After testing 14 large language models (LLMs) for coding capabilities, only five received positive reviews. ChatGPT Plus and Perplexity Pro are among the best, but free versions suffice for basic tasks. Google's Gemini Pro 2.5 and Microsoft’s Copilot show promise, albeit with limitations. The author warns against relying on most other models mentioned due to performance issues, highlighting that while AIs help with coding small projects, their effectiveness wanes for larger applications.
Unfortunately, not all chatbots can code alike. It's been a little over two years since that first test, and even now, four of the 13 LLMs I tested can't create working plugins.
Two of them, ChatGPT Plus and Perplexity Pro, cost $20 per month each. The free versions of the same chatbots do well enough that you could probably get by without paying.
Collection
[
|
...
]