Warscape
Simulated matchup Β· a model, not a forecast

πŸ‡ΊπŸ‡¦ Ukraine vs πŸ‡·πŸ‡΄ RomaniaMilitary comparison, and what happens if they fight

If Ukraine attacked Romania today, with no allies joining on either side, this is what the WARSCAPE engine produced: Ceasefire, front frozen after 270 days.

How the two militaries compare

Ukraine keeps 13 times as many soldiers under arms. Ukraine has 3.0 times the tanks. Ukraine has 2.0 times the combat aircraft. Ukraine spends 5.0 times as much on defence. Public, country-level figures from the data snapshot the run was pinned to (2026.09). See data sources for where each number comes from.

UkraineRomania
900,000Active soldiers70,000
500,000Reservists55,000
900Tanks300
2,000Artillery700
80Combat aircraft40
60Helicopters60
$40.0bnDefence budget$8.0bn
33.0mPopulation19.0m

What the war cost

Ukraine
attacked
17,512
soldiers killed or wounded
39
tanks destroyed
38
aircraft lost
+22
areas of land gained
63%
support at home, at the end
Romania
defended
3,098
soldiers killed or wounded
19
tanks destroyed
28
aircraft lost
βˆ’22
areas of land lost
49%
support at home, at the end

What decided it

01
Mobilisation helped Ukraine
Reservists mobilised: 753,385 vs 32,631.
02
Deployed combat power helped Ukraine
Average deployed combat power: 201 vs 23 model units.
03
Air situation helped Ukraine
Average share of air control for Ukraine: 78%.
04
Political cohesion helped Ukraine
Average cohesion: 73% vs 60%.
05
Logistics helped Romania
Average front-line supply efficiency: 44% vs 46%.
Think it would go differently?

This run assumed no allies, winter, full mobilization for the attacker and partial for the defender, and no nuclear weapons. Change any of that and watch it play out day by day on the map.

Other borders in this neighbourhood

All matchups β†’
After 270 simulated days the conflict between Ukraine and Romania ended with: Ceasefire, front frozen (prolonged stalemate). Aggregate personnel losses within the model: 17,512 (Ukraine) and 3,098 (Romania). This page reports one seeded run of a model on public, aggregate data. It is not a prediction, and no operational information is used.

Model-generated simulation on public, country-level data. Not a prediction. No operational, classified or real-time information is used.