terminal-bench-science
Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains
harbor-framework/terminal-bench-science
View on GitHub ↗Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains
terminal-bench-science grew +20.9% in the last 30 days, ranks 93rd of 442 in Research & Deep Research, actively maintained, last commit today.
Star trajectory
79 days tracked2026-08-07759 stars today2026-10-25
Momentum
+20.9% in 30d, above the Research & Deep Research median of +0.7%.
Maintenance
Last commit today, fresher than the median of 40d.
How it compares in Research & Deep Research
terminal-bench-science
759
stars
+20.9% 30d
commit today
Research & Deep Research median
272.5
stars
+0.7% 30d
commit ~40d ago
Leader · autoresearch
98.5k
stars
+1.9% 30d
commit 213 days ago
Ranked 93rd of 442 by stars.
shuxiachai/academic-commercialization-agent773-14WantongC/journal-adapt-writing-skill765-6
harbor-framework/terminal-bench-science759
retkowsky/Azure-AIGEN-demos754+5marella/chatdocs739+20- Language
- Python
- License
- Apache License 2.0
- Contributors
- 73
- Forks
- 498
- Watchers
- 5
- Open issues
- 103
- Releases
- 1
- Created
- 2026-01-25
- Stars this week
- +28
You've seen where terminal-bench-science stands today.
Get the moves before everyone else: the 5 Research & Deep Research repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.