{
  "id": 11849,
  "url": "https://arxiv.org/abs/2607.16057v1",
  "title": "Frontier AI performance across the business disciplines: a case-grounded benchmark of knowledge work and analytical reasoning",
  "summary": "Large language models (LLMs) are improving rapidly as reflected in benchmark scores, yet these AI benchmarks largely test capabilities such as factual recall, narrow question answering, mathematical problem-solving, and coding and agentic tool-use. What remains poorly measured is AI progress on the analytical knowledge work white-collar professionals perform daily, including synthesizing complex information, exercising judgment under uncertainty and incomplete information, applying strategic and",
  "authors": "Ajay Patel, Kartik Hosanagar, Ramayya Krishnan, Chris Callison-Burch, Karim Lakhani, Mitch Weiss",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-17T15:34:51.000Z",
  "fetched_at": "2026-07-20T05:10:09.534Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/11849",
  "original_url": "https://arxiv.org/abs/2607.16057v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}