BioSecBench-Function: A Verifiable Benchmark for Reasoning about Biological Function from Experimental Data
Dianzhuo Wang, Qian Xu, Arjun Banerjee, Rishi Jain, Aakarsh Vermani, Jonathan Felix, Gage Moreno, Faisal AlZaben, Nicholas Keul, Evan Seeyave, Harmon Bhasin
The paper introduces BioSecBench-Function, a benchmark for assessing AI agents' ability to infer biological function from experimental data, showing varying performance across models and tasks.
bioRxiv · Sep 8, 2026 · PreprintBiophysics