The ignition delay is an important quantity in low temperature combustion concepts where a prolonged ignition delay gives an enhanced fuel-air mixing process, favourable for decreased particulate and NOx emission levels. This article experimentally evaluates three different low-order physics-based correlation models and their ability to predict the ignition delay for the purpose of model-based controller design. The models relate the state of the gas mixture after the point of fuel injection in order to predict the ignition delay. The experiments were all performed on a six-cylinder direct-injection Scania diesel engine with a fuel mixture of 80 vol% gasoline and 20 vol% n-heptane. The results showed that ignition-delay variation was not easily predicted when the injection timing was varied close to top-dead-centre but that the model performance satisfactorily during intake-condition variations. The results also showed that a more complex model did not necessarily give an increased prediction performance.