Extended Thinking
A reasoning mechanism in Claude models that allows the model to conduct an internal reasoning process before generating a final answer. The depth of reasoning and token budget are controlled via an effort parameter, enabling deeper processing for more complex tasks.
Timeline (last 90 days)
Anthropic introduced the Extended Thinking feature in Claude as an exploration of making the thinking process visible.
Extended thinking enhances a model's logical reasoning and multi-step analysis capabilities, but cannot conjure new knowledge that the model has never been exposed to.
All Facts (2)
Anthropic introduced the Extended Thinking feature in Claude as an exploration of making the thinking process visible.
60%UnverifiedExtended thinking enhances a model's logical reasoning and multi-step analysis capabilities, but cannot conjure new knowledge that the model has never been exposed to.
50%