Primary evidence
- OpenAI IMO 2025 ProofsS1 · Primary research · Repository
OpenAI reports gold-level performance on IMO 2025 with a general reasoning model
The model worked from official natural-language problem statements without a proof assistant or internet access during the evaluation.
What happened?
OpenAI reported that an experimental reasoning model scored 35/42 on IMO 2025, solving five of six problems in natural language; public proofs were graded by three former IMO medalists.
Why it matters
Alongside Gemini's officially coordinated result days later, it marked the transition of general reasoning models into elite Olympiad-level mathematics.
Significance rationale: The result was an early public demonstration that a general-purpose reasoning model could produce natural-language solutions at the IMO gold threshold.
Historical context
Earlier developments
Later developments
—
Evidence & status at a glance
- Significance
- H1 · Historical milestone
- Verification
- Independently corroborated
- Evidence level
- E2 · Research record
- AI role
- AI primary, human verified
- Formal assurance
- No formal assurance
Contribution & verification
- Mathematical novelty
- Benchmark result
- Interface
- Informal
- AI contribution
- The model generated complete natural-language proof attempts under contest-style constraints.
- Human contribution
- OpenAI researchers ran the evaluation and former IMO medalists graded the public solutions.
- Verification
- Independently corroborated · E2 · Research record · No formal assurance
- Last reviewed
- 2026-09-11
Technical details
- Systems
- openai-experimental-reasoning-model
- Organizations
- openai
- Problems
- international-mathematical-olympiad-2025
- Methods
- reasoning-model, test-time-compute, natural-language-proof
Sources & artifacts
- OpenAI IMO 2025 ProofsS1 · Primary research · Repository · accessed 2026-09-10
- OpenAI and Google outdo the mathletes, but not each otherS4 · Reputable secondary · Media report · accessed 2026-09-10
Verification history
- 2025-07-19 · Partially verified · E2 · Research record
The Chronicle records this event from the cited primary or official source; the status does not imply independent Chronicle verification.
- 2026-09-10 · Independently corroborated · E2 · Research record
Independent reporting corroborated the core event description: OpenAI's separate evaluation used public natural-language solutions graded by three former IMO medalists and produced a reported 35/42 gold-threshold score. The Chronicle preserves the important distinction that this was not the IMO-coordinated grading process used for Google's Gemini result.
Corrections
No corrections recorded.