terminal-bench-1
A benchmark for LLMs on complicated tasks in the terminal
harbor-framework/terminal-bench-1
View on GitHub ↗A benchmark for LLMs on complicated tasks in the terminal
terminal-bench-1 grew +0.4% in the last 30 days, ranks 2nd of 52 in Domain-Specific Models, last commit 104 days ago.
Star trajectory
77 days tracked2026-08-072.6k stars today2026-10-23
Momentum
+0.4% in 30d, above the Domain-Specific Models median of +0.0%.
Maintenance
Last commit 104 days ago, fresher than the median of 324.5d.
How it compares in Domain-Specific Models
terminal-bench-1
2.6k
stars
+0.4% 30d
commit 104 days ago
Domain-Specific Models median
287.5
stars
+0.0% 30d
commit ~324.5d ago
Leader · FinGPT
21.4k
stars
+0.8% 30d
commit 30 days ago
Ranked 2nd of 52 by stars.
AI4Finance-Foundation/FinGPT21.4k-18.8k
harbor-framework/terminal-bench-12.6k
MetaGLM/FinGLM2.3k+335TigerResearch/TigerBot2.3k+344- Language
- Python
- License
- Apache License 2.0
- Contributors
- 94
- Forks
- 572
- Watchers
- 13
- Open issues
- 119
- Releases
- 0
- Created
- 2025-01-17
- Stars this week
- +5
You've seen where terminal-bench-1 stands today.
Get the moves before everyone else: the 5 Domain-Specific Models repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.