{"data":{"slug":"aime","etype":"benchmark","name":"AIME (Competition Math)","cat":"Capability","subtitle":"Olympiad-track problems — where reasoning models showed their jump.","summary":"The American Invitational Mathematics Examination became the standard hard-math benchmark because it resists pattern-matching: GPT-4o scored ~12%, o1 ~74–83%, and 2025 reasoning models near-perfect — the single clearest before/after of test-time compute. Gold-medal IMO performances by DeepMind and OpenAI systems in 2025 extended the story.","attrs":null,"kf":null,"aliases":["competition math","IMO"],"ticker":null,"exchange":null,"hq":null,"founded":null,"website":null,"status":null,"region":null,"asof":"2026-01-15","sources":[{"url":"https://maa.org/maa-invitational-competitions/","label":"MAA AIME"}]},"meta":{"found":true,"count":1,"served_from":"site cache (no live upstream calls)","as_of":"2026-10-14T06:34:33+00:00","disclaimer":"Research and information only — not investment advice. Structured records carry basis labels (vendor spec / reported / estimate); market quotes are delayed/indicative.","attribution":"Records compiled from vendor documentation, official filings and reputable public reporting; market quotes via financial data providers. See /data-sources."}}