Comparing 2 Rows, Slices

I have a numPy ndarray with the arbitrary values [1,2,3], [4,5,6]. Is there a way to compare "slices" ? For example, I would want to compare 1 to 4 or 2 to 5. I've been tinkering with numpy.max() for a while to no avail.

I thought something along the lines of this might work, but it doesn't.:

def xmax(r):
    xMax = np.max(r[0:2][0]) 
    return(xMax)

Any advice or direction is appreciated.