✅WizardCoder-34B surpasses GPT-4, ChatGPT-3.5 and Claude-2 on HumanEval with 73.2% pass@1
You must log in or # to comment.
Cool, but comparison is a stretch, as admitted by the authors. With identical test methodology gpt-4 is still better
Still a good news
Agreed, but still huge progress in OSS models in a very short time!
