RustRepoTrans: Repository-level Code Translation Benchmark Targeting Rust

TL;DR

This paper introduces RustRepoTrans, a new benchmark for repository-level code translation into Rust, evaluating LLMs' ability to handle complex, context-aware, incremental translation tasks across multiple source languages.

Contribution

It presents the first repository-level code translation benchmark targeting Rust, emphasizing incremental translation and context handling, and evaluates seven LLMs' performance on this challenging task.

Findings

DeepSeek-R1 achieves 51.5% Pass@1 on RustRepoTrans.

Performance drops by 22.2% when handling repository context.

Existing models struggle with repository-level, incremental translation scenarios.

Abstract

Recent advancements in large language models (LLMs) have demonstrated impressive capabilities in code translation, typically evaluated using benchmarks like CodeTransOcean and RepoTransBench. However, dependency-free benchmarks fail to capture real-world complexities by focusing primarily on simple function-level translations and overlooking repository-level context (e.g., dependencies). Full-repository translation benchmarks significantly exceed the current capabilities of existing models, resulting in performance bottlenecks that fail to provide actionable insights for guiding model development. Furthermore, existing benchmarks do not account for the scenario of incrementally translating new or modified modules from the source to the target language, which demands careful handling of repository-level contexts such as dependencies, cross-module references, and architectural divergence. Moreover, LLMs' effectiveness in translating to newer, low-resource languages like Rust remains largely underexplored. To address these gaps, we introduce RustRepoTrans, the first repository-level context code translation benchmark targeting incremental translation, comprising 375 tasks translating into Rust from C, Java, and Python. Using this benchmark, we evaluate seven representative LLMs, analyzing their errors to assess limitations in complex translation scenarios. Among them, DeepSeek-R1 performs best with 51.5% Pass@1, excelling in both basic functionality and additional translation abilities, such as noise robustness and syntactical difference identification. However, even DeepSeek-R1 experiences a 22.2% performance drop (Pass@1 from 73.7% to 51.5%) when handling repository-level context compared to previous benchmarks without such context.