LifeSciBench: AI Fails 64% of Life-Science Tasks 2026
June 24, 2026
OpenAI's LifeSciBench grades AI on 750 expert-written life-science research tasks. Its best model, GPT-Rosalind, passes just 36.1% — here's what that means.
#gpt-rosalind
GPT-Rosalind: OpenAI's Life Sciences AI Upgrade (2026)
June 5, 2026
OpenAI's June 2026 GPT-Rosalind update beats GPT-5.5 on drug-discovery benchmarks while using fewer tokens, adds Codex plugins, and partners with Novo Nordisk.
GPT-Rosalind: OpenAI's 2026 Life Sciences AI Model
April 18, 2026
OpenAI's GPT-Rosalind is its first frontier model built for drug discovery, biology, and translational medicine. Benchmarks, partners, and access details.