Frontier AI Performance Across the Business Disciplines: A Case-Grounded Benchmark of Knowledge Work and Analytical Reasoning

This paper introduces BusinessCaseBench, a benchmark built from hundreds of questions drawn from business-school cases across 18 disciplines. Each question is evaluated against a rubric derived from an expert-written instructor solution. The benchmark targets analytical knowledge work that conventional evaluations often under-measure, including synthesis, judgment under uncertainty, strategic and adversarial reasoning, trade-off analysis, and defensible structured writing. The abstract reports that frontier AI models already score highly against instructor rubrics and that performance within one model family improved substantially over two years. It discusses consequences for business education and entry-level professional work.