Preprint · 2025

Remote Labor Index: Measuring AI Automation of Remote Work

Mantas Mazeika, Alice Gatti, Cristina Menghini, Udari Madhushani Sehwag, Shivam Singhal, Yury Orlovskiy, Steven Basart, Manasi Sharma, Denis Peskoff, Elaine Lau, Jaehyuk Lim, Lachlan Carroll, Alice Blair, Vinaya Sivakumar, Sumana Basu, Brad Kenstler, Yuntao Ma, Julian Michael, Xiaoke Li, Oliver Ingebretsen, Aditya Mehta, Jean Mottola, John Teichmann, Kevin Yu, Zaina Shaik, Adam Khoja, Richard Ren, Jason Hausenloy, Long Phan, Ye Htet, Ankit Aich, Tahseen Rabbani, Vivswan Shah, Andriy Novykov, Felix Binder, Kirill Chugunov, Luis Ramirez, Matias Geralnik, Hernán Mesura, Dean Lee, Ed-Yeremai Hernandez Cardona, Annette Diamond, Summer Yue, Alexandr Wang, Bing Liu, Ernesto Hernandez, Dan Hendrycks

Abstract

AIs have made rapid progress on research-oriented benchmarks of knowledge and reasoning, but it remains unclear how these gains translate into economic value and automation. To measure this, we introduce the Remote Labor Index (RLI), a broadly multi-sector benchmark comprising real-world, economically valuable projects designed to evaluate end-to-end agent performance in practical settings. AI agents perform near the floor on RLI, with the highest-performing agent achieving an automation rate of 2.5%. These results help ground discussions of AI automation in empirical evidence, setting a common basis for tracking AI impacts and enabling stakeholders to proactively navigate AI-driven labor automation.

BibTeX Copy

@misc{mazeika_remote_2025,
	title = {Remote {Labor} {Index}: {Measuring} {AI} {Automation} of {Remote} {Work}},
	shorttitle = {Remote {Labor} {Index}},
	url = {http://arxiv.org/abs/2510.26787},
	doi = {10.48550/arXiv.2510.26787},
	abstract = {AIs have made rapid progress on research-oriented benchmarks of knowledge and reasoning, but it remains unclear how these gains translate into economic value and automation. To measure this, we introduce the Remote Labor Index (RLI), a broadly multi-sector benchmark comprising real-world, economically valuable projects designed to evaluate end-to-end agent performance in practical settings. AI agents perform near the floor on RLI, with the highest-performing agent achieving an automation rate of 2.5\%. These results help ground discussions of AI automation in empirical evidence, setting a common basis for tracking AI impacts and enabling stakeholders to proactively navigate AI-driven labor automation.},
	urldate = {2026-11-06},
	publisher = {arXiv},
	author = {Mazeika, Mantas and Gatti, Alice and Menghini, Cristina and Sehwag, Udari Madhushani and Singhal, Shivam and Orlovskiy, Yury and Basart, Steven and Sharma, Manasi and Peskoff, Denis and Lau, Elaine and Lim, Jaehyuk and Carroll, Lachlan and Blair, Alice and Sivakumar, Vinaya and Basu, Sumana and Kenstler, Brad and Ma, Yuntao and Michael, Julian and Li, Xiaoke and Ingebretsen, Oliver and Mehta, Aditya and Mottola, Jean and Teichmann, John and Yu, Kevin and Shaik, Zaina and Khoja, Adam and Ren, Richard and Hausenloy, Jason and Phan, Long and Htet, Ye and Aich, Ankit and Rabbani, Tahseen and Shah, Vivswan and Novykov, Andriy and Binder, Felix and Chugunov, Kirill and Ramirez, Luis and Geralnik, Matias and Mesura, Hernán and Lee, Dean and Cardona, Ed-Yeremai Hernandez and Diamond, Annette and Yue, Summer and Wang, Alexandr and Liu, Bing and Hernandez, Ernesto and Hendrycks, Dan},
	month = oct,
	year = {2025},
	note = {arXiv:2510.26787 [cs.LG]},
	keywords = {Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Machine Learning},
}