Unverified70% confidenceFactExact time
Reasoning models typically return a separate reasoning or thinking field in the response, distinct from the final answer field.
2
Sources
70%
Confidence
Long-term
Relevance
9/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA reasoning stream refers to the model's output of its thinking process before giving a final answer, which is returned incrementally (as deltas) during streaming and is typically interleaved with tool calls.79% similarVerifiedWhen Claude's Extended Thinking feature is enabled, the model outputs an internal reasoning process (a thinking block) before generating the final response; this reasoning is visible to the user but is not counted as part of the conversation context.78% similarVerifiedReasoning models perform internal Chain-of-Thought before returning final results, consuming large amounts of tokens and computation time in exchange for deeper understanding and lower error rates.77% similarUnverifiedFor models without a thinking mode, if a correct numerical answer is needed, you should have it show its reasoning process and then read the last line, rather than directly demanding "give only the number".77% similarVerifiedResearch has found that the chain-of-thought reasoning generated by models does not fully correspond to their actual internal computation processes, and may provide post-hoc explanations unrelated to the true decision-making path.77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/928179API
curl https://kongchang.com/api/v1/knowledge/claims/928179MCP
get_claim(id=928179)