X-HumanEval-X
Emerging4papers using it
1,434HF downloads
95HF likes
2023first seen
HumanEval-X is a benchmark for the evaluation of the multilingual ability of code generative models. It consists of 820 high-quality human-crafted data samples (each with test cases) in Python, C++, Java, JavaScript, and Go, and can be used for various tasks.
🤗 Hugging Face⚖ apache-2.0
Papers using X-HumanEval-X (4)
- LLMLOOP: Improving LLM-Generated Code and Tests through Automated Iterative Feedback LoopsCodeGeeX: A Pre-Trained Model for Code Generation with Multilingual
Benchmarking on HumanEval-XExploring Multi-Lingual Bias of Large Code Models in Code GenerationCodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model