Open Philanthropy recommended a grant of €786,060 (approximately $828,979 at the time of conversion) over two years to Friedrich Schiller University Jena to support the development of a benchmark assessing whether LLM agents can solve organic structural analysis problems in chemistry. The project will be led by Dr. Kevin Jablonka.
This grant was funded via a request for proposals for projects benchmarking LLM agents on consequential real-world tasks. This falls within our focus area of potential risks from advanced artificial intelligence.