Model techniques map
Techniquesinference & servingreasoning control

general family · filed under inference & serving

Chain-of-thought reasoning

The model produces reasoning content before its answer; the evidence also describes full access to that reasoning in some cases.

Also called Chain-of-Thought, COT, deep chain-of-thought, reasoning tokens, Chain-of-thought reasoning mode, Full chain-of-thought.

sources
8
models
6
labs adopt it
5
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

optional 2used 3default 2core 1

Documented in

Further reading

Picked by hand, not extracted: where to read more, not evidence for anything on this page.

Evidence

8 spans quoted from the sources, strongest treatment first.

Full chain-of-thought: Gain complete access to the model’s reasoning process, facilitating easier debugging and increased trust in outputs.

coreunclearin gpt-oss-120bOpenAI

Reasoning mode: Defaults to "high" (deep chain-of-thought), which suits complex tasks such as math, coding, and reasoning.

defaultinference servingin Hy4-previewTencent Hunyuan

It only has one reasoning effort right now, 'max'—and it shows. The model consumed 13,241 reasoning tokens to output 3,417 tokens of response.

defaultinference servingin Kimi K3Moonshot AI

It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.

usedmodel architecturein MiMo-V2.6-ProXiaomi

Provides complete access to the model's reasoning process, facilitating easier debugging and greater trust in outputs.

usedotherin gpt-ossOpenAI

generate both COT and TIR solution trajectories with DeepSeek-V4-Pro

usedtraining objectivein Nemotron 3 Ultra (STEM teacher)NVIDIA

reasoning_effort: "no_think" (default), "low", "high" (deep chain-of-thought)

optionalinference servingin Hy3Tencent

reasoning_effort: 'no_think' (default, direct response), 'low', 'high' (deep chain-of-thought)

optionalinference servingin Hy3Tencent Hunyuan

Filed alongside

Other methods under inference & serving :: reasoning control.