before defensive adjustments. If several top models forecast clean-sheet pathways, downgrade BTTS enthusiasm even when the raw xG sum looks juicy.

Best bet framing (consensus-led)

Our headline best bet label follows the consensus recommendation: Manchester City win. Pair that with the confidence band (Medium) — high dispersion across models usually argues for smaller stake or pass, even when the headline pick looks tempting for a today prediction card on social.

Explore more

Keep browsing today prediction coverage and league hubs.

Related matches

— Journal

Articles linked to these clubs or AI forecasting.

Ask multiple AIs about this match.

10 models vote yes or no with this match's last-5 form, head-to-head, live status and our model picks attached — not from memory. Then ask follow-ups to the same council.