Water inrush is one of the typical geological hazards in the construction of high-risk tunnels, and has caused severe losses. To predict water inrush accurately, a novel model was put forward for karst tunnels in the present study. The ideal point method coupled with the analytic hierarchy process method (AHP) was applied for risk assessment of water inrush. First, the ideal point method was introduced as a brand-new way to predict the risk level of water inrush. Second, the water inrush risk in karst tunnels was discussed in terms of influencing factors. With the consideration of karst hydrological and engineering geological conditions, seven key factors were selected as evaluation indices, including formation lithology, unfavorable geological conditions, groundwater level, landform and physiognomy, modified strata inclination, contact zones of dissolvable and insoluble rock, and layer and interlayer fissures. Then the ideal point method was used to deal with the multiple evaluation indices to determine the ideal point and the anti-ideal point. Meanwhile, the analytic hierarchy process method (AHP) was applied to determine the weight coefficient of each evaluation index. Thus, the minkowski distances respectively for the ideal point and the anti-ideal point were calculated. Based on the discriminant analysis theory, the closeness degrees to the ideal points were brought out to specify the risk level of water inrush. Finally, the proposed model was applied to a typical deep-buried karst tunnel: Jigongling Tunnel in China. The obtained results were compared with the results of the relevant methods and the practical findings, and reasonable agreements could validate the presented approach. The obtained results not only provide guidance for the construction of high-risk tunnels, but also bring out an alternative way for risk assessment of water inrush.