Technique · reasoning
Chain-of-Thought Prompting
A prompting technique that elicits step-by-step reasoning by showing exemplars that include intermediate reasoning steps.
Deployment timeline
- Claude Opus 4.6high
Deployed 2026-02-16 · Velocity 4y
“Claude Opus demonstrates step-by-step reasoning in its responses, consistent with chain-of-thought prompting.”
- GPT-4ohigh
Deployed 2026-02-16 · Velocity 4y
“GPT-4o can be prompted to show step-by-step reasoning, a core CoT capability.”
- GPT-5high
Deployed 2026-02-16 · Velocity 4y
“GPT-5 can be prompted to show step-by-step reasoning, a core CoT capability.”
- GPT-5.2 Prohigh
Deployed 2026-02-17 · Velocity 4y
“GPT-5.2 thinking mode is explicitly designed for step-by-step reasoning, a core CoT capability.”
- Claude 3high
Deployed 2026-02-18 · Velocity 4y
“Claude 3 exhibits strong chain-of-thought reasoning capabilities in its technical report.”
- Gemini 3 Prohigh
Deployed 2026-02-19 · Velocity 4y
“Gemini 1.5 Pro can reason across text, images, audio, and video in a chain-of-thought style.”
- Gemini 3.1medium
Deployed 2026-02-20 · Velocity 4y
“Gemini models are known to be prompted with chain-of-thought reasoning for complex tasks.”
- Claude 3.5 Sonnethigh
Deployed 2026-02-23 · Velocity 4y
“Claude 3.5 Sonnet demonstrates chain-of-thought reasoning in its outputs when solving complex problems.”
- Claude Sonnet 4.6medium
Deployed 2026-02-25 · Velocity 4y
“Claude models are known for their strong reasoning capabilities, often producing step-by-step reasoning in responses.”
- Claude Haiku 4.5high
Deployed 2026-02-25 · Velocity 4y
“Claude models are trained to produce step-by-step reasoning when appropriate, including in Haiku.”
- GPT-5.3medium
Deployed 2026-02-26 · Velocity 4y
“GPT-5.3-Codex demonstrates step-by-step reasoning in autonomous software development tasks.”
- Claude 4.5high
Deployed 2026-02-26 · Velocity 4y
“Claude 4.5 demonstrates step-by-step reasoning in complex tasks, showing chain-of-thought capabilities.”
- Gemini 3 Flashhigh
Deployed 2026-02-27 · Velocity 4y
“Gemini models are trained to reason step-by-step, and Gemini 1.5 Flash was shown to use chain-of-thought reasoning in its technical report.”
- GPT-OSS-120Bmedium
Deployed 2026-03-02 · Velocity 4y
“GPT-OSS-120B is a reasoning model that pushes the frontier of accuracy, implying it uses step-by-step reasoning techniques.”
- Grok 4.20medium
Deployed 2026-03-02 · Velocity 4y
“Grok is capable of step-by-step reasoning and can be prompted to show its work.”
- Kimi K2.5medium
Deployed 2026-03-04 · Velocity 4y
“Kimi K2.5 demonstrates step-by-step reasoning in its responses, a hallmark of chain-of-thought prompting.”
- Gemini 3.1 Flash-Litehigh
Deployed 2026-03-05 · Velocity 4y
“Gemini models are trained to reason step-by-step, and Gemini 1.5 Flash and Pro can be prompted to show their reasoning.”
- DeepSeek-R1high
Deployed 2026-03-17 · Velocity 4y
“DeepSeek-R1 is a reasoning model that generates step-by-step reasoning traces.”
- Claude 3.5 Opushigh
Deployed 2026-03-18 · Velocity 4y
“Claude 3.5 Sonnet (same family) demonstrates chain-of-thought reasoning in technical report examples.”
- GLM-5.1medium
Deployed 2026-03-21 · Velocity 4y
“GLM-5.1 demonstrates chain-of-thought reasoning capabilities in examples.”
- Qwen 3.6high
Deployed 2026-03-31 · Velocity 4y
“Qwen 3.6 demonstrates strong reasoning capabilities, including step-by-step reasoning.”
- GPT-5.4-Cyberhigh
Deployed 2026-04-16 · Velocity 4y
“GPT-4 can generate step-by-step reasoning when prompted appropriately, a core CoT capability.”
- GPT-Rosalindhigh
Deployed 2026-04-16 · Velocity 4y
“GPT-Rosalind uses chain-of-thought prompting to solve biology problems step-by-step.”
- Claude Opus 4.7high
Deployed 2026-04-16 · Velocity 4y
“Claude Opus 4.7 is described as a 'frontier reasoning model' with 'xhigh thinking effort', which inherently implies step-by-step reasoning capabilities.”
- Kimi K2.6high
Deployed 2026-04-20 · Velocity 4y
“Kimi K2.6 is built for long-horizon agentic coding with step-by-step reasoning capabilities.”