Large Language Models (LLMs)

• ChatGPT Tutorial

• LLama

• Prompt Tutorial

• Hallucination Problem

Large Language Models (LLMs) Ranking

Artificial Analysis

Artificial Analysis

Independent analysis of AI language models and API. Provides quality, speed, and price comparisons.

Model & API Providers Analysis | Artificial Analysis

Scale Leaderboards

SEAL leaderboards

Scale Leaderboards

---

Large Language Models

Close Source Models:

OpenAI o1

OpenAI's new o1 model, released on September 12, 2024, is now the most powerful LLM that can reason through complex problems by breaking them down into steps, excelling particularly in areas like mathematics, coding, and scientific reasoning where it outperforms previous models and even rivals human experts in some cases.

OpenAI o1 and o1 pro

https://openai.com/index/learning-to-reason-with-llms/

GPT-4o

GPT-4o-2024-08-06, OpenAI's most powerful LLM.

5/29/2024 ChatGPT with Gpt-4o is free for everyone

Grok-3

Elon Musk's AI company xAI officially launched Grok 3, touted as the "smartest AI on Earth," on February 18, 2025, claiming it surpasses previous models in reasoning and performance across various benchmarks.

Grok

Claude

https://claude.ai

Claude is a family of large language models developed by Anthropic, designed to generate natural, human-like responses to text and image-based inputs.

Anthropic introduced the new Claude 3.5 Sonnet, and Claude 3.5 Haiku.

Gemini

Gemini 2.5

https://deepmind.google/technologies/gemini/

Open Source Models:

Deepseek

DeepSeek v3 is an advanced open-source large language model with 671 billion parameters, offering superior performance and cost-effectiveness, making it a formidable alternative to closed-source models from tech giants like OpenAI and Google.

https://github.com/deepseek-ai/DeepSeek-V3

LLama

LLama is a family of state-of-the-art large language models developed by Meta, designed to perform a wide range of natural language processing tasks with varying levels of computational efficiency and accuracy.

Llama 4

https://ai.meta.com/blog/llama-4-multimodal-intelligence/

Llama 4 is Meta's latest open-weight multimodal AI model series featuring a Mixture of Experts architecture for efficient processing of text and images, with models like Scout offering a 10 million token context window and Maverick excelling in multilingual tasks.

Mistral

Mistral AI offers a range of large language models (LLMs), both open source and commercial, designed for various tasks such as text generation, code generation, and multilingual reasoning.

https://mistral.ai/

Mistral Large 2

Mistral AI has introduced Mistral Large 2, a cutting-edge Language Model (LLM) that boasts state-of-the-art reasoning, knowledge, and coding capabilities, with a 128k context window and support for dozens of languages, including French, German, Spanish, Italian, Portuguese, Arabic, Hindi, Russian, Chinese, Japanese, and Korean, along with 80+ coding languages.

Qwen3

Qwen3 is the latest generation of large language models from Alibaba Cloud, featuring a hybrid approach to problem-solving with both "thinking" and "non-thinking" modes, support for 119 languages, and a range of model sizes-including dense and Mixture-of-Experts (MoE) architectures, designed for scalable, efficient, and multilingual AI applications.

https://huggingface.co/Qwen/Qwen3-235B-A22B

---

RAG

Retrieval Augmented Generation (RAG) is a technique that enhances Large Language Models (LLMs) by retrieving relevant information from external knowledge sources to provide more accurate, up-to-date, and contextually appropriate responses

anything-llm

The all-in-one Desktop & Docker AI application with full RAG and AI Agent capabilities.

https://github.com/Mintplex-Labs/anything-llm

RAGFlow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

https://github.com/infiniflow/ragflow

Quivr

Open-source RAG Framework for building GenAI Second Brains 🧠 Build productivity assistant (RAG) ⚡️🤖 Chat with your docs (PDF, CSV, ...) & apps using Langchain, GPT 3.5 / 4 turbo, Private, Anthropic, VertexAI, Ollama, LLMs, Groq that you can share with users ! Efficient retrieval augmented generation framework.

https://www.quivr.com

Verba

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

https://github.com/weaviate/Verba

---

Fine Turning & More

Meta Fine Turning Guide

https://ai.meta.com/blog/how-to-fine-tune-llms-peft-dataset-curation/

Enterprise Guide to Building Intelligent AI Chatbots With RAG

https://www.nvidia.com/en-us/lp/ai-data-science/generative-ai/building-intelligent-ai-chatbots-with-rag-ebook/?ncid=pa-srch-goog-921287&wbraid=CmQKCAjwpvK4BhBuElQAC275K5Enwm5TbyBAJa9bTHOySqWuVbOOotxYcmXyq2DG8iG-VqmQeZ2vWWz8wWTs2HlOBi3Id8FSEYmB-nLapvZKxDS-t_tz9TbLINmy--__LHkaAmks&_bt=713058670066&_bk=&_bm=&_bn=&_bg=167350975575

---

Learning Resources:

Transformers, Explained: Understand the Model Behind GPT-3, BERT, and T5	https://daleonai.com/transformers-explained
What Is ChatGPT Doing … and Why Does It Work?	https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-doing-and-why-does-it-work/
ChatGPT Prompt Engineering for Developers	https://www.deeplearning.ai/short-courses/chatgpt-prompt-engineering-for-developers/
LLM101n: Let's build a Storyteller	https://github.com/karpathy/LLM101n
How GPT works	https://bbycroft.net/llm
How I Use "AI" by Nicholas Carlini	https://nicholas.carlini.com/writing/2024/how-i-use-ai.html
Transformer Explainer	https://poloclub.github.io/transformer-explainer/
Generative AI Handbook: A Roadmap for Learning Resources	https://genai-handbook.github.io
Anthropic courses	https://github.com/anthropics/courses/tree/master
Deep Dive into LLMs like ChatGPT by Andrej Karpathy	https://youtu.be/7xTGNNLPyMI?si=6WfUHQx8-XqNxlQQ
How I use LLMs by Andrej Karpathy	https://youtu.be/EWvNQjAaOHw?si=bzp-Dy5yvnCohubp
Google - Prompt Engineering by Lee Boonstra	https://www.kaggle.com/whitepaper-prompt-engineering