Skip to content
TheChatArchiveThe Chat Archive
Amazon Novaamazon.nova-pro-v1:0· AmazonHugging Face LMArena Human Preference 140K

Which models does Mistral currently offer for free, what are the parameter sizes and…

From a Chatbot Arena battleThe same person sent this prompt to two anonymous models at once. Compare it with Claudeclaude-sonnet-4-20250514’s answer.
  1. User

    Which models does Mistral currently offer for free, what are the parameter sizes and what are their AI benchmark scores?

  2. Amazon Nova Assistant

    As of the latest information available, Mistral AI offers several models for free, each with different parameter sizes and performance metrics. Here’s a summary of the key models they provide:

    Mistral 7B

    • Parameter Size: 7 Billion parameters
    • AI Benchmark Scores:
      • GLUE: Approximately 85-90
      • SuperGLUE: Approximately 75-80
      • MMLU: Approximately 65-70

    Mistral 7B Instruct

    • Parameter Size: 7 Billion parameters
    • AI Benchmark Scores:
      • GLUE: Approximately 88-92
      • SuperGLUE: Approximately 78-82
      • MMLU: Approximately 68-72

    Mistral Tiny

    • Parameter Size: 1 Billion parameters
    • AI Benchmark Scores:
      • GLUE: Approximately 70-75
      • SuperGLUE: Approximately 60-65
      • MMLU: Approximately 55-60

    Mistral Small

    • Parameter Size: 3 Billion parameters
    • AI Benchmark Scores:
      • GLUE: Approximately 80-85
      • SuperGLUE: Approximately 70-75
      • MMLU: Approximately 60-65

    Mistral Medium

    • Parameter Size: 10 Billion parameters
    • AI Benchmark Scores:
      • GLUE: Approximately 90-95
      • SuperGLUE: Approximately 82-86
      • MMLU: Approximately 72-76

    Please note that benchmark scores can vary based on the specific versions and updates of the models. For the most accurate and up-to-date information, it’s best to refer directly to Mistral AI’s official documentation or website.

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