Reasoning Models: OpenAI o1 and After

In 2024, a new class of models traded fast answers for slow, deliberate thinking, and benchmarks jumped.

25 min · Reviewed 2026

Thinking Longer, On Purpose

In September 2024, OpenAI previewed o1, a model that spent extra compute before answering, generating long internal chains of reasoning. On hard math, coding, and science benchmarks, o1 leapt past GPT-4o, sometimes by double-digit points on tests where progress had been crawling.

The core idea was not prompt-level chain of thought. It was training the model, often through reinforcement learning, to use its own thinking tokens effectively, and then letting it spend as many of those tokens as needed at inference time.

What reasoning models do well

Multi-step math and proofs where intermediate errors compound
Competitive programming problems requiring search
Scientific reasoning on benchmarks like GPQA Diamond
Agentic tasks that benefit from planning and reflection

Competitors followed quickly. Google's Gemini 2.0 Flash Thinking, DeepSeek's R1 in early 2025, and Anthropic's extended thinking mode all adopted variants of the paradigm. Some published training recipes openly; others kept them secret.

We've developed a new series of AI models designed to spend more time thinking before they respond.
— OpenAI, o1 announcement, 2024

The big idea: reasoning models reopened the scaling frontier by moving compute from training time into inference time. A model that can think longer is a different kind of model.

End-of-lesson check

8 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-history-reasoning-models-builders

What is the main idea of "Reasoning Models: OpenAI o1 and After"?
1. In 2024, a new class of models traded fast answers for slow, deliberate thinking, and benchmarks jumped.
2. Use AI as the final authority for the whole decision
3. Avoid checking the answer once it sounds polished
4. Focus only on speed instead of judgment
Which concept is most central to "Reasoning Models: OpenAI o1 and After"?
1. o1
2. reasoning models
3. inference-time compute
4. chain of thought
Which use of AI fits this topic best?
1. Let the AI decide what matters without your review
2. Use the answer before checking whether it fits the situation
3. Multi-step math and proofs where intermediate errors compound
4. Use the first answer without checking it
What should a careful learner remember about "Two axes of scaling"?
1. Use AI to draft or organize ideas about reasoning models, then verify before acting.
2. Skip the context so the tool can guess faster
3. Treat the output as private even after sharing it online
4. Use the answer without checking the source
You want to use AI after this lesson. What is the safest next step?
1. Act immediately because the AI answer is written clearly
2. Use the AI answer as a draft, then check it against a reliable source.
3. Hide uncertainty so the final answer looks cleaner
4. Use private or sensitive details before checking permission
How should AI output about reasoning models be treated?
1. As proof that no other source is needed
2. As a replacement for context, consent, or expert review
3. As a draft or helper output that still needs human judgment and verification
4. As something that becomes correct when it sounds confident
Name one way to verify an AI answer about reasoning models.
Which action would help you apply "Reasoning Models: OpenAI o1 and After" responsibly?
1. Use the tool to avoid thinking through the tradeoff
2. Keep going even if the output conflicts with a trusted source
3. Use the first answer without checking it
4. Competitive programming problems requiring search

← Back to interactive lesson

Tendril · Builders · AI Foundations

Reasoning Models: OpenAI o1 and After

In 2024, a new class of models traded fast answers for slow, deliberate thinking, and benchmarks jumped.

25 min · Reviewed 2026

Thinking Longer, On Purpose

What reasoning models do well

Multi-step math and proofs where intermediate errors compound
Competitive programming problems requiring search
Scientific reasoning on benchmarks like GPQA Diamond
Agentic tasks that benefit from planning and reflection

We've developed a new series of AI models designed to spend more time thinking before they respond.
— OpenAI, o1 announcement, 2024

The big idea: reasoning models reopened the scaling frontier by moving compute from training time into inference time. A model that can think longer is a different kind of model.

End-of-lesson check

8 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-history-reasoning-models-builders

What is the main idea of "Reasoning Models: OpenAI o1 and After"?
1. In 2024, a new class of models traded fast answers for slow, deliberate thinking, and benchmarks jumped.
2. Use AI as the final authority for the whole decision
3. Avoid checking the answer once it sounds polished
4. Focus only on speed instead of judgment
Which concept is most central to "Reasoning Models: OpenAI o1 and After"?
1. o1
2. reasoning models
3. inference-time compute
4. chain of thought
Which use of AI fits this topic best?
1. Let the AI decide what matters without your review
2. Use the answer before checking whether it fits the situation
3. Multi-step math and proofs where intermediate errors compound
4. Use the first answer without checking it
What should a careful learner remember about "Two axes of scaling"?
1. Use AI to draft or organize ideas about reasoning models, then verify before acting.
2. Skip the context so the tool can guess faster
3. Treat the output as private even after sharing it online
4. Use the answer without checking the source
You want to use AI after this lesson. What is the safest next step?
1. Act immediately because the AI answer is written clearly
2. Use the AI answer as a draft, then check it against a reliable source.
3. Hide uncertainty so the final answer looks cleaner
4. Use private or sensitive details before checking permission
How should AI output about reasoning models be treated?
1. As proof that no other source is needed
2. As a replacement for context, consent, or expert review
3. As a draft or helper output that still needs human judgment and verification
4. As something that becomes correct when it sounds confident
Name one way to verify an AI answer about reasoning models.
Which action would help you apply "Reasoning Models: OpenAI o1 and After" responsibly?
1. Use the tool to avoid thinking through the tradeoff
2. Keep going even if the output conflicts with a trusted source
3. Use the first answer without checking it
4. Competitive programming problems requiring search

← Back to interactive lesson