Large language models and agents have achieved remarkable progress in code generation. However, existing benchmarks focus on isolated function/class-level generation (e.g., ClassEval) or modifications to existing codebases (e.g., SWE-Bench), neglecting complete microservice repository generation that reflects real-world 0-to-1 development workflows. To bridge this gap, we introduce RepoGenesis, the first multilingual benchmark for repository-level end-to-end web microservice generation, comprising 106 repositories (60 Python, 46 Java) across 18 domains and 11 frameworks, with 1,258 API endpoints and 2,335 test cases verified through a "review-rebuttal" quality assurance process. We evaluate open-source agents (e.g., DeepCode) and commercial IDEs (e.g., Cursor) using Pass@1, API Coverage (AC), and Deployment Success Rate (DSR). Results reveal that despite high AC (up to 73.91%) and DSR (up to 100%), the best-performing system achieves only 23.67% Pass@1 on Python and 21.45% on Java, exposing deficiencies in architectural coherence, dependency management, and cross-file consistency. Notably, GenesisAgent-8B, fine-tuned on RepoGenesis (train), achieves performance comparable to GPT-5 mini, demonstrating the quality of RepoGenesis for advancing microservice generation. We release our benchmark at https://github.com/microsoft/DKI_LLM/tree/main/RepoGenesis.

翻译：大型语言模型与智能体在代码生成领域已取得显著进展。然而，现有基准测试主要关注孤立的函数/类级别生成（如ClassEval）或对现有代码库的修改（如SWE-Bench），忽略了反映真实世界从零到一开发流程的完整微服务仓库生成。为填补这一空白，我们提出了RepoGenesis，这是首个面向仓库级端到端Web微服务生成的多语言基准测试，包含涵盖18个领域和11种框架的106个仓库（60个Python，46个Java），包含1,258个API端点和2,335个测试用例，并通过“评审-复审”质量保证流程进行验证。我们使用Pass@1、API覆盖率（AC）和部署成功率（DSR）评估了开源智能体（如DeepCode）和商业IDE（如Cursor）。结果显示，尽管AC（最高达73.91%）和DSR（最高达100%）表现优异，但性能最佳的系统在Python上仅达到23.67%的Pass@1，在Java上为21.45%，暴露出其在架构一致性、依赖管理和跨文件协调性方面的不足。值得注意的是，基于RepoGenesis（训练集）微调的GenesisAgent-8B模型，其性能可与GPT-5 mini相媲美，这证明了RepoGenesis在推动微服务生成研究方面的质量。我们已在https://github.com/microsoft/DKI_LLM/tree/main/RepoGenesis发布本基准测试。