The aim of this study is To compare robotic-assisted and conventional total knee arthroplasty (TKA) on both short- and long-term outcomes A systematic review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. PubMed, Cochrane, Scopus, and Web of Science databases were searched for relevant studies. The studies included were randomised controlled trials directly comparing robotic-assisted versus conventional TKA. The outcomes were pooled as mean difference (MD) or risk ratio (RR), with 95% confidence interval. RevMan software version 5.4 was used for performing the statistical analysis. Nine studies deemed eligible for inclusion. The data showed a significant favouring of robotic-assisted than the conventional TKA in mechanical alignment, Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC), and femoral coronal plane outliers (MD = − 1.10, 95% CI [− 1.51, − 0.69], p < 0.00001), (MD = − 1.19, 95% CI [− 2.35, − 0.03], p = 0.04), and (RR = 0.49, 95% CI [0.30, 0.80], p = 0.004), respectively. On the other hand, conventional TKA was better in range of motion-flexion (long-term) than the robotic-assisted one (MD = − 3.02, 95% CI [− 3.68, − 2.37], p < 0.00001). There were no significant differences between them in knee society score-knee score, knee society score-function score, change in hospital for special surgery (HSS) knee rating scale, and change in range of motion-extension (MD = − 0.36, 95% CI [− 2.43, 1.70], p = 0.73), (MD = − 0.34, 95% CI [− 2.36, 1.68], p = 0.74), (MD = 0.78, 95% CI [− 0.84, 2.40], p = 0.34), and (MD = 0.16, 95% [− 1.32, 1.64], p = 0.83), respectively. Robotic-assisted TKA demonstrated better outcomes than conventional TKA in terms of mechanical alignment and WOMAC scores. However, the conventional TKA showed a better range of motion-flexion in the long term. More data are needed to assess long-term outcomes comprehensively.