# High HumanEval Score

A large language model fine-tuned based on the starcoder2-3b model, specializing in code generation tasks, achieving a score of 65.9 pass@1 in the HumanEval-Python test

A large language model fine-tuned based on CodeLlama-34B-Python, achieving 69.5% pass@1 on HumanEval, surpassing GPT-4's performance

WizardCoder-33B-V1.1 is an open-source large language model for code, trained on deepseek-coder-33b-base, demonstrating excellent performance on code generation benchmarks like HumanEval.