Abstract: A content-based video evaluation model for users' QoE is proposed to achieve an accurate evaluation of the network video quality. In addition to obtain the coding bit rate and the packet loss rate from the packet headers, the model also obtain the frame type, the macro-block type and the motion vector from the payload information, using the motion vectors and the ratio of intra-coded macro-blocks to represent the motion characteristics of video content, combined it with the coding bit rate and the packet loss rate to establish the distortion model and transmission distortion model respectively, and the content-based video evaluation model for users' QoE is then generated. Experimental results show that the Pearson Correlation Coefficient between objective score obtained from the model calculations and subjective MOS scores is as high as 0.964 4 and the Root Mean Square Error of them is 0.349 0. The proposed model has a great accuracy on predicting users' QoE of networked videos of different content account with its good performance.