Remote Labor Index Measures AI Automation of Remote Work

The Remote Labor Index (RLI) is a multi-sector benchmark designed to evaluate the performance of AI agents on real-world, economically valuable remote-work projects. This initiative addresses the gap between AI progress on research benchmarks and its actual impact on labor automation. The RLI encompasses a broad range of projects, including game development, product design, architecture, data analysis, and video animation, representing over 6,000 hours of real work valued at over $140,000. Evaluation results indicate that state-of-the-art AI agents perform near the floor on RLI projects, with the best-performing model achieving a very low automation rate. This suggests that contemporary AI systems are not yet capable of completing the vast majority of projects at a quality level that would be accepted as commissioned work. However, the analysis also shows that models are steadily improving, providing a basis for tracking the trajectory of AI automation. The RLI serves as a valuable tool for grounding discussions of AI automation in empirical evidence and enabling stakeholders to proactively navigate its impacts. By providing a common basis for tracking progress, the RLI can help inform policy decisions and guide investments in AI research and development.