Terminal-Bench-Science: Evaluating AI agents on scientific research workflows
Stanford researchers have introduced Terminal-Bench-Science, a new benchmark designed to evaluate AI agents on complex, real-world scientific research workflows. The initiative aims to foster the development of AI assistants capable of handling technically demanding tasks in various scientific disciplines.
Why it matters
This represents a shift toward evaluating AI on practical, expert-level scientific utility rather than standardized textbook problems, potentially accelerating research discovery.
Terminal-Bench-Science evaluates AI agents on workflows from researchers' own work. Scientists, not model developers or data vendors, set the bar for scientific capability in AI.
Terminal-Bench-Science is a benchmark led by researchers at Stanford University and built by the team behind Terminal-Bench in collaboration with domain experts from a range of scientific disciplines and research institutions around the world. It measures the AI agent capabilities through a diverse set of challenging, expert-curated workflows drawn from scientific research.
Terminal-Bench-Science is a continuous benchmark that evolves alongside frontier AI, creating a feedback loop between scientific needs and AI development. Our first release includes 70 tasks from the life, physical, Earth, mathematical, and engineering sciences. The strongest model evaluated, Claude Opus 5, achieves a 30% resolution rate on Terminal-Bench-Science 0.1.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in