JobBench: Aligning Agent Work With Human Will

Researchers introduced JobBench, a new benchmark that evaluates AI agents on 130 tasks across 35 occupations based on workflows experts prioritize for delegation. The benchmark assesses models using fact-anchored rubrics averaging 35.6 criteria per task, with the top-performing model, Claude Opus 4.7 under Claude Code, achieving only 45.9%. JobBench aims to shift AI development from replacing workers to enhancing human capabilities by focusing on tasks people actually want delegated rather than those with the highest economic value.

arXiv:2605.26329v1 Announce Type: new Abstract: 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.