llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model DirectoryCompare Models

Scoring & Data

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 Leaderboard

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 17, 2026

Models53
Model coverage53
MetricScore
EvidenceB

On this page

  • Ranking
  • Highlights
  • Distribution
  • Top models
  • About
  • FAQ

AIME 2024 Ranking

Higher score ranks better on this benchmark.

30 of 53 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelXAGrok-3 MinixAIScore95.8%Percentile100.0%Participants53EvidenceCEvaluatedAug 17, 2026
Rank02ModelOPo4-miniOpenAIScore93.4%Percentile98.1%Participants53EvidenceCEvaluatedAug 17, 2026
Rank03ModelXAGrok-3xAIScore93.3%Percentile96.2%Participants53EvidenceCEvaluatedAug 17, 2026
Rank04ModelMELongCat-Flash-ThinkingMeituanScore93.3%Percentile94.2%Participants53EvidenceCEvaluatedAug 17, 2026
Rank05ModelGOGemini 2.5 ProGoogleScore92.0%Percentile92.3%Participants53EvidenceCEvaluatedAug 17, 2026
Rank06ModelOPo3OpenAIScore91.6%Percentile90.4%Participants53EvidenceCEvaluatedAug 17, 2026
Rank07ModelDEDeepSeek-R1-0528DeepSeekScore91.4%Percentile88.5%Participants53EvidenceCEvaluatedAug 17, 2026
Rank08ModelZAGLM-4.5Zhipu AIScore91.0%Percentile86.5%Participants53EvidenceCEvaluatedAug 17, 2026
Rank09ModelMAMinistral 3 (14B Reasoning 2512)Mistral AIScore89.8%Percentile84.6%Participants53EvidenceCEvaluatedAug 17, 2026
Rank10ModelZAGLM-4.5-AirZhipu AIScore89.4%Percentile82.7%Participants53EvidenceCEvaluatedAug 17, 2026
Rank11ModelGOGemini 2.5 FlashGoogleScore88.0%Percentile80.8%Participants53EvidenceCEvaluatedAug 17, 2026
Rank12ModelOPo3-miniOpenAIScore87.3%Percentile78.8%Participants53EvidenceCEvaluatedAug 17, 2026
Rank13ModelDEDeepSeek R1 Distill Llama 70BDeepSeekScore86.7%Percentile76.9%Participants53EvidenceCEvaluatedAug 17, 2026
Rank14ModelDEDeepSeek R1 ZeroDeepSeekScore86.7%Percentile75.0%Participants53EvidenceCEvaluatedAug 17, 2026
Rank15ModelMIMiniMax M1 80KMiniMaxScore86.0%Percentile73.1%Participants53EvidenceCEvaluatedAug 17, 2026
Rank16ModelMAMinistral 3 (8B Reasoning 2512)Mistral AIScore86.0%Percentile71.2%Participants53EvidenceCEvaluatedAug 17, 2026
Rank17ModelOPo1-proOpenAIScore86.0%Percentile69.2%Participants53EvidenceCEvaluatedAug 17, 2026
Rank18ModelACQwen3 235B A22BAlibaba Cloud / Qwen TeamScore85.7%Percentile67.3%Participants53EvidenceCEvaluatedAug 17, 2026
Rank19ModelOPMiniCPM-SALAOpenBMBScore83.8%Percentile65.4%Participants53EvidenceCEvaluatedAug 17, 2026
Rank20ModelDEDeepSeek R1 Distill Qwen 32BDeepSeekScore83.3%Percentile63.5%Participants53EvidenceCEvaluatedAug 17, 2026
Rank21ModelDEDeepSeek R1 Distill Qwen 7BDeepSeekScore83.3%Percentile61.5%Participants53EvidenceCEvaluatedAug 17, 2026
Rank22ModelMIMiniMax M1 40KMiniMaxScore83.3%Percentile59.6%Participants53EvidenceCEvaluatedAug 17, 2026
Rank23ModelACQwen3 32BAlibaba Cloud / Qwen TeamScore81.4%Percentile57.7%Participants53EvidenceCEvaluatedAug 17, 2026
Rank24ModelMIPhi 4 Reasoning PlusMicrosoftScore81.3%Percentile55.8%Participants53EvidenceCEvaluatedAug 17, 2026
Rank25ModelIBGranite 3.3 8B BaseIBMScore81.2%Percentile53.9%Participants53EvidenceCEvaluatedAug 17, 2026
Rank26ModelIBGranite 3.3 8B InstructIBMScore81.2%Percentile51.9%Participants53EvidenceCEvaluatedAug 17, 2026
Rank27ModelACQwen3 30B A3BAlibaba Cloud / Qwen TeamScore80.4%Percentile50.0%Participants53EvidenceCEvaluatedAug 17, 2026
Rank28ModelANClaude 3.7 SonnetAnthropicScore80.0%Percentile48.1%Participants53EvidenceCEvaluatedAug 17, 2026
Rank29ModelDEDeepSeek R1 Distill Llama 8BDeepSeekScore80.0%Percentile46.1%Participants53EvidenceCEvaluatedAug 17, 2026
Rank30ModelDEDeepSeek R1 Distill Qwen 14BDeepSeekScore80.0%Percentile44.2%Participants53EvidenceCEvaluatedAug 17, 2026
Rank31ModelACQwQ-32BAlibaba Cloud / Qwen TeamScore79.5%Percentile42.3%Participants53EvidenceCEvaluatedAug 17, 2026
Rank32ModelMAKimi-k1.5Moonshot AIScore77.5%Percentile40.4%Participants53EvidenceCEvaluatedAug 17, 2026
Rank33ModelMAMin istral 3 (3B Reasoning 2512)Mistral AIScore77.5%Percentile38.5%Participants53EvidenceCEvaluatedAug 17, 2026
Rank34ModelMIPhi 4 ReasoningMicrosoftScore75.3%Percentile36.5%Participants53EvidenceCEvaluatedAug 17, 2026
Rank35ModelOPo1OpenAIScore74.3%Percentile34.6%Participants53EvidenceCEvaluatedAug 17, 2026
Rank36ModelMAMagistral MediumMistral AIScore73.6%Percentile32.7%Participants53EvidenceCEvaluatedAug 17, 2026
Rank37ModelGOGemini 2.0 Flash ThinkingGoogleScore73.3%Percentile30.8%Participants53EvidenceCEvaluatedAug 17, 2026
Rank38ModelMELongCat-Flash-LiteMeituanScore72.2%Percentile28.9%Participants53EvidenceCEvaluatedAug 17, 2026
Rank39ModelMAKimi K2 0905Moonshot AIScore72.0%Percentile26.9%Participants53EvidenceCEvaluatedAug 17, 2026
Rank40ModelMAMagistral Small 2506Mistral AIScore70.7%Percentile25.0%Participants53EvidenceCEvaluatedAug 17, 2026
Rank41ModelMAKimi K2 InstructMoonshot AIScore69.6%Percentile23.1%Participants53EvidenceCEvaluatedAug 17, 2026
Rank42ModelMAKimi K2-Instruct-0905Moonshot AIScore69.6%Percentile21.1%Participants53EvidenceCEvaluatedAug 17, 2026
Rank43ModelDEDeepSeek-V3.1DeepSeekScore66.3%Percentile19.2%Participants53EvidenceCEvaluatedAug 17, 2026
Rank44ModelDEDeepSeek-V3 0324DeepSeekScore59.4%Percentile17.3%Participants53EvidenceCEvaluatedAug 17, 2026
Rank45ModelDEDeepSeek R1 Distill Qwen 1.5BDeepSeekScore52.7%Percentile15.4%Participants53EvidenceCEvaluatedAug 17, 2026
Rank46ModelACQwQ-32B-PreviewAlibaba Cloud / Qwen TeamScore50.0%Percentile13.5%Participants53EvidenceCEvaluatedAug 17, 2026
Rank47ModelOPGPT-4.1 miniOpenAIScore49.6%Percentile11.5%Participants53EvidenceCEvaluatedAug 17, 2026
Rank48ModelOPGPT-4.1OpenAIScore48.1%Percentile9.6%Participants53EvidenceCEvaluatedAug 17, 2026
Rank49ModelOPo1-previewOpenAIScore42.0%Percentile7.7%Participants53EvidenceCEvaluatedAug 17, 2026
Rank50ModelDEDeepSeek-V3DeepSeekScore39.2%Percentile5.8%Participants53EvidenceCEvaluatedAug 17, 2026
Rank51ModelOPGPT-4.5OpenAIScore36.7%Percentile3.9%Participants53EvidenceCEvaluatedAug 17, 2026
Rank52ModelOPGPT-4.1 nanoOpenAIScore29.4%Percentile1.9%Participants53EvidenceCEvaluatedAug 17, 2026
Rank53ModelOPGPT-4oOpenAIScore13.1%Percentile0.0%Participants53EvidenceCEvaluatedAug 17, 2026

