Objective To explore the effect of modified gap balancing on sagittal alignment and functional recovery of femoral prosthesis in patients with total knee arthroplasty. Methods The patients with knee osteoarthritis in our hospital for initial TKA (96 cases, 96 knees) from April 2017 to June 2020 were divided into group A (GB) and group B (measure resection). The general information, surgical indicators, imaging indicators, prognostic indicators and 1-year postoperative complications of all subjects were collected. A random walk model was used to evaluate the functional recovery of the two groups of patients. Results There were no significant differences in general data and surgical indicators between the two groups (P＞0.05). One year after operation, knee flexion 90° stress angle of medial and lateral tibiofemoral joint and FPFA in group A were significantly improved compared with those in group B (P＜0.05). One year after operation, the visual analogy score and KSS score of group A were significantly improved compared with those of group B (P＜0.05). The random walking model evaluated the functional recovery of patients in group A was significantly better than that in group B. Compared with group B, group A had a lower risk of complications at 1 year after operation (P＜0.05). Conclusion In TKA, the application of the modified GB is more helpful than the MR to maintain a good sagittal alignment of the femoral prosthesis and 90° stability of the knee flexion, and effectively relieve pain, and the postoperative recovery of knee joint function is better