AI Agent Benchmark for Real-World Professional Workflows
Agents' Last Exam evaluates AI agents on long-horizon professional workflows with verifiable outcomes across industries such as finance, robotics, bioinformatics, media, and more.
AI Agent Benchmark for Real-World Professional Workflows 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, comp
saved by
related reading
- [2606.05405] Agents' Last Examarxiv.org
- CAD Arena · Normal Researchnormal.ai
- AI Model & API Providers Analysis | Artificial Analysisartificialanalysis.ai
- Measuring the performance of our models on real-world tasks | OpenAIopenai.com
- EdgeBench | Scaling Laws of Environment Learningedge-bench.org
- Senior SWE-Benchsenior-swe-bench.snorkel.ai
- Measuring AI Ability to Complete Long Tasks - METRmetr.org
- Measuring AI Ability to Complete Long Software Tasksarxiv.org
- benchmarks.bio — Agentic benchmarks on messy, real-world biological databenchmarks.bio
- ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering | alphaXivalphaxiv.org
- Center for Responsible, Decentralized Intelligence at Berkeleyrdi.berkeley.edu
- Agent Evaluation: A Detailed Guidecameronrwolfe.substack.com