Tag
Deep Life Sci is an open source agentic assistant built for clinical and lab scientists, providing access to vast databases like ClinicalTrials.gov and PubMed with sub-agents for efficient document review.
The article introduces BenchBench-Protocol, a benchmark of 149 real-world wet-lab protocol-modification tasks to evaluate large language models' reasoning, with Claude Opus 5 scoring highest at 59.2%.
A paper published in Science Magazine demonstrates a broad range of life science research being conducted autonomously using agentic AI to accelerate discovery.
Anthropic announced Claude Science, an AI workbench for scientists, and revealed its own plans to develop drugs for neglected diseases using AI, entering a competitive field of AI-driven drug discovery.
OpenAI introduces LifeSciBench, a benchmark of 750 expert-authored tasks to evaluate AI systems on realistic life science research workflows, including evidence handling, analysis, and scientific reasoning.
Anthropic is reportedly closing access to life science research capabilities, a move that underscores growing safety concerns and policy shifts in AI research.
OpenAI’s new life-science model “GPT-Rosalind” inside Codex autonomously ranks asthma drug targets by orchestrating specialist sub-agents that merge genetics, transcriptomics, safety and IP data into a single evidence-backed decision.