harbor-framework/
Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains
by Harbor Python Apache-2.0 licence 544 forks Created Jan 2026 View on GitHub
- Stars
- 893
- 7% of harbor-framework's stars
- Rank
- #73,798
- of 852,119 repos, top 9%
- In Python
- #13,416
- of 173,305 repos, top 8%
Among 852,119 repos
630–1k stars: 35,611 repos, including terminal-bench-science
top 50%top 10%top 1%top 0.1% 
Stars along the bottom, and repos in each band on a log scale
Quick stats
- Next rank
- +1 star to reach #73,714
- Next milestone
- +6,319 stars to reach the top 1%
- Popular
- One of 490,778 repos with 100+ stars