Interpreting Dual-Use Biology Benchmarks for Frontier AI: Measurement, Saturation, and Generational Analysis
Grant Ellison, Jeffrey Lee, Barbara Del Castello, Sunishchal Dev, Brady, Kyle · RAND Corporation eBooks · 2026
The authors use item response theory and an interpretive taxonomy to address the motivating question: “What can benchmark data reveal about what artificial intelligence (AI) can do now that it could not do before?” Findings indicate that many benchmark tasks are no longer informative, but there is a discriminating frontier of tasks, with recent gains in performance concentrated in difficult tasks theorized to be relevant to real-world risks.