Terminal-Bench-Science 0.1 A
AI benchmark · Agentic
What is Terminal-Bench-Science 0.1?
Terminal-Bench-Science 0.1 measures AI agents' resolution rate on 70 expert-curated, verifiable scientific research workflows run in terminal environments across life, physical, earth, mathematical, and engineering sciences.
Science mostly
“Terminal-Bench-Science 0.1 includes 70 tasks across the life, physical, earth, mathematical, and engineering sciences.”
terminal-bench-science.ai/announcement ↗“LIFE SCIENCES19Biology8Medicine & Health6Neuroscience4Ecology & Evolution1”
terminal-bench-science.ai/announcement ↗“MATHEMATICAL SCIENCES17Applied Mathematics & Scientific Computing6Operations Research & Optimization5Formal Mathematics & Theorem Proving3Statistics3”
terminal-bench-science.ai/announcement ↗
Who built Terminal-Bench-Science 0.1
Led by Stanford University.
Lineage
Benchmarks this one is built on and built from: versions, subsets, extensions and the indexes that combine them.
Built on
Terminal-Bench original
Terminal-Bench-Science earlier version
Tier A
Widely used: a lab reports it, or 50 or more models are scored on it.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- 12 models scored
- reported by Anthropic
- in curated RL directories (2 pts)
On X · well regarded, moderate buzz, from 12 posts about Terminal-Bench-Science 0.1 in the last month
Labs cite Terminal-Bench-Science 0.1 in model launches, notably Anthropic's Fable 5.2 at 74.6%; others report local runs and anticipate a harder successor.
How we got to tier A
- Adoption: 12 models scored; reported by Anthropic. Tier A.
- On X: well regarded, moderate buzz. “Labs cite Terminal-Bench-Science 0.1 in model launches, notably Anthropic's Fable 5.2 at 74.6%; others report local runs and anticipate a harder successor.” No move.
- In curated RL directories: 2 points, a floor of C.
- Confirmed: a line from its own site or paper places it.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Where Terminal-Bench-Science 0.1 sits
Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-11-16 snapshot.