We present a novel analysis of the redshift-space power spectrum of galaxies in the Sloan Digital Sky Survey III (SDSS-III) Baryon Oscillation Spectroscopic Survey (BOSS). Our methodology improves upon previous analyses by using a theoretical model based on cosmological simulations coupled with a perturbative description of the galaxy-matter connection and a phenomenological prescription of fingers of God. This enables a very robust analysis down to mildly non-linear scales, k similar or equal to 0.4 h Mpc(-1). We carried out a number of tests on mock data, different subsets of BOSS, and using model variations, all of which support the robustness of our analysis. Our results provide constraints on sigma(8) , Omega(m), h , and S-8- sigma(8)root Omega(m)/0.3 . Specifically, we measure Omega(m) = 0.301 +/- 0.011, sigma(8) = 0.745(-0.035)(+0.028), h = 0.705 +/- 0.015, and S-8 = 0.747(-0.039)(+ 0.032) when all the nuisance parameters of our model are left free. By adopting relationships among bias parameters measured in galaxy formation simulations, the value of S-8 remains consistent whereas uncertainties are reduced by similar to 20 per cent . Our cosmological constraints are some of the strongest obtained with the BOSS power spectrum alone: they exhibit a 2 . 5 -3 . 5 sigma tension with the results of the Planck satellite, agreeing with the lower values of S-8 derived from gravitational lensing. However, the cosmological model preferred by Planck is still a good fit to the BOSS data, assuming small departures from physical bias priors and, therefore, cannot be excluded at high significance. We conclude that, at the present, the BOSS data alone does not show strong evidence for a tension between the predictions of Lambda cold dark matter (Lambda CDM) for the high- and low-redshift Universe.