{"slug":"terminal-bench-1","name":"terminal-bench-1","category":"eval","categoryName":"Evaluation, red-teaming & guardrails","audience":["ai-era"],"primary":"ai-era","openClosed":"open","pricing":"open-source","license":"Apache-2.0","maintained":"yes","officialUrl":"https://www.tbench.ai","repo":"https://github.com/harbor-framework/terminal-bench-1","latestVersion":"","latestRelease":"","stars":2605,"starsAsOf":"2026-10-22","description":"A benchmark for LLMs on complicated tasks in the terminal","descriptionZh":"终端任务 agent 基准","callMethods":["CLI"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":[],"language":"Python","lastPush":"2026-07-11","formerly":"laude-institute/terminal-bench","packages":[],"recentVersions":[],"alternatives":["promptfoo","openai-evals","deepeval","ragas","lm-evaluation-harness","opencompass","swe-bench","giskard-oss"],"stacks":[],"scenarios":["evaluate-and-monitor"],"problems":[],"reasonZh":"终端任务基准","sources":["priority","oss","github-pool"],"record":"https://aimap.page/api/v1/software/terminal-bench-1.json","pages":{"en":"https://aimap.page/en/software/terminal-bench-1/","zh-hans":"https://aimap.page/zh-hans/software/terminal-bench-1/"}}