Claude 3: Definition and Examples
Claude 3 is a family of language models developed by Anthropic, launched in March 2024, comprising three variants (Haiku, Sonnet, and Opus) offering different levels of performance and cost.
Full definition
Claude 3 refers to the third major generation of language models created by Anthropic, a company specializing in AI safety. Launched in March 2024, this family comes in three models — Haiku, Sonnet, and Opus — which differ in reasoning power, execution speed, and pricing. This multi-tier architecture allows users to choose the model best suited to their use case.
Claude 3 marked a turning point for Anthropic by introducing multimodal capabilities: all three models can analyze images in addition to text, significantly expanding the range of possible applications. The Claude 3 family also pushed boundaries in terms of context window, with a standard capacity of 200,000 tokens, allowing very long documents to be processed in a single request.
In terms of performance, Claude 3 Opus positioned itself as a direct competitor to GPT-4 on benchmark tests, while Sonnet offered excellent value for money for common professional uses, and Haiku stood out for its speed and low cost for simple tasks. This range allowed Anthropic to establish itself as a major player in the LLM market.
Claude 3 has since been succeeded by the Claude 3.5, Claude 4, and Claude 4.5/4.6 families, but it remains an important reference in the history of generative AI as the moment when Anthropic achieved parity with the best models on the market.
Etymology
The name "Claude" is a tribute to Claude Shannon, American mathematician and engineer considered the father of information theory. The number 3 indicates the third major generation of the model. The variant names (Haiku, Sonnet, Opus) borrow from poetic and musical vocabulary, reflecting a progression in size and complexity.
Concrete examples
Long document analysis with Claude 3 Opus
Here is a 150-page annual report. Summarize the key financial points, identify mentioned risks, and propose three strategic questions for the board of directors.
Multimodal use for image analysis
Describe this user interface screenshot. Identify usability issues and suggest three concrete improvements following Nielsen's design principles.
Quick task with Claude 3 Haiku for batch processing
Classify each of these 500 customer reviews into three categories: positive, negative, or neutral. Return the result in JSON format.
Practical usage
In prompt engineering, choosing the right Claude 3 model is crucial: use Opus for complex tasks requiring deep reasoning, Sonnet for common professional uses, and Haiku for volume processing where speed is paramount. Leverage the large context window by providing complete documents rather than excerpts, and take advantage of multimodal capabilities by combining text and images in your prompts.
Related concepts
FAQ
What is the difference between Claude 3 Haiku, Sonnet, and Opus?
Is Claude 3 still available or has it been replaced?
What are the multimodal capabilities of Claude 3?
See also
How to use this prompt
- Copy the prompt with the button above.
- Paste it into ChatGPT, Claude or your favorite AI assistant.
- Replace the bracketed variables with your details, then refine the result.
About Prompt Guide
Prompt Guide is a free library of 2500+ ready-to-use prompts for ChatGPT, Claude and other AIs, with guides to learn prompting and tools to build and optimize your own prompts.
More definitions
Code Completion: Definition and Examples
Code completion is an AI-powered feature that automatically suggests code as the developer types, predicting lines, functions
Code Generation: Definition and Examples
Code generation enables producing source code from natural language instructions. Discover how ChatGPT, Claude, and Copilot write code.
Codex (OpenAI): Definition and Use Cases
Codex is OpenAI's autonomous coding agent. Understand how it works, its differences from Claude Code and Cursor, and when to use it.
Completion: Definition and Examples
Response generated by a language model (LLM) from a given prompt. Completion is the text produced by the AI to complete, answer, or extend the user's input.
Computer Use: Definition and Examples
Ability of an AI model to directly interact with a computer by controlling the mouse, keyboard, and screen, just as a human user would.
Confusion Matrix: Definition and Examples
Learn to read a confusion matrix: true positives, false negatives, accuracy, precision and recall explained with concrete examples in machine learning.
Get new prompts every week
Join our newsletter.