llmboard.aiLeaderboard Center
Overall
Overall RankingOpen Models
Tools
Model DirectoryCompare Models
Capabilities
CodingReasoningMathKnowledgeInstruction Following
Price & Efficiency
Price & ValueCapability vs. PriceRuntime Performance
Modalities
Image GenerationVideo GenerationSpeech ModelsEmbeddings
Core Benchmarks
GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-ProView all benchmarks
Methods
Scoring & Data
393 models668 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll BenchmarksReasoningMath

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai

math benchmark

AIME 2024

American Invitational Mathematics Examination 2024, consisting of 30 challenging mathematical reasoning problems from AIME I and AIME II competitions. Each problem requires an integer answer between 0-999 and tests advanced mathematical reasoning across algebra, geometry, combinatorics, and number theory. Used as a benchmark for evaluating mathematical reasoning capabilities in large language models at Olympiad-level difficulty.

Updated Aug 11, 2026

Models53
Model coverage53
MetricScore
EvidenceB

On this page

  • Ranking
  • Distribution
  • Highlights
  • About
  • FAQ

AIME 2024 Ranking

Higher score ranks better on this benchmark.

53 rows
Columns

Show columns

01XAGrok-3 MinixAI95.8%100.0%53CAug 11, 2026
02OPo4-miniOpenAI93.4%98.1%53CAug 11, 2026
03XAGrok-3xAI93.3%96.2%53CAug 11, 2026
04MELongCat-Flash-ThinkingMeituan93.3%94.2%53CAug 11, 2026
05GOGemini 2.5 ProGoogle92.0%92.3%53CAug 11, 2026
06OPo3OpenAI91.6%90.4%53CAug 11, 2026
07DEDeepSeek-R1-0528DeepSeek91.4%88.5%53CAug 11, 2026
08ZAGLM-4.5Zhipu AI91.0%86.5%53CAug 11, 2026
09MAMinistral 3 (14B Reasoning 2512)Mistral AI89.8%84.6%53CAug 11, 2026
10ZAGLM-4.5-AirZhipu AI89.4%82.7%53CAug 11, 2026
11GOGemini 2.5 FlashGoogle88.0%80.8%53CAug 11, 2026
12OPo3-miniOpenAI87.3%78.8%53CAug 11, 2026
13DEDeepSeek R1 Distill Llama 70BDeepSeek86.7%76.9%53CAug 11, 2026
14DEDeepSeek R1 ZeroDeepSeek86.7%75.0%53CAug 11, 2026
15MIMiniMax M1 80KMiniMax86.0%73.1%53CAug 11, 2026
16MAMinistral 3 (8B Reasoning 2512)Mistral AI86.0%71.2%53CAug 11, 2026
17OPo1-proOpenAI86.0%69.2%53CAug 11, 2026
18ACQwen3 235B A22BAlibaba Cloud / Qwen Team85.7%67.3%53CAug 11, 2026
19OPMiniCPM-SALAOpenBMB83.8%65.4%53CAug 11, 2026
20DEDeepSeek R1 Distill Qwen 32BDeepSeek83.3%63.5%53CAug 11, 2026
21DEDeepSeek R1 Distill Qwen 7BDeepSeek83.3%61.5%53CAug 11, 2026
22MIMiniMax M1 40KMiniMax83.3%59.6%53CAug 11, 2026
23ACQwen3 32BAlibaba Cloud / Qwen Team81.4%57.7%53CAug 11, 2026
24MIPhi 4 Reasoning PlusMicrosoft81.3%55.8%53CAug 11, 2026
25IBGranite 3.3 8B BaseIBM81.2%53.9%53CAug 11, 2026
26IBGranite 3.3 8B InstructIBM81.2%51.9%53CAug 11, 2026
27ACQwen3 30B A3BAlibaba Cloud / Qwen Team80.4%50.0%53CAug 11, 2026
28ANClaude 3.7 SonnetAnthropic80.0%48.1%53CAug 11, 2026
29DEDeepSeek R1 Distill Llama 8BDeepSeek80.0%46.1%53CAug 11, 2026
30DEDeepSeek R1 Distill Qwen 14BDeepSeek80.0%44.2%53CAug 11, 2026
31ACQwQ-32BAlibaba Cloud / Qwen Team79.5%42.3%53CAug 11, 2026
32MAKimi-k1.5Moonshot AI77.5%40.4%53CAug 11, 2026
33MAMin istral 3 (3B Reasoning 2512)Mistral AI77.5%38.5%53CAug 11, 2026
34MIPhi 4 ReasoningMicrosoft75.3%36.5%53CAug 11, 2026
35OPo1OpenAI74.3%34.6%53CAug 11, 2026
36MAMagistral MediumMistral AI73.6%32.7%53CAug 11, 2026
37GOGemini 2.0 Flash ThinkingGoogle73.3%30.8%53CAug 11, 2026
38MELongCat-Flash-LiteMeituan72.2%28.9%53CAug 11, 2026
39MAKimi K2 0905Moonshot AI72.0%26.9%53CAug 11, 2026
40MAMagistral Small 2506Mistral AI70.7%25.0%53CAug 11, 2026
41MAKimi K2 InstructMoonshot AI69.6%23.1%53CAug 11, 2026
42MAKimi K2-Instruct-0905Moonshot AI69.6%21.1%53CAug 11, 2026
43DEDeepSeek-V3.1DeepSeek66.3%19.2%53CAug 11, 2026
44DEDeepSeek-V3 0324DeepSeek59.4%17.3%53CAug 11, 2026
45DEDeepSeek R1 Distill Qwen 1.5BDeepSeek52.7%15.4%53CAug 11, 2026
46ACQwQ-32B-PreviewAlibaba Cloud / Qwen Team50.0%13.5%53CAug 11, 2026
47OPGPT-4.1 miniOpenAI49.6%11.5%53CAug 11, 2026
48OPGPT-4.1OpenAI48.1%9.6%53CAug 11, 2026
49OPo1-previewOpenAI42.0%7.7%53CAug 11, 2026
50DEDeepSeek-V3DeepSeek39.2%5.8%53CAug 11, 2026
51OPGPT-4.5OpenAI36.7%3.9%53CAug 11, 2026
52OPGPT-4.1 nanoOpenAI29.4%1.9%53CAug 11, 2026
53OPGPT-4oOpenAI13.1%0.0%53CAug 11, 2026

