Who leads the AIME 2024 benchmark?

o1-preview currently leads AIME 2024 with a score of 83.3 on accuracy.

What is the state-of-the-art score on AIME 2024?

The state-of-the-art result on AIME 2024 is 83.3 (accuracy), achieved by o1-preview as of 2026.

How many models are tracked on AIME 2024?

Codesota tracks 3 models on AIME 2024.

When was the AIME 2024 leaderboard last updated?

The AIME 2024 leaderboard on Codesota includes results through 2026.

Codesota · Benchmark · AIME 2024Home/Leaderboards/Language & Knowledge/Mathematical Reasoning/AIME 2024

Unknown

AIME 2024.

Name: AIME 2024 Benchmark Results
Creator: Unknown
Published: 2026-01-01
License: https://creativecommons.org/licenses/by/4.0/

30 challenging math problems from the 2024 AIME competition. Tests advanced mathematical reasoning.

Paper ↗Leaderboard ↓Lineage

§ 01 · Leaderboard

Results by metric.

Only 3 models on this benchmark

Help build the community leaderboard — submit your model results.

Found a wrong score or missing run?

Use row edits to send a sourced correction into moderation.

Add / edit result ↗Report issue ↗

accuracy

Accuracy is the reported evaluation metric for AIME 2024. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for accuracyverifiedpapervendorcommunityunverified

Muted rows were not state of the art when published — an earlier or same-year result already scored better.

Rank	Model	Trust	Score	Year	Links	Fix
01	o1-preview Non-API entry from src	unverified	83.3	2026	N/A	Looks wrong?
02	claude-35-opus Non-API entry from src	unverified	16	2026	N/A	Looks wrong?
03	gpt-4o Non-API entry from src	unverified	13.4	2026	N/A	Looks wrong?

Lineage

AIME 2024 in context.

See full mathematical reasoning benchmarks lineage →

Predecessors (1)

saturating2021-11

MATH

AIME is not an AI benchmark by origin — it is the human competition that feeds into USAMO/IMO. It became an AI frontier benchmark when o1 started scoring competitively. Because it is updated annually with fresh problems, it provides contamination control that MATH (fixed dataset) cannot.

This benchmark (1)

active2024-03

AIME 2024

Successors (1)

active2024-11

FrontierMath

AIME problems are finite and increasingly contaminated as training sets grow. FrontierMath sources unpublished research-frontier problems — contamination by design impossible. The step change from competition math to research math.

§ 04 · Submit a result

Add to the leaderboard.

Submit a Result

← Back to Mathematical Reasoning