DESNZ & DSIT Group Commercial Tender Result

AISI ChemBio - LLM Benchmarking (Chem)-AISI requires a Supplier to help develop it evaluations related to chemistry and biology (CB). The Supplier will help deploy and expand its automated benchmarking suite and support its human uplift studies related to biological capabilities. Supplier(s) will develop questions or tasks, develop grading rubrics, and provide expert human baselines and expert human grading. For each deliverable, AISI will provide detailed guidance.