Terminal-Bench-Science
terminal-bench-science.ai- Category
- Developer Tools
- Listed in
- Find AI benchmarks
- Type
- TOOL
- GitHub
- 832 stars
- Latest release
- v0.1.0
- Date
About
Research workflows authored and reviewed by domain experts across the life, physical, earth, mathematical, and engineering sciences, which agents complete in a terminal. It is a continuous benchmark with tagged releases, so compare the same release, harness, and trial count.
Why it made the leaderboard
Compare the task, benchmark version, harness, and grading method before using model scores to choose a model.
Intel on Terminal-Bench-Science
Tags
benchmarkevaluation
Media
Comments (0)
No comments yet
Editorially curated, with community endorsements as a secondary signal. Corrections welcome.