SVRPBench: A Realistic Benchmark for Stochastic Vehicle Routing Problem

TL;DR

SVRPBench is a comprehensive, high-fidelity benchmark for stochastic vehicle routing that captures real-world urban delivery uncertainties, challenging current algorithms to improve robustness and generalization.

Contribution

This paper introduces SVRPBench, the first realistic, large-scale benchmark for stochastic vehicle routing with diverse scenarios and detailed uncertainty modeling.

Findings

RL solvers like POMO and AM degrade under distributional shift

Classical and metaheuristic methods show robustness to uncertainty

Benchmark facilitates research on adaptive and generalizable routing algorithms

Abstract

Robust routing under uncertainty is central to real-world logistics, yet most benchmarks assume static, idealized settings. We present SVRPBench, the first open benchmark to capture high-fidelity stochastic dynamics in vehicle routing at urban scale. Spanning more than 500 instances with up to 1000 customers, it simulates realistic delivery conditions: time-dependent congestion, log-normal delays, probabilistic accidents, and empirically grounded time windows for residential and commercial clients. Our pipeline generates diverse, constraint-rich scenarios, including multi-depot and multi-vehicle setups. Benchmarking reveals that state-of-the-art RL solvers like POMO and AM degrade by over 20% under distributional shift, while classical and metaheuristic methods remain robust. To enable reproducible research, we release the dataset and evaluation suite. SVRPBench challenges the community to design solvers that generalize beyond synthetic assumptions and adapt to real-world uncertainty.