# JobBench: Aligning Agent Work With Human Will

arXiv: https://arxiv.org/abs/2605.26329 · HTML: https://mlsanity.com/paper/2605.26329/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 45 references that are in the map.
- First posted on arXiv 25 May 2026.

## Builds on (most cited first, 17 of 17)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?](https://mlsanity.com/paper/2403.07718/) (2024)
- [GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models](https://mlsanity.com/paper/2303.10130/) (2023)
- [GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks](https://mlsanity.com/paper/2510.04374/) (2025)
- [Future of Work with AI Agents: Auditing Automation and Augmentation Potential across the U.S. Workforce](https://mlsanity.com/paper/2506.06576/) (2025)
- [PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning](https://mlsanity.com/paper/2511.11562/) (2025)
- [OneMillion-Bench: How Far are Language Agents from Human Experts?](https://mlsanity.com/paper/2603.07980/) (2026)

## Built on by (most cited first, 10 of 10)

- [Kimi K3: Open Frontier Intelligence](https://mlsanity.com/paper/2607.24653/) (2026)
- [RRSI: Regularized Recursive Self-Improvement of Agent Harnesses](https://mlsanity.com/paper/2609.24972/) (2026)
- [Agent Skills Should Go Beyond Text: The Case for Visual Skills](https://mlsanity.com/paper/2606.01414/) (2026)
- [GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks](https://mlsanity.com/paper/2608.03764/) (2026)
- [FinProBench: Evaluating Financial AI Agents with Role-Grounded Rubrics Derived from Professional Deliverables](https://mlsanity.com/paper/2608.04077/) (2026)
- [Raven: The Harness of Harnesses for Composable Agentic Intelligence](https://mlsanity.com/paper/2609.33439/) (2026)
- [MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement](https://mlsanity.com/paper/2610.11959/) (2026)
- [Atria Dawn: The Dawn of Agentic Superintelligence](https://mlsanity.com/paper/2609.15818/) (2026)
- [WorkGenesis: Building the Worlds That Teach Agents to Work](https://mlsanity.com/paper/2609.39325/) (2026)
- [REMORY: Learning Residual Memory for Context Compaction](https://mlsanity.com/paper/2610.11287/) (2026)

## Abstract (arXiv)

Current benchmarks for occupational AI agents are scoped primarily by economic values, telling a replacement story. We introduce JobBench, which evaluates AI agents on the workflows that experts identify as high-priority for delegation, empowering humans based on their needs instead of replacing them with GDP value. JobBench covers 130 agentic tasks across 35 occupations. Each task is packaged as a workspace of heterogeneous reference files, requiring the agent to reason through the cluttered information streams of real professional work. Outputs are graded by a fact-anchored chain of rubrics, averaging 35.6 binary criteria per task. We evaluate 36 models; the strongest, Claude Opus~4.7 under Claude Code, reaches only 45.9 %. We hope JobBench shifts the community's target labour-market effect from replacement to enhancement: building agents that do what humans actually want delegated, not only what is most economically valuable.