0

AIME 2025: Problems from the American Invitational Mathematics Examination

Saturated

A benchmark for evaluating AI's ability to solve challenging mathematics problems from the 2025 AIME - a prestigious high school mathematics competition.

Open
Publisher
Mathematical Association of America (MAA)
Domain
Mathematics
License
mit
Published
Oct 2025
Notable for
Benchmark for evaluating Mathematics.
Canonical
github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/aime2025

Cite

Notes

Only stored in your browser.

Attribution

Leaderboard scores
AAprime-hub
Attribution policy →

Top score 99.0% by GPT-5.2 - 205 models reporting (46 frontier)

Score history

205
0%25%50%75%100%Apr 24Sep 24Feb 25Jul 25Dec 25Phi-3 Mini Instruct 3.8BGPT-4o-minio1 PreviewGrok 3 minio4 MiniGrok 4GPT-5 CodexGPT-5.2

Top models

205
AIME 2025: Problems from the American Invitational Mathematics ExaminationBar chart with 21 bars. Highest value: GPT-5.2 at 99.
21 models

Related tools

5
View all

Implementations, trainers, datasets and scaffolds linked to this eval.

Aime2025 (Dev Team)

Dev Team

AIME-25 evaluation environment

ImplementationRL EnvMath

Aime2025 (Prime Intellect)

Prime Intellect

AIME-25 evaluation environment

ImplementationRL EnvMathV1

Aime2025 (Sboesen)

AIME-25 evaluation environment

ImplementationRL EnvMath

Vf Openbench (Aarush)

Environment for single-turn tasks in OpenBench

Trains towardRL Env

Deepconf

DeepConf environment for confidence-aware LLM reasoning evaluation

Trains towardRL EnvMathReasoningDeepconf

FAQ

What is AIME 2025: Problems from the American Invitational Mathematics Examination?
A benchmark for evaluating AI's ability to solve challenging mathematics problems from the 2025 AIME - a prestigious high school mathematics competition.
What is the current top score on AIME 2025: Problems from the American Invitational Mathematics Examination?
The top reported score is 99.0% by GPT-5.2, across 205 models reporting (46 from frontier labs).
How can a model improve its AIME 2025: Problems from the American Invitational Mathematics Examination score?
Tools linked to AIME 2025: Problems from the American Invitational Mathematics Examination on Sophon include Aime2025 (Dev Team), Aime2025 (Prime Intellect), Aime2025 (Sboesen), Vf Openbench (Aarush) - RL environments, datasets, and scaffolds that target this eval.
What license is AIME 2025: Problems from the American Invitational Mathematics Examination under?
AIME 2025: Problems from the American Invitational Mathematics Examination is available under mit.