Lilly Tech Systems
The Complete LLM Directory
A comprehensive reference of every major Large Language Model — organized by provider. Explore model specs, context windows, pricing, capabilities, and side-by-side comparisons to find the right LLM for any use case.
Directory Sections
Browse by provider or explore the comparison and open-source guides.
1. Overview
The LLM landscape explained. Model categories, timeline of releases, size ranges, and how to read benchmarks like MMLU and HumanEval.
2. OpenAI Models
GPT-4o, GPT-4 Turbo, o1, o3, o4-mini, DALL-E 3, Whisper, and every other OpenAI model with full specs.
3. Anthropic Models
Claude Opus 4, Sonnet 4, Haiku 3.5, and every Claude generation. Constitutional AI approach and 200K context.
4. Google Models
Gemini 2.5 Pro, Gemini Flash, Gemma, PaLM 2, and the full Google DeepMind model family with up to 2M context.
5. Meta Models
Llama 4 Scout, Llama 4 Maverick, Llama 3 series, Llama 2, and Code Llama. Open-weight models for everyone.
6. Other Providers
Mistral, Cohere, xAI Grok, DeepSeek, Qwen, Phi, AI21, Amazon Titan, and more from every major provider.
7. Open Source Models
Top open-source LLMs ranked. How to download and run models. Licensing, quantization formats, and community fine-tunes.
8. Comparison
Master comparison table of all models. Decision guide by use case, budget, and privacy. "Which LLM should I use?" flowchart.
What You'll Find
This directory covers every major LLM with consistent, comparable details.
Full Model Specs
Parameters, context windows, release dates, multimodal support, and capabilities for every listed model.
Pricing Details
Input and output token pricing, free tiers, and cost comparisons across providers.
Benchmark Scores
MMLU, HumanEval, GPQA, MT-Bench, and other benchmark results to compare performance objectively.
Use Case Guidance
Recommendations for which models work best for coding, writing, analysis, research, and production deployments.