Terminal-Bench-Science 0.1 releases 70 cross-domain science tasks

sanmikoyejo · x · 2026-08-28

Terminal-Bench-Science 0.1 features 70 tasks spanning the life, physical, earth, mathematical, and engineering sciences. Each task is contributed by a researcher porting their own real workflows into challenging agentic tasks.

Related event: Stanford-led Terminal-Bench-Science Benchmark Released; Top Model Passes Only 30%(17 posts)→

Original post →

More from Research

Research channel →