Tabnine adds support for Anthropic’s Claude 3.5 Sonnet 

In keeping with our goal of supporting the latest and most advanced models, we’ve recently updated our support for Anthropic’s models with the switch to Claude 3.5 Sonnet. As with all of the other models Tabnine supports, you’re now able to use the Claude 3.5 Sonnet model with any chat interactions with Tabnine, including software planning (i.e., asking general coding questions or better understanding code in an existing project), code generation, code explanation and project onboarding, creating tests, fixing code, creating documentation, and refactoring code. Additionally, when using the Claude 3.5 Sonnet model, you’ll still benefit from Tabnine’s highly personalized recommendations, which take into account the context from locally available data in your IDE and your organization’s global codebase(s) to tailor AI-generated output to your project and engineering practices. 

Claude 3.5 Sonnet: The newest and most powerful model from Anthropic

Released last week, Claude 3.5 Sonnet is Anthropic’s first release in the forthcoming Claude 3.5 family of models. Claude 3.5 Sonnet raises the bar for intelligence and outperforms Claude 3 Opus (the most powerful model in the Claude 3 family of models) on a wide range of evaluations, including coding. In Anthropic’s internal coding evaluation, Claude 3.5 Sonnet solved 64% of problems, outperforming Claude 3 Opus (which solved only 38%). In Anthropic’s tests, the model easily handles code translations, making it recommended by Anthropic for updating legacy applications and migrating codebases. Claude 3.5 Sonnet also operates at twice the speed of Claude 3 Opus. 

Extending the switchable models functionality with cutting-edge models

We launched the ability to switch models in Tabnine earlier this year, allowing users to switch the LLM used by Tabnine’s chat capabilities in real time. With this update, we’re continuing our commitment to support the newest, state-of-the-art models as soon as they become available. 

You can now choose from 8 different models to integrate with Tabnine’s AI software development chat tools. This includes two custom-built, fully private models from Tabnine, plus popular LLMs from third-party vendors:

• Anthropic’s Claude 3.5 Sonnet
• Cohere’s Command R
• Mistral’s Codestral
• OpenAI’s GPT-4o (and earlier models)

With Tabnine, you’re not locked into any one model. Switch instantly between LLMs for specific projects, use cases, or to meet the compliance and security requirements of specific teams. There’s no additional cost for you to use the Claude 3.5 Sonnet model. 

Check out our Docs to learn more about this functionality. If you’re not yet a customer, you can sign up for Tabnine Pro today (it’s free for 90 days) or contact us to learn more.