In order to promote the application of metal magnetic memory technology in the damage detection of bridge steel box beam, a static bending test on the steel box beam of the bridge are carried out, and magnetic signal distribution of the upper flange with the most serious deformation are extracted. The quantitative relationship between the stress in the damage region and magnetic signal or magnetic signal gradient is established, and how to characterize the stress and damage state of steel beam are put forward by magnetic field gradient index. The results show that the magnetic signal curve of the upper flange is opposite to the stress change form, and the magnetic signal curve reverses into negative value after entering the plastic state, and increases with the stress change speed, so the component can be judged to enter the plastic state and be damaged soon. The maximum value of the magnetic field gradient curve appears in the position with the most serious damage, and with the increase of the load, the maximum value point of the magnetic gradient constantly moves to the middle of the steel beam, thus the early warning of the failure state can be carried out. The relation curve between magnetic field gradient and stress can obviously distinguish the whole stress process of the component includes four states: initial, yield, plasticity and damage. The stress state and damage state of components can be characterized by magnetic field gradient index. This study can provide reference and basis for the application of metal magnetic memory detection technology in the quantitative assessment and early warning of the damage status of bridge steel beams.