LLama 3 70B
VS
ChatGPT 3.5

What about the images?

Currently, ChatGPT 3.5 API has no computer vision capabilities. neither can this particular model generate images, unlike its more modern counterparts.

Same for LLama, no image analysis is possible.

Conclusion

LLama 3 beat ChatGPT 3.5 in all regards, being a more modern and well-versed model. You might be asking - what about GPT 4, and GPT 4 omni? Well, those models boast orders of magnitude more parameters, but we'll make sure to test them in the future. You can start your own tests now in our Playground.

Pricing

The Pricing model is given in AI/ML API tokens. As LLama 3 is open source, setting it up and maintaining locally would have different pricing.

This is a complete victory for LLama 3 over ChatGPT 3.5. This means that for development one is substantially better than the other. Yet, has similar pricing, which means there you might prefer.

Compare for yourself

While we've highlighted some strengths, the best model for your specific task depends on your needs. The snippet below provides a starting point to test and compare two language models, Llama 3 and ChatGPT 3.5. Play around with different prompts and see which model delivers the most relevant and impressive results for you!

import openai

def main():
    client = OpenAI(
      api_key='<YOUR_API_KEY>',
      base_url="https://api.aimlapi.com",
    )

    # Specify the two models you want to compare
    model1 = 'meta-llama/Llama-3-70b-chat-hf'
    model2 = 'gpt-3.5-turbo-16k'
    selected_models = [model1, model2]

    system_prompt = 'You are an AI assistant that only responds with jokes.'
    user_prompt = 'Why is the sky blue?'
    results = {}

    for model in selected_models:
        try:
            response = client.chat.completions.create(
                model=model,
                messages=[
                    {'role': 'system', 'content': system_prompt},
                    {'role': 'user', 'content': user_prompt}
                ],
            )

            message = response.choices[0].message.content
            results[model] = message
        except Exception as error:
            print(f"Error with model {model}:", error)

    # Compare the results
    print('Comparison of models:')
    print(f"{model1}: {results.get(model1, 'No response')}")
    print(f"{model2}: {results.get(model2, 'No response')}")

if __name__ == "__main__":
    main()

‍

Conclusion

LLamas' win over ChatGPT was and still remains a huge victory for open-source models and  Meta. It has won in chatting and pricing, and shown good results in coding. Many apps now use LLama 3 as their main model, and it is a quick and reliable model that has earned its place in the big race.

No matter which model you choose, you are sure to be impressed by its capabilities. Pick LLama 3 if this comparison has satisfied you. Choose ChatGPT 3.5 if you still need more evidence. Or search in our Models catalog, which provides newer models like ChatGPT 4o and Claude 3 Haiku.