Some developers say they\u2019ve had largely positive experiences with GPT-5 so far. Jenny Wang, an engineer, investor, and creator of the personal styling agent Alta, told WIRED the model appears to be better at completing complex coding tasks in one shot than other models. She compared it to OpenAI\u2019s o3 and 4o, which she uses frequently for code generation and straightforward fixes \u201clike formatting, or if I want to create an API endpoint similar to what I already have,\u201d Wang says.<\/p>\n
In her tests of GPT-5, Wang says she asked the model to generate code for a press page for her company\u2019s website, including specific design elements that would match the rest of the site\u2019s aesthetic. GPT-5 completed the task in one take, whereas in the past, Wang would have had to revise her prompts during the process. There was one significant error, though: \u201cIt hallucinated the URLs,\u201d Wang says.<\/p>\n
Another developer, who spoke on the condition of anonymity because their employer didn\u2019t authorize them to speak to the press, says GPT-5 excels at solving deep technical problems.<\/p>\n
The developer\u2019s current hobby project is writing a programmatic network analysis tool, one that would require code isolation for security purposes. \u201cI basically presented my project and some paths I was considering, and GPT-5 took it all in and gave back a few recommendations along with a realistic timeline,\u201d the developer explains. \u201cI\u2019m impressed.\u201d<\/p>\n
A handful of OpenAI\u2019s enterprise partners and customers, including Cursor, Windsurf, and Notion, have publicly vouched for GPT-5\u2019s coding and reasoning skills. (OpenAI included many of these remarks in its own blog post<\/a> announcing the new model.) Notion also shared on X<\/a> that it\u2019s \u201cfast, thorough, and handles complex work 15 percent better than other models we\u2019ve tested.\u201d<\/p>\n But within days of GPT-5\u2019s release, some developers were weighing in online with complaints. Many said that GPT-5\u2019s coding abilities seemed behind the curve for what was supposed to be a state-of-the-art, ultra-capable model from the world\u2019s buzziest AI company.<\/p>\n \u201cOpenAI\u2019s GPT-5 is very good, but it seems like something that would have been released a year ago,\u201d says Kieran Klassen, a developer who has been building an AI assistant for email inboxes. \u201cIts coding capabilities remind me of Sonnet 3.5,\u201d he adds, referring to an Anthropic model that launched in June 2024.<\/p>\n Amir Salihefendi\u0107, founder of the startup company Doist, said in a social media post<\/a> that he\u2019s been using GPT-5 in Cursor and has found it \u201cpretty underwhelming\u201d and that \u201cit\u2019s especially bad at coding.\u201d He said the release of GPT-4 felt like a \u201cLlama 4 moment,\u201d referring to Meta\u2019s AI model, which had also disappointed some people in the AI community.<\/p>\n