This　paper　investigates　the　structural　performance　of　concrete-filled　stainless　steel　tubular　(CFSST)　columns　composed　of　rectangular　and　square　sections.　A　fiber-based　mathematical　model　is　developed　to　simulate　the　nonlinear　performance　of　such　columns　loaded　concentrically　accounting　for　the　local　buckling　of　steel　tube.　An　accurate　lateral　pressure　model,　as　well　as　a　strength　degradation　parameter　are　proposed　based　on　the　existing　test　results　and　incorporated　in　the　mathematical　modeling　developed.　A　large　test　dataset　is　used　to　validate　the　accuracy　of　the　numerical　prediction.　The　mathematical　model　is　employed　to　study　the　sensitivities　of　important　column　parameters　on　their　axial　behavior.　The　accuracy　of　the　existing　confinement　model　of　rectangular　CFST　columns　is　evaluated　in　predicting　the　performance　of　CFSST　short　columns.　Furthermore,　the　accuracy　of　the　existing　codified　design　models　as　well　as　and　the　simplified　design　model　proposed　in　this　study　to　quantify　the　ultimate　compressive　strength　of　such　columns　is　investigated.　An　accurate　artificial　neural　network　(ANN)　model　along　with　the　GUI　feature　is　developed　for　the　design　engineers　as　a　tool　to　predict　their　ultimate　axial　strengths.