Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark
This work addresses the need for assessing AI capabilities in virology, highlighting dual-use risks and governance gaps, though it is incremental as it focuses on benchmarking rather than novel AI methods.
The authors introduced the Virology Capabilities Test (VCT), a benchmark to evaluate large language models' ability to troubleshoot complex virology laboratory protocols, finding that the top-performing model achieved 43.8% accuracy, outperforming 94% of expert virologists.
We present the Virology Capabilities Test (VCT), a large language model (LLM) benchmark that measures the capability to troubleshoot complex virology laboratory protocols. Constructed from the inputs of dozens of PhD-level expert virologists, VCT consists of $322$ multimodal questions covering fundamental, tacit, and visual knowledge that is essential for practical work in virology laboratories. VCT is difficult: expert virologists with access to the internet score an average of $22.1\%$ on questions specifically in their sub-areas of expertise. However, the most performant LLM, OpenAI's o3, reaches $43.8\%$ accuracy, outperforming $94\%$ of expert virologists even within their sub-areas of specialization. The ability to provide expert-level virology troubleshooting is inherently dual-use: it is useful for beneficial research, but it can also be misused. Therefore, the fact that publicly available models outperform virologists on VCT raises pressing governance considerations. We propose that the capability of LLMs to provide expert-level troubleshooting of dual-use virology work should be integrated into existing frameworks for handling dual-use technologies in the life sciences.