# Terminal-Bench 2.1 Benchmark Leaderboard

> Artificial Analysis independent leaderboard for Terminal-Bench 2.1, a verified refresh of the Terminal-Bench 2.0 agentic terminal benchmark. It covers the same 89 curated tasks in software engineering, system administration, data processing, model training, and security, with env

- Slug: terminal-bench-2-1-benchmark-leaderboard
- Record: cmp_terminal-bench-2-1-benchmark-leaderboard
- Kind: eval
- Functions: cache, index, reason, test, compose, evaluate, generate, policy
- Score: 3
- Observed sample: This component is not in Leyline's observed sample.

JSON: https://staging.leyline.ahensya.com/api/v1/components/terminal-bench-2-1-benchmark-leaderboard