10 Claude

Anthropic

Anthropic’s Claude represents a family of large language models (LLMs) specifically designed with safety, helpfulness, and honesty as core principles.^[1] Developed by Anthropic, a public benefit corporation founded by former OpenAI researchers, Claude distinguishes itself through its emphasis on constitutional AI training methods and robust safety measures.^[2] For users, Claude offers sophisticated reasoning capabilities, extensive context windows, and a commitment to accurate and well-sourced responses.

Claude’s development philosophy prioritises harmlessness and truthfulness alongside capability, resulting in an AI assistant that tends to be more cautious and transparent about limitations.^[3] The platform offers multiple model variants optimised for different use cases, from quick daily tasks to complex analysis requiring deep reasoning. Claude’s training emphasises a nuanced understanding of context, ethical reasoning, and the ability to engage with complex and multi-faceted problems. The models have gained recognition for their thoughtful responses and strong performance across analytical and creative tasks.

 Watch

Have a look at the newly redesigned user interface for Claude below.

Interface

Claude is accessible through Anthropic’s direct chat interface. Interact with this guide below to understand the various functionalities within the Claude interface.

Anthropic offers both free and paid versions of Claude. While using the free plan, Claude’s context window and daily message limit (i.e., the outputs) may vary based on demand. Users are notified if a prompt exceeds the available context window or if they reach the daily message limit. However, users on the ‘pro’ plan benefit from a context window of over 200,000 tokens (approximately 500 pages of text), with message limits that are five times those of the free service. For relatively short conversations with Claude, users can send at least 45 messages every five hours. Once users reach the limit, it is reset every five hours.

Claude 4 Family of Models

Claude 4 is the family of models that represents the company’s most powerful models.^[4] Claude Sonnet 4.6 is the company’s current standard model, which provides a balance of capability, speed, and cost-effectiveness.^[5] Whereas Claude Opus 4.6 is the company’s most capable model in the Claude family, designed for the most complex and challenging tasks.^[6] Statistics for this model include:

• Context window of 200,000 tokens
• Maximum output of 64,000 tokens
• The knowledge cutoff is February 2025
• Achieved 81.2% accuracy on LegalBench Benchmark testing (with thinking mode turned on)

Extended Thinking

First introduced with the Claude 3.7 Sonnet model, the 'extended thinking' feature enables a user to choose whether the model responds immediately or takes longer to think before replying. This option was added as a user interface option with a button to enable the 'extended thinking' mode (see the interface walkthrough above). Enabling 'extended thinking' is similar to the 'reasoning' models (discussed in more detail in Prompting a Reasoning Model). The mode allows for step-by-step processing, which is visible to the end user. Users can choose when they want the model to respond and when they prefer it to take a bit longer before answering.

Users can view the model's steps and outputs in the Graphical User Interface (GUI). Developers using the model can also specify how long the model should consider a problem.

Legacy Models

Users can work with older models, including Opus 4.5 and 3, and Sonnet 4.5. Stats include:

Opus 4.5

• Context window of 200,000 tokens
• Maximum output of 64,000 tokens
• The knowledge cutoff is January 2025
• Achieved 84.6% accuracy accuracy on LegalBench Benchmark testing (with thinking mode turned on)

Opus 3

• Context window of 200,000 tokens
• Maximum output of 4,000 tokens
• The knowledge cutoff is January 2025
• Achieved 73.2% accuracy accuracy on LegalBench Benchmark testing

Sonnet 4.5

• Context window of 200,000 tokens
• Maximum output of 64,000 tokens
• The knowledge cutoff is January 2025
• Achieved 84.1% accuracy accuracy on LegalBench Benchmark testing (with thinking mode turned on)

Claude Cowork

Going beyond the chat interface, Anthropic introduced a product called 'Cowork'. Claude Cowork is a desktop AI agent, currently available as a research preview for all paid Claude subscribers (Pro, Max, Team, and Enterprise) on macOS and Windows.^[7] Inspired by the success of Claude Code, Anthropic built Cowork to bring the same powerful agentic capabilities to non-developers. Claude can directly read from and write to your local files without manual uploads or downloads, break complex work into smaller tasks and coordinate parallel workstreams, generate professional outputs (like Excel spreadsheets, PowerPoint presentations, and formatted documents). Watch the following video that provides an illustrative example of using Cowork.

Essentially, by downloading the Claude app, a user grants Claude access to a folder of their choosing, instructs the tool with the desired outcome, and Claude gets to work with far more agency than a standard conversation would allow. This is an example of what is known as 'computer use' that was first introduced to researchers and developers with the Claude Sonnet 3.5 model.^[8] You can watch an illustrative example of computer use below.

Plugins

An interesting aspect of Claude Cowork is the ability to customise the experience with plugins. A user can install a plugin to bundle tools, knowledge, and workflows into the installed application. Examples of approved plugins on Anthropic's website can be found on the marketplace here. Currently, there is one law plugin on the marketplace. Simply called 'legal', it 'automates contract review, NDA triage, compliance workflows, legal briefings, and templated responses — all configurable to your organisation's playbook and risk tolerances.'^[9] The plugin was built for in-house counsel, product counsel, privacy/compliance, and litigation support teams.^[10]