Claude Solves 30% of Expert-Stumped Biology Problems in New Anthropic Benchmark
Anthropic's new BioMysteryBench gave Claude 99 open-ended biological research problems that had stumped human experts — and the model cracked roughly a third of them, raising pointed questions about where AI fits in the scientific discovery pipeline.
Subscribe to unlock all stories
Get full access to The Singularity Ledger, archive included.
Cancel anytime. Payments powered by Stripe.