ByteDance-Seed/Multi-SWE-bench
收藏Hugging Face2025-09-18 更新2025-04-12 收录
下载链接:
https://hf-mirror.com/datasets/ByteDance-Seed/Multi-SWE-bench
下载链接
链接失效反馈官方服务:
资源简介:
Multi-SWE-bench是一个多语言基准数据集,用于评估大型语言模型(LLM)在现实世界代码问题解决中的表现。该数据集涵盖了Java、TypeScript、JavaScript、Go、Rust、C和C++共7种编程语言,包含1632个由68位专家注释的高质量实例。这些实例是从2456个候选实例中精心挑选出来的,以确保可靠性。
Multi-SWE-bench is a multilingual benchmark dataset designed to evaluate the performance of Large Language Models (LLMs) in real-world code issue resolution. The dataset spans across 7 programming languages: Java, TypeScript, JavaScript, Go, Rust, C, and C++, and includes 1,632 high-quality instances curated from 2,456 candidates by 68 expert annotators for reliability.
提供机构:
ByteDance-Seed



