ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity

Large language models (LLMs) are rapidly acquiring capabilities relevant to biological research, from literature synthesis to interpretation of experimental data. Increasingly, LLM agents can also perform in silico biology tasks that previously required experienced human biologists. These emerging AI capabilities offer new opportunities for scientific discovery and biomedical advances, but they also shift the landscape of biosecurity risks. To address this, we introduce the Agentic Bio-Capabilities Benchmark (ABC-Bench), a suite of tasks to measure agentic biosecurity-relevant capabilities. ABC-Bench evaluates LLM agents on both benign and dual-use biology tasks: writing code to operate liquid handling robots, designing DNA fragments for in vitro assembly, and evading DNA synthesis screening. These tasks require a combination of biology and software expertise. All tested LLM agents outperformed the median expert human baseliner on all three tasks. Agents performed highly on tasks drawing on published knowledge and well-documented protocols, and more weakly on a task requiring novel bioinformatics reasoning. In three wet-lab validation experiments, we found that OpenAI’s o4-mini-high produced scripts that, when run on an OpenTrons liquid handling robot, successfully assembled DNA with expected sequences.

Emerging AI capabilities offer new opportunities for scientific discovery and biomedical advances, but they can also enable biosecurity-related misuse. We introduce the Agentic Bio-Capabilities Benchmark (ABC-Bench), a suite of evaluations to measure biosecurity-relevant biological and software capabilities. We find that leading LLMs outperform PhD biologists on all tasks–Liquid-Handling Robot, Fragment Design, and Screening Evasion—and can write code that successfully assembles target DNA on an OpenTrons robot. These findings underscore the need for thoughtful mitigations to balance beneficial research with safety concerns.