Terminal-Bench-Science Aims to Fill the Measurement Gap in Science
BenBlaiszik · x · 2026-08-28
Science is the foundation of human progress, and accelerating scientific workflows is a massive lever. Terminal-Bench-Science aims to fill the measurement gap by evaluating the frontier of agent capabilities across life, physical, mathematical, earth, and engineering sciences.
Related event: Stanford-led Terminal-Bench-Science Debuts; Claude Opus 5 Passes Just 30%(19 posts)→
More from Research
- OpenAI gives $5M to Simons Foundation's $15M push to help mathematicians navigate AI-era results — OpenAI · 2026-10-15
- DeepPhylo infers phylogenetic trees without unrealistic evolutionary assumptions — anshulkundaje · 2026-10-15
- Wander preprint explores graph foundation models via shared objective and random-walk interface — mmbronstein · 2026-10-15
- CHI Reviewer: AI Slop Is Real, but Unusually Rigorous Papers Still Getting Through — IanArawjo · 2026-10-15
- Into the Unknown: CMU benchmark finds 114 of 135 AI-written research papers fail integrity checks — arankomatsuzaki · 2026-10-15
- Benchling launches Science Foundries: multiplayer agent swarms for end-to-end science workflows — nlarusstone · 2026-10-15