France vs. Morocco — Consensus Ensemble (QF, World Cup 2026)
Thu July 9, 2026 · 22:00 CEST (20:00 UTC / 16:00 EDT) · Gillette Stadium, Foxborough MA (OPEN-AIR)
TL;DR
🇫🇷 France advance ~60% (FRA win 90' ~47% / Draw ~25% / MAR ~28%). Modal 1-1 or FRA 2-1. Mbappé #1 scorer (30-36%), Ounahi #1 MAR (15-28%). FRA's elite defense (3 GA in 5 games) vs MAR's false-9 pivot (no specialist finisher) is the defining matchup.
(2-agent consensus — g4 [glm-5-turbo] failed 3× to rate-limit and could not complete. mm3 + g5 agree tightly: FRA advance 59-60%, FRA win 46-48%, draw 24-25%. Narrow 1pt spread = both anchored on the same WDM + the same MAR regression thesis. g4's scoreline-precision strength is absent — modal scoreline split is less robust than a full trio.)
- 90' win: FRA ~47% consensus (mm3 46% / g5 48%) — moderate favorite, not a blowout. WDM fav_share 0.66.
- Draw band: 25% consensus (mm3 25% / g5 24%) — R32-4 cap (fav_share 0.60-0.70 → 20-25%). Bounou's pen pedigree keeps the ET/pens path live.
- Advance: FRA ~60% (mm3 59% / g5 60%). MAR ~40%.
- Modal scoreline: 1-1 (mm3 16%) or FRA 2-1 (g5 13%). Runners-up: FRA 1-0 (mm3 13%).
- Who Scores: Mbappé #1 FRA (mm3 30% / g5 36%). Ounahi #1 MAR (mm3 28% / g5 15%).
- Watch: MAR's false-9 pivot (Saibari dropped → Díaz) — no specialist finisher vs FRA's elite CB axis. If level at 60', MAR's bench (15.8% sub-impact, Rahimi) + Bounou's shootout pedigree tilt it.
Ensemble Reconciliation
| Agent | Model | 90' FRA | 90' Draw | 90' MAR | Advance FRA | Modal 90' |
|---|---|---|---|---|---|---|
| mm3 | minimax/MiniMax-M3 | 46% | 25% | 29% | 59% | 1-1 (16%) |
| g5 | zai/glm-5.2 (xhigh) | 48% | 24% | 28% | 60% | FRA 2-1 (13%) |
| g4 | glm-5-turbo (xhigh) | — | — | — | — | FAILED (rate-limit) |
| CONSENSUS | — | ~47% | ~25% | ~28% | ~60% | 1-1 / FRA 2-1 |
⚠️ 2-agent ensemble. g4 (glm-5-turbo, xhigh) failed 3× to API rate-limit and could not produce output. The consensus is mm3 + g5 only. Agent-strength caveat: g4's validated strength is scoreline precision on clear favorites (FRA fav_share 0.66 qualifies) — its absence makes the modal scoreline less robust. The 1pt spread between mm3/g5 is tight; flag as potential shared-anchoring (both keyed on MAR's R16 xG regression), not necessarily high confidence.
Key factors (both agents agree):
- WDM fav_share 0.66 — FRA moderate favorite (squad value €1.195B vs €318M = 3.76:1), not a blowout. MAR's AFCON pedigree + drew-Brazil form compress the gap.
- MAR's false-9 pivot is the model-breaker — Saibari dropped (0 KO goals), Díaz as false 9, no specialist finisher vs FRA's elite Saliba-Upamecano axis (3 GA in 5 games). Both agents flag F17 4th (no striker).
- MAR R16 was borrowed — 0.79 xG → 3 goals (+2.2 over-performance). Regression vs FRA defense expected.
- Bounou hot-GK diluted (R32-5f) — confirmed-form but in open 4-2-3-1 (not low block) → ×0.25 weight, not ×0.5-0.6. Pen pedigree (2× WC shootout winner) is real → MAR ~65% if pens reached.
- MAR bench (15.8%) >> FRA bench (5.3%) — Rahimi super-sub raises MAR's late-equalizer threat.
- Tello LOW-PEN (7-12% pen, 2-3 yellows) — inverse of rule #16 archetype.
- F11 weather: open-air, but ~26-29°C seasonal norm → net neutral (below 33°C threshold; Tier-1 FRA gets 50% reduction in 28-32°C band anyway).
- F12 = 0% (QF, no conservation for either side).
Consensus reconciled by lead (2-agent ensemble — g4 rate-limited). Spread 1pt (tight — flag shared anchoring on MAR xG regression). Modal: 1-1 / FRA 2-1. Watch: 60' sub window + MAR bench cavalry + Bounou shootout pedigree if level.