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%

AIME 2024 Score Distribution

A closer view of the leading scores on this benchmark.

AIME 2024

The Top AI Models for AIME 2024

The first five results on this benchmark, with official price and output speed added where the model identity can be matched.

Ranking basisThis aime 2024 AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.

  1. 01
    XA
    Grok-3 MinixAI
    Score
    95.8%
    Speed
    Up to 100 tok/s via xAI

    Strengths

    • Ranks #1 of 53 compared models
    • 100th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures AIME 2024, not total model capability
  2. 02
    OP
    o4-miniOpenAI
    Score
    93.4%
    Price
    $1.1 input / $4.4 output per 1M tokens
    Speed
    Up to 115 tok/s via OpenAI

    Strengths

    • Ranks #2 of 53 compared models
    • 98th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures AIME 2024, not total model capability
  3. 03
    XA
    Grok-3xAI
    Score
    93.3%
    Speed
    Up to 100 tok/s via xAI

    Strengths

    • Ranks #3 of 53 compared models
    • 96th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures AIME 2024, not total model capability
  4. 04
    ME
    LongCat-Flash-ThinkingMeituan
    Score
    93.3%
    Speed
    Up to 100 tok/s via Meituan

    Strengths

    • Ranks #4 of 53 compared models
    • 94th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures AIME 2024, not total model capability
  5. 05
    GO
    Gemini 2.5 ProGoogle
    Score
    92.0%
    Price
    $1.3 input / $10 output per 1M tokens
    Speed
    Up to 86 tok/s via Google

    Strengths

    • Ranks #5 of 53 compared models
    • 92th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures AIME 2024, not total model capability

Selection summary

Best AI Models for AIME 2024

Grok-3 Mini currently leads AIME 2024 with 95.8%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.

Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.

Benchmark rank #1Grok-3 Mini95.8% · Up to 100 tok/s via xAIBenchmark rank #2o4-mini93.4% · $1.1 input / $4.4 output per 1M tokensBenchmark rank #3Grok-393.3% · Up to 100 tok/s via xAI

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.