This paper presents a comprehensive benchmarking tool for autonomous shipping in polar environments, addressing the growing interest in polar routes due to climate change and reduced Arctic ice coverage. While these routes offer significant economic and environmental benefits by reducing distance, fuel consumption, and emissions, they also present severe navigational challenges such as dynamic weather, unpredictable ice formations, and GPS degradation. We propose a simulation framework built on Gazebo—a high-fidelity, open-source platform widely used in robotics and autonomous driving—to evaluate SLAM and routing algorithms under realistic polar conditions. By leveraging sensor fusion techniques, including LiDAR, radar, sonar, and cameras, our framework facilitates rapid development and benchmarking of both traditional and reinforcement learning-based navigation strategies.