Warscape
Simulated matchup ยท a model, not a forecast

๐Ÿ‡ท๐Ÿ‡ธ Serbia vs ๐Ÿ‡ญ๐Ÿ‡ท CroatiaMilitary comparison, and what happens if they fight

If Serbia attacked Croatia today, with no allies joining on either side, this is what the WARSCAPE engine produced: Defender holds after 258 days.

How the two militaries compare

Serbia keeps 1.7 times as many soldiers under arms. Serbia has 3.3 times the tanks. Serbia has 2.1 times the combat aircraft. Both spend about the same 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.

SerbiaCroatia
25,000Active soldiers15,000
50,000Reservists20,000
230Tanks70
300Artillery100
25Combat aircraft12
50Helicopters30
$1.5bnDefence budget$1.5bn
6.6mPopulation3.9m

What the war cost

Serbia
attacked
2,073
soldiers killed or wounded
21
tanks destroyed
14
aircraft lost
0
land changed hands
35%
support at home, at the end
Croatia
defended
643
soldiers killed or wounded
4
tanks destroyed
7
aircraft lost
0
land changed hands
49%
support at home, at the end

What decided it

01
Mobilisation helped Serbia
Reservists mobilised: 118,927 vs 15,599.
02
Logistics helped Serbia
Average front-line supply efficiency: 96% vs 62%.
03
Deployed combat power helped Serbia
Average deployed combat power: 10 vs 5 model units.
04
Air situation helped Serbia
Average share of air control for Serbia: 62%.
05
Economic resilience helped Serbia
Average economic stability index: 0.96 vs 0.81.
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 โ†’
After 258 simulated days the conflict between Serbia and Croatia ended with: Defender holds (prolonged stalemate). Aggregate personnel losses within the model: 2,073 (Serbia) and 643 (Croatia). 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.