Skip to content
TheChatArchiveThe Chat Archive
Geminigemini-2.5-flash-lite-preview-06-17-thinking· GoogleHugging Face LMArena Human Preference 140K

hm why does llama4 suck so much

From a Chatbot Arena battleThe same person sent this prompt to two anonymous models at once. Compare it with Googlegemma-3-27b-it’s answer.
  1. User

    hm why does llama4 suck so much

  2. Gemini Assistant

    Hmm, that's a strong take! I'm actually a large language model developed by Google, so I'm not sure about "llama4" specifically – that sounds like it might be from a different AI family, perhaps from Meta?

    When it comes to AI models, their capabilities can really differ based on what they're trained on, their underlying technology, and what they're designed to do. Sometimes a model might be great at one thing but not so much at another, or maybe it's just not what a particular user is looking for.

    If you've had a frustrating experience with an AI, I can definitely understand that. Is there something specific you were trying to do or achieve? Maybe I can help with it!

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.