Evaluating LLMs for my personal use case

(darkcoding.net)

48 points | by goranmoomin 7 hours ago

7 comments

  • rplnt 1 hour ago
    > Almost all models got almost all my evaluations correct

    I find this the most surprising. I have yet to cross 50% threshold of bullshit to possibly truth. In any kind of topic I use LLMs for.

    • simonw 31 minutes ago
      It's useful to build up an intuition for what kind of questions LLMs can answer and what kind of questions they can't.

      Once you've done that your success rate goes way up.

  • JSR_FDED 1 hour ago
    Which of these can I run locally on a 64GB Mac Mini Pro? And how much does quantization affect the quality?
    • simonw 28 minutes ago
      I use a 64GB M2 MacBook Pro. I tend to find any model that's smaller than 32B works well (I can just about run a 70B but it's not worth it as I have to quit all other apps first).

      My current favorite to run on my machine is OpenAI's gpt-oss-20b because it only uses 11GB of RAM and it's designed to run at that quantization size.

      I also really like playing with the Qwen 3 family at various sizes and I'm fond of Mistral Small 3.2 as a vision LLM that works well.

  • EagnaIonat 2 hours ago
    > To access their best models via the API, OpenAI now requires you to complete a Know-You-Customer process similar to opening a bank account.

    While this is true, you can download the OpenAI open source model and run it in Ollama.

    The thinking is a little slow, but the results have been exceptional vs other local models.

    https://ollama.com/library/gpt-oss

    • 0x457 1 hour ago
      openai/gpt-oss-120b is in this blog post.
  • faangguyindia 2 hours ago
    i use gemini flash and pro for pretty much everything. Why? they offer it free to test.

    I tried signup for openai wayy too much friction, they start asking for payment without even you using any free credits, guess what that's one sure way to lose business.

    same for claude, i couldn't even get claude through vertex as its available only in limited regions, and i am in asia pasific right now.

  • giancarlostoro 3 hours ago
    Him using different ones is why I use Perplexity, I get to try different models and honestly its pretty darn decent, gives me everything in an organized way, I can see all the different links, and all the files it outputs can be downloaded as a simple zip file. It has everything from GTP5 to Deepseek R1 and even Grok.

    There's other sites similar to perplexity that host multiple models as well, I have not tried the plethora of others, I feel like Perplexity does the most to make sure whatever model you pick it works right for you and all its output is usefully catalogued.

  • thorum 1 hour ago
    > Six of the eleven picked the same movie

    This is surely the greatest weakness of current LLMs for any task needing a spark of creativity.

    • Timwi 32 minutes ago
      This is definitely something very early LLMs could do that has kind of gotten beat out of them. I used to ask ChatGPT to simulate a text adventure game, but now if you try that you always get exactly the same one.
  • sandreas 3 hours ago
    This is an interesting overview, thank you. Different tasks, different models, all-day-usage and pretty complete (while still opinionated, which I like).

    However, checking the results my personal overall winner if I had to pick only ONE probably would be

      deepseek/deepseek-chat-v3-0324
    
    which is a good compromise between fast, cheap and good :-) Only for specific tasks (write a poem...) I would prefer a thinking model.