TUA-Bench：通用终端使用代理的基准测试

摘要

随着大语言模型和相关框架的持续进步，运行在终端中的智能体正日益具备执行编码任务之外更广泛的通用计算机使用能力。然而，现有基准测试未能充分评估通用终端计算机使用智能体（TUA）：通用计算机使用基准主要针对图形用户界面（GUI），而基于终端的基准则主要侧重于历史上与命令行紧密相关的技术和编程工作流程。我们引入了TUA-Bench，这是一个面向终端使用智能体的通用基准测试。TUA-Bench包含五个任务族中的120个真实世界任务，涵盖日常数字活动——包括文档编辑、电子邮件管理和实时网络信息检索——以及与博士级领域专家共同设计的、需要专业软件支持的科研与工程工作流程。这一广度使TUA-Bench区别于以往专注于命令行或特定领域的基准测试。每个任务均为人工设计，在一个配有确定性设置脚本的真实终端中运行，并通过基于执行的评分协议进行评估。我们发现，最强的前沿智能体——使用最大推理努力的Claude Code（基于Claude Opus 4.8）——取得了65.8%的整体性能，在两条轨道上均存在显著差距。通过提供对终端使用能力的广泛且真实的评估，TUA-Bench旨在推动从狭窄、特定任务的助手向能够在多样化数字环境中可靠运行的通用智能体的转变。

English

As large language models and harness frameworks continue to advance, agents operating in terminals are increasingly capable of performing a broader range of general computer-use tasks beyond coding. However, existing benchmarks do not adequately evaluate general-purpose terminal computer-use agents (TUAs): general computer-use benchmarks primarily target graphical user interfaces (GUIs), whereas terminal-based benchmarks largely emphasize technical and programming-centric workflows historically native to the shell. We introduce TUA-Bench, a general-purpose benchmark for terminal-use agents. TUA-Bench includes 120 real-world tasks across five task families, covering routine digital activities-including document editing, email management, and live-web information seeking-as well as scientific and engineering workflows co-designed with PhD-level domain experts that require specialized software. This breadth distinguishes TUA-Bench from prior shell-focused or domain-specific benchmarks. Each task is manually designed, runs in a real terminal with a deterministic setup script, and is evaluated by an execution-based scoring protocol. We find that the strongest frontier agent, Claude Code with Claude Opus 4.8 max reasoning effort, achieves 65.8% overall performance, with substantial gaps across both tracks. By providing a broad and realistic evaluation of terminal-use capabilities, TUA-Bench aims to accelerate the transition from narrow, task-specific assistants to general-purpose agents capable of operating reliably across diverse digital environments.