# Large Language Models (LLMs)

Navigation:

{% hint style="success" %}

* [Prompt Engineering](/learn/large-language-models-llms/prompt-engineering.md)
* [Hallucination](/learn/large-language-models-llms/hallucination.md)
  {% endhint %}

## Large Language Models (LLMs) Ranking

{% tabs %}
{% tab title="Artificial Analysis" %}
Independent analysis of AI language models and API. Provides quality, speed, and price comparisons.

{% embed url="<https://artificialanalysis.ai>" %}
{% endtab %}

{% tab title="Scale Leaderboards" %}
{% embed url="<https://scale.com/leaderboard?utm_source=www.theaivalley.com&utm_medium=newsletter&utm_campaign=2-new-shocking-details-about-sam-altman-s-firing>" %}
Scale Leaderboards
{% endembed %}

{% endtab %}

{% tab title="LM Arena" %}
LMArena.ai is a comprehensive AI model leaderboard, ranking over 240 large language models across various domains—including text, vision, web development, search, and coding—based on more than 3.5 million user votes.

Unlike traditional benchmarks, LMArena employs a crowdsourced, blind-voting system where users compare anonymous model responses to the same prompt and vote for the better one. This approach provides a dynamic, real-world evaluation of model performance.

{% embed url="<https://lmarena.ai/leaderboard>" %}
{% endtab %}

{% tab title="HuggingFace" %}

<https://huggingface.co/open-llm-leaderboard>
{% endtab %}

{% tab title="vellum" %}
<https://www.vellum.ai/llm-leaderboard>
{% endtab %}
{% endtabs %}

### Comparison

| AI Model                   | Core Strength (2026)      | Context Window  | Agent Capability         | Starting Price    |
| -------------------------- | ------------------------- | --------------- | ------------------------ | ----------------- |
| **ChatGPT (GPT-5.2)**      | Generalist & Logic (o3)   | 256K Tokens     | Operator (Browser Agent) | $20/mo            |
| **Claude 4 (Opus/Sonnet)** | Human-like Writing & Code | 500K+ Tokens    | Computer Use (Desktop)   | $20/mo            |
| **Gemini 3 (Ultra)**       | Google Ecosystem & Video  | 2M - 10M Tokens | Google Workspace Agent   | $19.99/mo         |
| **Grok 4**                 | Real-time X Data & Wit    | 128K+ Tokens    | Integrated Social Agent  | $8/mo (X Premium) |

***

## Large Language Models

### Close Source Apps:

{% hint style="success" %}

* ChatGPT
* Grok
* Claude
* Gemini
  {% endhint %}

### Open Source Models:

{% hint style="success" %}

* Deepseek
* LLama
* Mistral
* Qwen
  {% endhint %}

***

## Learning Resources:

<table data-header-hidden><thead><tr><th width="321.546875"></th><th width="428.5442708333333"></th><th></th></tr></thead><tbody><tr><td><strong>How I use LLMs</strong> by Andrej Karpathy</td><td><a href="https://youtu.be/EWvNQjAaOHw?si=bzp-Dy5yvnCohubp">https://youtu.be/EWvNQjAaOHw?si=bzp-Dy5yvnCohubp</a></td><td></td></tr><tr><td>What Is ChatGPT Doing … and Why Does It Work?</td><td><a href="https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-doing-and-why-does-it-work/">https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-doing-and-why-does-it-work/</a></td><td></td></tr><tr><td>ChatGPT Prompt Engineering for Developers</td><td><a href="https://www.deeplearning.ai/short-courses/chatgpt-prompt-engineering-for-developers/">https://www.deeplearning.ai/short-courses/chatgpt-prompt-engineering-for-developers/</a></td><td></td></tr><tr><td>LLM101n: Let's build a Storyteller</td><td><a href="https://github.com/karpathy/LLM101n">https://github.com/karpathy/LLM101n</a></td><td></td></tr><tr><td>How GPT works</td><td><a href="https://bbycroft.net/llm">https://bbycroft.net/llm</a></td><td></td></tr><tr><td>How I Use "AI" by Nicholas Carlini</td><td><a href="https://nicholas.carlini.com/writing/2024/how-i-use-ai.html">https://nicholas.carlini.com/writing/2024/how-i-use-ai.html</a></td><td></td></tr><tr><td>Transformer Explainer</td><td><a href="https://poloclub.github.io/transformer-explainer/">https://poloclub.github.io/transformer-explainer/</a></td><td></td></tr><tr><td>Generative AI Handbook: A Roadmap for Learning Resources</td><td><a href="https://genai-handbook.github.io">https://genai-handbook.github.io</a></td><td></td></tr><tr><td>Anthropic courses</td><td><a href="https://github.com/anthropics/courses/tree/master">https://github.com/anthropics/courses/tree/master</a></td><td></td></tr><tr><td>Deep Dive into LLMs like ChatGPT by Andrej Karpathy</td><td><a href="https://youtu.be/7xTGNNLPyMI?si=6WfUHQx8-XqNxlQQ">https://youtu.be/7xTGNNLPyMI?si=6WfUHQx8-XqNxlQQ</a></td><td></td></tr><tr><td>Google - Prompt Engineering by Lee Boonstra</td><td><a href="https://www.kaggle.com/whitepaper-prompt-engineering">https://www.kaggle.com/whitepaper-prompt-engineering</a></td><td></td></tr></tbody></table>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.aiandbusiness.com/learn/large-language-models-llms.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.