The evaluation of input device spectral sensitivity is often performed in terms of colorimetric quality and potential noise caused by overlaps among spectral sensitivities. Based on the assumption that the white balancing function should aim at color constancy rather than chromatic adaptation, we have proposed a new measure to evaluate camera sensitivities. We measure how accurate camera estimates the colors of typical objects under a standard light source from the ones under different light sources. Firstly, we apply these three evaluation measures, which are colorimetric error, noise amount, and newly proposed color constancy prediction error (CCPE), to eight sets of camera sensitivities. Thus it is found that sensitivity set of a conventional TV camera performs better CCPE than the E-H-P primaries. Secondly, we optimized primary conversion with a linear diagonal matrix transform, a. k. a. von Kries transformation, in order to minimize CCPE. The sensitivity obeying the Luther condition does not necessarily perform the best while the conventional TV camera sensitivity gives the best result. Lastly, we evaluate the optimized results with spectral reflectance database for several light sources including fluorescent lamps. We found that a linear combination of color rendering properties (Ra) of light sources and reciprocal color temperature difference from the standard light source well estimates CCPE.