Terminal-Bench
Terminal-Bench provides a suite of benchmarks for evaluating the capabilities of AI agents in terminal environments. It offers standardized tasks, leaderboards, and performance metrics to help researchers and developers assess and compare agent performance. The platform is open source and designed for the AI research community.
Open SourceApache-2.0WebCLICloud-managed
2.7kstars
1.2kforks
5features
2025since
Overview
5 featuresIn the LLM eval & observability space, Terminal-Bench takes a focused approach. It focuses on measuring and comparing the performance of AI agents in terminal-based tasks. Terminal-Bench is an open-source project aimed at AI researchers and agent developers. The project is open source (Apache-2.0). It ships for the web and the command line.
Behind Terminal-Bench is Nicholas Carlini, and it first shipped in 2025. Development happens publicly on GitHub with 2.7k stars and 496 commits in the last 90 days. Key capabilities include agent benchmarking, leaderboard, and task examples.
Summary written by a language model from the project’s public pages.
- Agent benchmarking
- Leaderboard
- Task examples
- Terminal challenges
- Performance metrics
Tags
agent-benchmarkingterminal-evaluationai-leaderboardcli-benchmarksagent-testing
AI capabilities
Code
Built with & integrations
Framework
Next.jsFastAPI
Hosting
Netlify
AI providers
anthropicopenaigoogle_geminimultiple
Runs on
BrowserCLICloud-managed
Detected from
- Next.js
- x-nextjs-prerender header · x-powered-by header · /_next/static/ in the HTML
- openai
- bgpt- in the HTML
- Netlify
- x-nf-request-id header
- multiple
- bLangChain in the HTML
- anthropic
- bclaude in the HTML · bclaude- in the HTML
- google_gemini
- bgemini- in the HTML
Trust & compliance
License
Apache-2.0
Verified signals
Indexing history
1What PulseGate has recorded for this listing
Frequently asked questions about Terminal-Bench
- What does Terminal-Bench do?
- Terminal-Bench focuses on measuring and comparing the performance of AI agents in terminal-based tasks. It is catalogued under LLM eval & observability on PulseGate.
- Who is Terminal-Bench for?
- Terminal-Bench is an open-source project built for AI researchers and agent developers.
- Does Terminal-Bench have a free plan?
- Yes — Terminal-Bench is open source under the Apache-2.0 license and free to use.
- What platforms does Terminal-Bench run on?
- Terminal-Bench runs on the web and the command line.
- Is Terminal-Bench still maintained?
- The GitHub repository shows 496 commits in the last 90 days.
- What are alternatives to Terminal-Bench?
- Similar projects tracked by PulseGate include agentbench-cli, benchflow, and ToolBench.agentbench-clibenchflowToolBench
- Who makes Terminal-Bench?
- Terminal-Bench is developed by Nicholas Carlini.
- When did Terminal-Bench launch?
- Terminal-Bench first shipped in 2025.
Similar projects
Closest matches by what these projects do