AIME 2026
Accuracy of LLMs on the 30 problems of the 2026 American Invitational Mathematics Examination (AIME I and II), a contamination-free competition-math benchmark requiring integer answers (0-999), evaluated live by MathArena.
What this benchmark measures
Accuracy of LLMs on the 30 problems of the 2026 American Invitational Mathematics Examination (AIME I and II), a contamination-free competition-math benchmark requiring integer answers (0-999), evaluated live by MathArena.
Rows on this page are sourced from public benchmark artifacts, leaderboard exports, or source-linked model reports. Each row keeps benchmark version, source model name, and available run details attached to the score.
The metric shown here is accuracy. It should be interpreted within AIME 2026, not compared as part of a site-wide ranking.
Frequently asked
What is AIME 2026?
Accuracy of LLMs on the 30 problems of the 2026 American Invitational Mathematics Examination (AIME I and II), a contamination-free competition-math benchmark requiring integer answers (0-999), evaluated live by MathArena. It is a reasoning benchmark measured by accuracy.
What does accuracy mean on AIME 2026?
AIME 2026 reports accuracy (%); higher is better. Scores are shown only within AIME 2026 and are never averaged with other benchmarks.
What is the top reported AIME 2026 score?
Claude Opus 4.8 has the top reported score on AIME 2026: 100.00% (accuracy).
Why do AIME 2026 scores differ across runs?
Harness, scaffold, reasoning effort, and prompt setup change results, so two runs of the same model can differ. evals.report keeps each score with its run context so the differences stay visible.
Does evals.report rank models across benchmarks?
No. AIME 2026 scores are shown within their own metric; evals.report never combines benchmarks into a composite ranking or a single "best model".