AI News HubLIVE
In-site rewrite3 min read

Agents' Last Exam: AI Agent Benchmark for Real-World Professional Workflows

Agents' Last Exam is a large-scale benchmark built by Berkeley RDI and over 300 industry experts, covering 55 sub-industries and 1,500+ tasks to evaluate AI agents on long-horizon, economically valuable, verifiable real-world workflows. It measures agent performance in professional software like Adobe After Effects, Siemens NX, and Unreal Engine across animation, engineering, game development, manufacturing, architecture, and neuroscience.

SourceHacker News AIAuthor: gurjeet

Agents' Last Exam

Challenge and measure AI agents on economically valuable and real-world tasks.

Agents' Last Exam is building the largest-scale, broadest-coverage agent evaluation benchmark to date, measuring performance on long-horizon, economically valuable tasks with verifiable outcomes. Led by Berkeley RDI and 300+ industry experts, it now spans all 55 targeted sub-industries covering most major fields of professional work performed on a computer, with 1,500+ tasks collected toward a 5,000-task target, keeping scores objective, comparable, and meaningful across domains.

GitHub

LeaderboardAgent traces

arXiv

Contribute a TaskOpen for co-authorship

Motion & VFX

Agents complete animation and visual effects production tasks in Adobe After Effects.

Animation

3D Modeling

Agents perform 3D model creation and editing tasks in Siemens NX.

Engineering

Game Development

Scene setup, asset placement, and rendering tasks in Unreal Engine.

Game Dev

Mold Flow Analysis

Simulation and mold flow analysis tasks in Moldex3D manufacturing software.

Manufacturing

Architectural Modeling

3D modeling and energy analysis workflows in Rhino 3D for urban design in Zurich.

Architecture

Brain Imaging

Neuroimaging analysis and brain structure segmentation tasks in FSLeyes.

Neuroscience

Motion & VFX

Agents complete animation and visual effects production tasks in Adobe After Effects.

Animation

3D Modeling

Agents perform 3D model creation and editing tasks in Siemens NX.

Engineering

Game Development

Scene setup, asset placement, and rendering tasks in Unreal Engine.

Game Dev

Mold Flow Analysis

Simulation and mold flow analysis tasks in Moldex3D manufacturing software.

Manufacturing

Architectural Modeling

3D modeling and energy analysis workflows in Rhino 3D for urban design in Zurich.

Architecture

Brain Imaging

Neuroimaging analysis and brain structure segmentation tasks in FSLeyes.

Neuroscience

Motion & VFX

Agents complete animation and visual effects production tasks in Adobe After Effects.

Animation

3D Modeling

Agents perform 3D model creation and editing tasks in Siemens NX.

Engineering

Game Development

Scene setup, asset placement, and rendering tasks in Unreal Engine.

Game Dev

Mold Flow Analysis

Simulation and mold flow analysis tasks in Moldex3D manufacturing software.

Manufacturing

Architectural Modeling

3D modeling and energy analysis workflows in Rhino 3D for urban design in Zurich.

Architecture

Brain Imaging

Neuroimaging analysis and brain structure segmentation tasks in FSLeyes.

Neuroscience

Motion & VFX

Agents complete animation and visual effects production tasks in Adobe After Effects.

Animation

3D Modeling

Agents perform 3D model creation and editing tasks in Siemens NX.

Engineering

Game Development

Scene setup, asset placement, and rendering tasks in Unreal Engine.

Game Dev

Mold Flow Analysis

Simulation and mold flow analysis tasks in Moldex3D manufacturing software.

Manufacturing

Architectural Modeling

3D modeling and energy analysis workflows in Rhino 3D for urban design in Zurich.

Architecture

Brain Imaging

Neuroimaging analysis and brain structure segmentation tasks in FSLeyes.

