Primary evidence
- Learning to reason with LLMsS2 · Official institutional · Official announcement · 2024-09-12
OpenAI o1 introduces inference-time reasoning with a large AIME performance jump
The o1 series was trained to spend more inference-time computation on multi-step reasoning before producing an answer.
What happened?
OpenAI reported o1 at 74% single-sample accuracy on AIME 2024 and 93% after reranking 1,000 samples, far above GPT-4o's 12% baseline.
Why it matters
The release helped establish test-time compute and long reasoning traces as central levers for frontier mathematical performance, providing context for later math-specific systems.
Significance rationale: OpenAI o1 was a major general-purpose reasoning-model release, but its place in the AI4Math Chronicle is contextual: AIME demonstrated capability rather than the release itself contributing a new mathematical result, proof, formalization, or math-specific system.
Historical context
Earlier developments
Later developments
—
Related milestones
—
Evidence & status at a glance
- Significance
- H3 · Context event
- Verification
- Claimed
- Evidence level
- E1 · Primary claim
- AI role
- Computation only
- Formal assurance
- No formal assurance
Contribution & verification
- Mathematical novelty
- Benchmark result
- Interface
- Informal, Symbolic
- AI contribution
- The model performs extended internal reasoning before answering mathematical problems.
- Human contribution
- OpenAI researchers designed the reasoning training method and benchmark evaluations.
- Verification
- Claimed · E1 · Primary claim · No formal assurance
- Last reviewed
- 2026-09-11
Technical details
- Systems
- openai-o1
- Organizations
- openai
- Problems
- aime-2024
- Methods
- reasoning-model, test-time-compute, reinforcement-learning
Sources & artifacts
- Learning to reason with LLMsS2 · Official institutional · Official announcement · accessed 2026-09-10
Verification history
- 2024-09-12 · Claimed · E1 · Primary claim
The Chronicle records this event from the cited primary or official source; the status does not imply independent Chronicle verification.
Corrections
No corrections recorded.