humaneval on Hacker News: 1 stories with screenshots

Beating GPT-4 on HumanEval with a fine-tuned CodeLlama-34B (phind.com)

737 points by rushingcreek 3 years ago | 258 comments

Phind blog post announcing fine-tuned CodeLlama-34B models that score 67.6% and 69.5% pass@1 on HumanEval, beating GPT-4's reported 67%.