OpenAI o1: reasoning models trained with reinforcement learning
Confirmed
Importance: historic (5 of 5)The takeaway
OpenAI released o1-preview and o1-mini, models trained with large-scale RL to ‘think’ via a long private chain of thought before answering, yielding large gains in math, science and coding and introducing test-time compute scaling.
Status
- Claim
Confirmed
- Our reporting
- High confidence
- Importance
- Historic (5 of 5)
- Last verified
- 29 September 2026
Your AI and this story
- GPT-6 AstraIn its training data
- Claude Opus 5.5In its training data
- Gemini 4 HydrogenIn its training data
- Grok 4.7In its training data
It happened before the cutoffs of all four assistants, so it can be in their training data.
Key facts
- Announced 12 September 2024 (o1-preview, o1-mini); full o1 released 5 December 2024
- AIME 2024: o1 averaged 74% (single sample) vs 12% for GPT-4o, per OpenAI
- Exceeded PhD-level accuracy on GPQA Diamond science questions, per OpenAI
- Performance improved with both more RL training compute and more thinking time
- Codenamed ‘Strawberry’ in press reports
What happened
OpenAI introduced a new model series that spends variable inference-time compute reasoning before responding.
Why it matters
Opened the ‘reasoning model’ era and a new scaling axis (test-time compute); every major lab followed within months.
Sources
2 sources from 1 site. Numbers match the chips in the text.
2 sources: 2 primary
Primary
- Learning to reason with LLMs (OpenAI)openai.com, official
- Introducing OpenAI o1-preview (OpenAI)openai.com, official
Changes
- Filed