Purpose The aim of this study was to investigate the clinical and radiological results of the MAKO CT‐based robotic‐assisted system for total knee arthroplasty (TKA). Methods A PRISMA systematic review was conducted using four databases (MEDLINE, EMBASE, Pubmed, GOOGLE SCHOLAR) to identify all clinical and radiological studies reporting information regarding the use and results of the CT‐based robotic‐assisted system to perform TKA between 2016 and 2020. The main investigated outcome criteria were postoperative pain, analgesia requirements, clinical scores, knee range of motion, implant positioning and the revision rate. The ROBINS‐I tool (Risk Of Bias In Non‐randomized Studies of Interventions) was used to evaluate the quality of included studies and the risk of bias. Results A total of 36 studies were identified, of which 26 met inclusion criteria. Of these 26 studies, 14 were comparative. The follow‐up varied from 30 days to 17 months. This CT‐based, saw cutting Robotic TKA is associated with a significantly lower postoperative pain score (2.6 versus 4.5) and with significantly reduced time to hospital discharge (77 h versus 105), compared with conventional TKA. The two comparative studies assessing functional outcomes at 1 year reported significantly better functional scores with CT‐based robotic TKA compared with conventional TKA (WOMAC score: 6 ± 6 versus 9 ± 8 ( p < 0.05); KSS function score: 80 versus 73 ( p = 0.005)). Only three comparative studies assessed implant positioning, and these reported better implant positioning with CT‐based robotic‐assisted TKA. Conclusion The CT‐based robotic‐assisted system for TKA reduced postoperative pain and improved implant positioning with equal or slightly superior improvement of the functional outcomes at one year, compared to conventional TKA. Level of evidence Systematic review level IV.