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 Directory

Scoring & Data

Scoring & Data
1367 models808 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 Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

math benchmark

AIME 2024 Leaderboard

AIME 2024 is a set of 30 challenging mathematical reasoning problems from the AIME I and AIME II competitions.

Updated Oct 23, 2026

Models54
Model coverage54
MetricScore
EvidenceB

On this page

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

AIME 2024 Ranking

Higher score ranks better on this benchmark.

30 of 54 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelXAGrok-3 MinixAIScore95.80%Percentile100.00%Participants54EvidenceCEvaluatedOct 22, 2026
Rank02ModelOPo4-miniOpenAIScore93.40%Percentile98.11%Participants54EvidenceCEvaluatedOct 22, 2026
Rank03ModelXAGrok-3xAIScore93.30%Percentile96.23%Participants54EvidenceCEvaluatedOct 22, 2026
Rank04ModelMELongCat-Flash-ThinkingMeituanScore93.30%Percentile94.34%Participants54EvidenceCEvaluatedOct 22, 2026
Rank05ModelGOGemini 2.5 ProGoogleScore92.00%Percentile92.45%Participants54EvidenceCEvaluatedOct 22, 2026
Rank06ModelOPo3OpenAIScore91.60%Percentile90.57%Participants54EvidenceCEvaluatedOct 22, 2026
Rank07ModelDEDeepSeek-R1-0528DeepSeekScore91.40%Percentile88.68%Participants54EvidenceCEvaluatedOct 22, 2026
Rank08ModelZAGLM-4.5Zhipu AIScore91.00%Percentile86.79%Participants54EvidenceCEvaluatedOct 22, 2026
Rank09ModelMAMinistral 3 (14B Reasoning 2512)Mistral AIScore89.80%Percentile84.91%Participants54EvidenceCEvaluatedOct 22, 2026
Rank10ModelZAGLM-4.5-AirZhipu AIScore89.40%Percentile83.02%Participants54EvidenceCEvaluatedOct 22, 2026
Rank11ModelGOGemini 2.5 FlashGoogleScore88.00%Percentile81.13%Participants54EvidenceCEvaluatedOct 22, 2026
Rank12ModelOPo3-miniOpenAIScore87.30%Percentile79.25%Participants54EvidenceCEvaluatedOct 22, 2026
Rank13ModelDEDeepSeek R1 Distill Llama 70BDeepSeekScore86.70%Percentile77.36%Participants54EvidenceCEvaluatedOct 22, 2026
Rank14ModelDEDeepSeek R1 ZeroDeepSeekScore86.70%Percentile75.47%Participants54EvidenceCEvaluatedOct 22, 2026
Rank15ModelMIMiniMax M1 80KMiniMaxScore86.00%Percentile73.58%Participants54EvidenceCEvaluatedOct 22, 2026
Rank16ModelMAMinistral 3 (8B Reasoning 2512)Mistral AIScore86.00%Percentile71.70%Participants54EvidenceCEvaluatedOct 22, 2026
Rank17ModelOPo1-proOpenAIScore86.00%Percentile69.81%Participants54EvidenceCEvaluatedOct 22, 2026
Rank18ModelACQwen3 235B A22BAlibaba Cloud / Qwen TeamScore85.70%Percentile67.92%Participants54EvidenceCEvaluatedOct 22, 2026
Rank19ModelOPMiniCPM-SALAOpenBMBScore83.75%Percentile66.04%Participants54EvidenceCEvaluatedOct 22, 2026
Rank20ModelDEDeepSeek R1 Distill Qwen 7BDeepSeekScore83.30%Percentile64.15%Participants54EvidenceCEvaluatedOct 22, 2026
Rank21ModelDEDeepSeek R1 Distill Qwen 32BDeepSeekScore83.30%Percentile62.26%Participants54EvidenceCEvaluatedOct 22, 2026
Rank22ModelMIMiniMax M1 40KMiniMaxScore83.30%Percentile60.38%Participants54EvidenceCEvaluatedOct 22, 2026
Rank23ModelACQwen3 32BAlibaba Cloud / Qwen TeamScore81.40%Percentile58.49%Participants54EvidenceCEvaluatedOct 22, 2026
Rank24ModelMIPhi 4 Reasoning PlusMicrosoftScore81.30%Percentile56.60%Participants54EvidenceCEvaluatedOct 22, 2026
Rank25ModelIBGranite 3.3 8B BaseIBMScore81.20%Percentile54.72%Participants54EvidenceCEvaluatedOct 22, 2026
Rank26ModelIBGranite 3.3 8B InstructIBMScore81.20%Percentile52.83%Participants54EvidenceCEvaluatedOct 22, 2026
Rank27ModelACQwen3 30B A3BAlibaba Cloud / Qwen TeamScore80.40%Percentile50.94%Participants54EvidenceCEvaluatedOct 22, 2026
Rank28ModelANClaude 3.7 SonnetAnthropicScore80.00%Percentile49.06%Participants54EvidenceCEvaluatedOct 22, 2026
Rank29ModelDEDeepSeek R1 Distill Llama 8BDeepSeekScore80.00%Percentile47.17%Participants54EvidenceCEvaluatedOct 22, 2026
Rank30ModelDEDeepSeek R1 Distill Qwen 14BDeepSeekScore80.00%Percentile45.28%Participants54EvidenceCEvaluatedOct 22, 2026

