Agents' Last Exam

ALE introduces a benchmark evaluating AI agents on long-horizon, economically valuable real-world tasks across 13 industry clusters, finding current full pass rates below 1%.

Yiyou Sun, Xinyang Han, Weichen Zhang, Yuanbo Pang, Tianyu Wang, Yuhan Cao, Yixiao Huang, Chris Duroiu, H. M. Zhang, Jeffrey Lin, Weishu Zhang, Tyler Zeng, Ying Yan, Bo Liu, Hanson Wen, Mingyang Xu, Xiaoyuan Liu (4692781), Zimeng Chen, Weiyan Shi, Amanda Dsouza, Vincent Sunn Chen, Bryant, Patrick, Carl Boettiger, Yamini Rangan, Bradley Rothenberg, Kyle Steinfeld, Arvind Rao, Tapio Schneider, Georgios Yannakakis, Laure Zanna, Kaan Ozbay, Ida Sim, Tarek Zohdi, George Em Karniadakis, Jack Gallant, Teresa Head-Gordon, Yushan Li, Wenxi Deng, Tao Sun (91038), Huiqi Wang

Published Jun 3, 2026▲ 392 on Hugging Face Code ★ 1,083 arXiv ↗

78%

OverallHighly rated

OverallHighly ratedVote to see the scoreThe exact score shows once you've voted, so every vote is your own call. The first half of each home page shelf shows its scores.

Readers

–

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel11/20reviewers recommend it

lenient 5/5

medium 6/10

strict 0/5

AI panel?Vote to see what the 20 AI reviewers said

Panel consensus

ALE delivers a rigorous 1,000-task, expert-built taxonomy across 13 industry clusters with sub-1% pass rates, but its economic-impact framing remains unverified without sustained-cost harnesses or baseline transparency.

Abstract

Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and economically valuable workflows. This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long horizon, economically valuable, real world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts, ALE covers non-physical industries defined with reference to O*NET / SOC 2018 (the U.S. federal occupational taxonomy). It is organized around a task taxonomy with 55 sub fields grouped into 13 industry clusters covering 1K+ tasks. Current results show that the hardest tier remains far from saturated: across mainstream harness and backbone configurations, the average full pass rate is below 1%. ALE is designed as a living benchmark: its task pool grows continuously as new workflows and industries are onboarded. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for closing the gap between benchmark success and GDP relevant impact.