摘要：现实世界中的数据科学涉及长周期工作流，涵盖数据整理、探索、建模、可视化和验证，并要求在真实操作环境中协调使用 notebook、IDE、终端、浏览器和数据库等工具。然而，现有基准缺少真实计算机交互，也未评估 Agent 能否在逼真的计算环境中执行完整的端到端数据科学工作流，因此未能捕捉数据科学实践中多阶段、多工具协作的特性。我们提出 DSAgentBench，这是首个评估 Agent 能否在真实计算机环境内自动化完整数据科学工作流的基准。DSAgentBench 包含 275 项多样化任务，覆盖整个数据科学生命周期，反映了实践中所需的复杂性与工具协调能力。每项任务都要求 Agent 基于中间输出作出决策并协调使用工具，同时配备确定性评估器，用于验证分析正确性、可视化输出和模型性能，而非仅检查代码是否执行。我们对 15 个闭源和开源模型开展的大规模实验显示，即使是最强的 Agent——Claude-4.6-Sonnet，任务成功率也仅为 56.70%；所有开源 Agent 的成功率均低于 1%，并且经常在工具编排、操作系统环境定位和多步骤推理上失败。这些结果揭示了当前 Agent 系统与真实数据科学工作流之间存在显著能力差距，使 DSAgentBench 成为开发具备环境定位能力、可验证且自主的数据科学 Agent 的基础。我们在此 HTTPS 链接发布 DSAgentBench。

Abstract:Real-world data science involves long-horizon workflows that span data wrangling, exploration, modeling, visualization, and validation, and require coordinated use of tools such as notebooks, IDEs, terminals, browsers, and databases within real operating environments. Yet existing benchmarks lack real-computer interaction and do not evaluate whether agents can execute complete end-to-end data-science workflows in realistic computing environments, failing to capture the multi-stage, multi-tool nature of data-science practice. We introduce DSAgentBench, the first benchmark to evaluate whether agents can automate full data-science workflows inside real computer environments. DSAgentBench contains 275 diverse tasks covering the entire data-science life-cycle, reflecting the complexity and tool coordination required in practice. Each task requires grounding decisions in intermediate outputs and coordinated tool use, and includes a deterministic evaluator that verifies analytical correctness, visual outputs, and model performance rather than code-only execution. Our extensive experiments with 15 closed- and open-source models show that even the strongest agent, Claude-4.6-Sonnet, achieves only 56.70% task success, while all open-source agents remain below 1%, frequently failing at tool orchestration, OS grounding, and multi-step reasoning. These results reveal a substantial capability gap between current agentic systems and real data-science workflows, positioning DSAgentBench as a foundation for developing grounded, verifiable, autonomous data-science agents. We release DSAgentBench at this https URL.