We propose a network of model neurones that 'reads' the information encoded as a mean spiking rate by mechanisms relevant to the organism. The streams of independent irregular spiking activity with a Poisson distribution enters the network in parallel via two inputs. The network integrated both synaptic inputs and at the same time acts as a counter allowing their continuous comparison. Detection of the mean spiking rate difference is signalled by spikes emitted at the output. The exactness of the mean-rate discrimination was quantified by the probability of theoretically best comparison.