LLM Model Card Directory

Predecessor to Claude 3, offering strong all-round performance

Updated version of Claude 2 with improved accuracy

Fastest and most compact model for near-instant responsiveness

Balance of intelligence and speed

Powerful model for highly complex tasks

Anthropic's most intelligent model

Google's first-generation model offering only text and image reasoning

Google's next-generation model with a breakthrough 2 million context window

Google's fastest multimodal model with great performance for diverse, repetitive tasks and a 1 million token context window

Google's smallest model for lower intelligence use cases with a 1 million token context window

A dialogue use case optimized variant of Llama 2 models. Llama 2 is an auto-regressive language model that uses an optimized transformer architecture

An optimized dialogue variant of Llama 2, trained on more data with an improved transformer architecture

Ideal for limited resources and edge devices, excelling in summarization, classification, sentiment analysis, and translation

Ideal for content creation, AI, and enterprise, excelling in summarization, classification, sentiment analysis, language modeling, dialogue, and code generation

Ideal for enterprise level applications, research and development, synthetic data generation and model distillation.

Ideal for limited computational power and resources, faster training times, and edge devices.

Ideal for content creation, conversational AI, language understanding, research development, and enterprise applications.

Lightweight text-only model for fast, accurate responses, ideal for edge devices and mobile apps. Enables on-device AI, ensuring privacy and low latency

Multimodal model for text and image input/output, ideal for visual intelligence tasks like image analysis, document processing, and multimodal chatbots

Multimodal model, ideal for visual intelligence in image analysis, document processing, multimodal chatbots, and autonomous systems

World’s best edge model

Powerful edge model with extremely high performance/price ratio

Mistral's top-tier reasoning model for high-complexity tasks with the latest version v2 released July 2024

Mistral's latest enterprise-grade small model with the latest version v2 released September 2024

Mistral's cutting-edge language model for coding released May 2024

A 12B model with image understanding capabilities in addition to text

Mistral's best multilingual open source model released July 2024

Mistral's first dense model released September 2023

Mistral's first sparse mixture-of-experts released December 2023

Mistral's best open source model to date released April 2024

A powerful model that excels at solving difficult problems with wide-ranging knowledge and expertise

The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Currently points to gpt-4-turbo-2024-04-09

OpenAI's high-intelligence flagship model for complex, multi-step tasks. GPT-4o is cheaper and faster than GPT-4 Turbo

OpenAI's affordable and intelligent small model for fast, lightweight tasks. GPT-4o mini is cheaper and more capable than GPT-3.5 Turbo

A reasoning model designed to solve hard problems across domains

A faster and cheaper reasoning model particularly good at coding, math, and science

Comparable performance to Grok 2 but with improved efficiency, speed and capabilities