Partially observable multi-agent cooperation (POMAC) is a popular task in multi-agent systems, where recognized environments play a vital role for algorithms development and testing like the StarCraft Multi-Agent Challenge. However, POMAC in real world often faces more complex situations beyond the simulation scope of current environments, such as asynchronous cooperation, which largely limits the development of multi-agent cooperation algorithms. To cope with this gap, we propose WarGame Challenge (WGC), which provides four sub-environments to reflect reality-inspired characteristics in POMAC, i.e., cooperation with asynchronous actions, strongly stochastic environments, changeable agents, and asymmetric opponents. Along with the benchmark, we embed Pymarl package and provide baseline multi-agent reinforcement learning algorithms for researchers’ use. The overall codes and projects will be released after the paper review process.