Univocal identification of retinal ganglion cells (RGCs) is an essential prerequisite for studying their degeneration and neuroprotection. Before the advent of phenotypic markers, RGCs were normally identified using retrograde tracing of retinorecipient areas. This is an invasive technique, and its use is precluded in higher mammals such as monkeys. In the past decade, several RGC markers have been described. Here, we reviewed and analyzed the specificity of nine markers used to identify all or most RGCs, i.e., pan-RGC markers, in rats, mice, and macaques. The best markers in the three species in terms of specificity, proportion of RGCs labeled, and indicators of viability were BRN3A, expressed by vision-forming RGCs, and RBPMS, expressed by vision- and non-vision-forming RGCs. NEUN, often used to identify RGCs, was expressed by non-RGCs in the ganglion cell layer, and therefore was not RGC-specific. γ-SYN, TUJ1, and NF-L labeled the RGC axons, which impaired the detection of their somas in the central retina but would be good for studying RGC morphology. In rats, TUJ1 and NF-L were also expressed by non-RGCs. BM88, ERRβ, and PGP9.5 are rarely used as markers, but they identified most RGCs in the rats and macaques and ERRβ in mice. However, PGP9.5 was also expressed by non-RGCs in rats and macaques and BM88 and ERRβ were not suitable markers of viability.