Intracellular reactive oxygen species (ROS) are closely associated with cancer cell types. Therefore, ROS-based pattern recognition is a promising strategy for precise diagnosis of cancer, but such a possibility has never been reported yet. Herein, we proposed an ROS-responsive fluorescent sensor array based on pH-controlled histidine-templated gold nanoclusters (AuNCs@ His) to distinguish cancer cell types and their proliferation states. In this strategy, three types of AuNCs@His with diverse fluorescence profiles were first synthesized by only adjusting the pH value. Upon the addition of various ROS, fluorescence quenching of three types of AuNCs@His occurred with different degrees, thereby forming unique optical "fingerprints", which were well-clustered into several separated groups without overlap by principal component analysis (PCA). The sensing mechanism was attributable to the oxidation of AuNCs@His by ROS, as revealed by X-ray photoemission spectroscopy, Fourier transform infrared spectroscopy, 1 H nuclear magnetic resonance spectroscopy, and electrospray ionization mass spectrometry. Based on the ROS-responsive sensing pattern, cancer cell types were successfully differentiated via PCA with 100% accuracy. Additionally, the proposed sensor array exhibited excellent performance in distinguishing the proliferation states of cancer cells, which was supported by the results of the Ki-67 immunohistochemistry assay. Overall, the ROS-responsive fluorescent sensor array can serve as a promising tool for precise diagnosis of cancer, indicating great potential for clinical application.