HumanEval-XL

A collection of cross-lingual benchmark for code generation.

Papers using HumanEval-XL (8)

Fully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language Models2025 · 6 citesSwiftEval: Developing a Language-Specific Benchmark for LLM-generated Code Evaluation2025 · 1 citesProgramming Language Confusion: When Code LLMs Can't Keep their Languages Straight2025CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X2023 · 208 citesMutation-based Consistency Testing for Evaluating the Code Understanding Capability of LLMs2024 · 9 citesHumanEval-XL: A Multilingual Code Generation Benchmark for Cross-lingual Natural Language Generalization2024 · 4 citesCodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model2023 · 1 citesInterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translation2024 · 1 cites