AIME 2024 Highlights

The leading models and scores on this benchmark.

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.

What is AIME 2024?

What AIME 2024 measures and how its scores work.

AIME 2024 is a math benchmark consisting of problems from the 2024 American Invitational Mathematics Examination, with each problem requiring an integer answer between 0-999.

It measures mathematical reasoning capabilities across algebra, geometry, combinatorics, and number theory at Olympiad-level difficulty using the Score metric.

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
No
Evaluation key
overall

LLM Stats. 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 95.80%.

What are the top three models on AIME 2024?

The current leaders are Grok-3 Mini (95.80%), o4-mini (93.40%), and Grok-3 (93.30%).

Which AIME 2024 model has the lowest official input price?

Min istral 3 (3B Reasoning 2512) has the lowest matched official input price at $0.10 input / $0.10 output per 1M tokens.

Which models are fastest among AIME 2024 results?

The fastest matched records are Min istral 3 (3B Reasoning 2512) (1,222.00 tok/s via Mistral AI), Qwen3 32B (327.70 tok/s via Sambanova), and Ministral 3 (8B Reasoning 2512) (237.50 tok/s via Mistral AI).

Does the highest score result prove overall model quality?

No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.

What does AIME 2024 measure?

It measures mathematical reasoning capabilities across algebra, geometry, combinatorics, and number theory at Olympiad-level difficulty using the Score metric.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

54 model results are currently shown.

Does this benchmark affect the overall score?

No. This benchmark is shown for reference but does not contribute to the overall score.

Rank #1Grok-3 Mini95.80%
Rank #2o4-mini93.40%
Rank #3Grok-393.30%
Rank #4LongCat-Flash-Thinking93.30%

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

  1. 01
    XA
    Grok-3 MinixAI
    Score
    95.80%
    Speed
    Up to 100.00 tok/s via xAI

    Strengths

    • Ranks #1 of 54 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
    93.40%
    Price
    $1.1 input / $4.4 output per 1M tokens
    Speed
    Up to 115.00 tok/s via OpenAI

    Strengths

    • Ranks #2 of 54 compared models
    • 98th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures AIME 2024, not total model capability
  3. 03
    XA
    xAI
    Score
    93.30%
    Speed
    Up to 100.00 tok/s via xAI

    Strengths

    • Ranks #3 of 54 compared models
    • 96th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures AIME 2024, not total model capability
  4. 04
    ME
    Meituan
    Score
    93.30%

    Strengths

    • Ranks #4 of 54 compared models
    • 94th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures AIME 2024, not total model capability
  5. 05
    GO
    Google
    Score
    92.00%
    Price
    $1.3 input / $10 output per 1M tokens
    Speed
    Up to 85.00 tok/s via Google

    Strengths

    • Ranks #5 of 54 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 95.80%. 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.

Grok-3
LongCat-Flash-Thinking
Gemini 2.5 Pro
Benchmark rank #1Grok-3 Mini95.80% · Up to 100.00 tok/s via xAI
Benchmark rank #2o4-mini93.40% · $1.1 input / $4.4 output per 1M tokens
Benchmark rank #3Grok-393.30% · Up to 100.00 tok/s via xAI