What's Your Favorite LLM –and Why?

[zyruh]

There’s no shortage of large language models—ChatGPT, Claude, Perplexity, Mistral, Gemini, and more. Each has its strengths and quirks. I’m curious: which one do you find yourself using most often, and what makes it stand out for you? Is it accuracy, speed, personality, features, cost, or something else entirely? Looking forward to hearing your experiences and insights.

[maxloh]

Allen AI's OLMo2. It is the only truly open-source model I've heard of.

The training code and dataset are also open-sourced.

[MrCoffee7]

GLM-4.5 from https://chat.z.ai because it renders math notation so well that other LLMs tend to mangle and it uses color coding when showing Python code.

[bigyabai]

Qwen3 30B 2507 is a good mix of speed and performance, for my taste. I use an abliterated quant and have no complaints.