AIME 2024 Score Distribution

A closer view of the leading scores on this benchmark.

AIME 2024

AIME 2024 Highlights

The leading models and scores on this benchmark.

Rank #1Grok-3 Mini95.8%Rank #2o4-mini93.4%Rank #3Grok-393.3%Rank #4LongCat-Flash-Thinking93.3%

What is AIME 2024?

What AIME 2024 measures and how its scores work.

American Invitational Mathematics Examination 2024, consisting of 30 challenging mathematical reasoning problems from AIME I and AIME II competitions. Each problem requires an integer answer between 0-999 and tests advanced mathematical reasoning across algebra, geometry, combinatorics, and number theory. Used as a benchmark for evaluating mathematical reasoning capabilities in large language models at Olympiad-level difficulty.

Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.

Family
AIME 2024
Modality
text
Primary category
math
Score direction
higher
LLMBoard eligible
Yes
Evaluation key
aime-2024|llm-stats-current

Benchmark scores retain their original unit. Overall score eligibility is shown separately.

FAQ

Common questions about AIME 2024.

Which model scores highest on AIME 2024?

Grok-3 Mini is currently ranked first with 95.8%.

What does AIME 2024 measure?

American Invitational Mathematics Examination 2024, consisting of 30 challenging mathematical reasoning problems from AIME I and AIME II competitions. Each problem requires an integer answer between 0-999 and tests advanced mathematical reasoning across algebra, geometry, combinatorics, and number theory. Used as a benchmark for evaluating mathematical reasoning capabilities in large language models at Olympiad-level difficulty.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

53 model results are currently shown.

Does this benchmark affect the overall score?

Yes. This benchmark can contribute to the current LLMBoard capability score.