Neuroscience

Motion & VFX

3D Modeling

Game Development

Mold Flow Analysis

Architectural Modeling

Brain Imaging

Motion & VFX

3D Modeling

Game Development

Mold Flow Analysis

Architectural Modeling

Brain Imaging

What makes Agents' Last Exam different

Broadest CoverageVerifiable OutcomesLong-HorizonEconomically Valuable

55

Sub-Industries Covered

1.5K+

Tasks Collected

300+

Experts

Co-led by

×

Contributors & Partners from

Academic Institutions

MIT

Harvard

Stanford

UC Berkeley

Oxford

CMU

Caltech

ETH Zurich

Yale

Columbia

UPenn

Cornell

Brown

Johns Hopkins

NIH

UCLA

UCSF

NYU

U Michigan

U Washington

Georgia Tech

USC

UIUC

WashU

U Melbourne

UC San Diego

UC Santa Barbara

UC Irvine

UW-Madison

Emory

UNC

McGill

U Waterloo

Boston University

U Helsinki

Monash

U Colorado

UC Santa Cruz

UC Riverside

Northeastern

Syracuse

Lehigh

UT Southwestern

Texas A&M

MIT

Harvard

Stanford

UC Berkeley

Oxford

CMU

Caltech

ETH Zurich

Yale

Columbia

UPenn

Cornell

Brown

Johns Hopkins

NIH

UCLA

UCSF

NYU

U Michigan

U Washington

Georgia Tech

USC

UIUC

WashU

U Melbourne

UC San Diego

UC Santa Barbara

UC Irvine

UW-Madison

Emory

UNC

McGill

U Waterloo

Boston University

U Helsinki

Monash

U Colorado

UC Santa Cruz

UC Riverside

Northeastern

Syracuse

Lehigh

UT Southwestern

Texas A&M

Industries

Goldman Sachs

JPMorgan

Morgan Stanley

PIMCO

Adobe

Oracle

Hippocratic AI

HubSpot

Brix

Photon Fund

Snorkel AI

UniPat AI

TCCI

Goldman Sachs

JPMorgan

Morgan Stanley

PIMCO

Adobe

Oracle

Hippocratic AI

HubSpot

Brix

Photon Fund

Snorkel AI

UniPat AI

TCCI

Advisory Committee

George Em KarniadakisProfessor @Brown

Applied Mathematics

NAE MemberPINN · DeepONet co-creator

Tapio SchneiderProfessor @Caltech

Climate Dynamics

CliMA founderGoogle Principal Scientist

Teresa Head-GordonChancellor's Prof. @UC Berkeley

Computational Chemistry

ACS / AIMBE FellowNIH AViDD Center PI

Laure ZannaProfessor @NYU Courant

Ocean & Climate Science

Keller ChairNSF LEAP co-director

Jack GallantChancellor's Prof. @UC Berkeley

Computational Neuroscience

Brain-decoding pioneerWheeler Center co-director

Tarek ZohdiAssoc. Dean @UC Berkeley

Computational Mechanics

Humboldt Research AwardFormer USACM President

Ida SimChief Research Informatics Officer @UCSF

Clinical Research Informatics

NAM MemberVivli co-founder

Arvind RaoProfessor @U Michigan

Biomedical Informatics

AAAS FellowAMIA Fellow (FAMIA)

Kaan OzbayDirector, C2SMART @NYU

Transportation

NSF CAREER AwardGlobal Network Professor

Carl BoettigerAssoc. Professor @UC Berkeley

Ecological Forecasting

rOpenSci co-founderESA Early Career Fellow

Kyle SteinfeldAssoc. Professor @UC Berkeley

Computational Design

MDes DirectorHellman Fellow

Yamini RanganCEO @HubSpot

CRM & Marketing Automation

Former Dropbox CCO

Bradley RothenbergCEO @nTop

Engineering Design

Implicit modeling CADNASA, Lockheed, Honeywell

Why Contribute - Help Set the Standard for Agent Evaluation in Your Industry

Shape evaluation standards, publish research, and earn recognition.

Insight into Agents in Industry

See exactly how AI agents handle real workflows in industry, and where they fall short.

Learn more →

Co-authorship on Manuscript

Qualifying contributors receive co-authorship credit on the research publication.

Learn more →

Monetary Awards

High-impact contributions are recognized with monetary awards from our $100K+ funding pool.

Learn more →

Choose How You'd Like to Contribute

For Domain Experts

Contribute domain expertise and real workflow data - no coding required.

Contribute a Task

For Researchers & Engineers

Turn real workflows into challenging, reproducible agent benchmarks: setup, execution, and evaluation.

Join Research

FAQ

Common questions about software access, authorship, venues, and timeline.

FAQ page →

Contact

For inquiries, reach out to the team directly.

[email protected]

Stay Updated

Subscribe for announcements, benchmark releases, and updates.

Join mailing list →