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 2026 Leaderboard

All 30 problems from the 2026 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.

Updated Aug 17, 2026

Models21
Model coverage21
MetricScore
EvidenceB

On this page

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

AIME 2026 Ranking

Higher score ranks better on this benchmark.

21 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelZAGLM-5.2Zhipu AIScore99.2%Percentile100.0%Participants21EvidenceCEvaluatedAug 17, 2026
Rank02ModelSASakana NamazuSakana AIScore96.7%Percentile95.0%Participants21EvidenceCEvaluatedAug 17, 2026
Rank03ModelMAKimi K2.6Moonshot AIScore96.4%Percentile90.0%Participants21EvidenceCEvaluatedAug 17, 2026
Rank04ModelTMInkling-SmallThinking Machines LabScore95.5%Percentile85.0%Participants21EvidenceCEvaluatedAug 17, 2026
Rank05ModelZAGLM-5.1Zhipu AIScore95.3%Percentile80.0%Participants21EvidenceCEvaluatedAug 17, 2026
Rank06ModelACQwen3.6 PlusAlibaba Cloud / Qwen TeamScore95.3%Percentile75.0%Participants21EvidenceCEvaluatedAug 17, 2026
Rank07ModelUPSolar Pro 4UpstageScore95.3%Percentile70.0%Participants21EvidenceCEvaluatedAug 17, 2026
Rank08ModelMEMuse Glimmer-30BMetaScore94.7%Percentile65.0%Participants21EvidenceCEvaluatedAug 17, 2026
Rank09ModelMIMAI-Thinking-1MicrosoftScore94.5%Percentile60.0%Participants21EvidenceCEvaluatedAug 17, 2026
Rank10ModelBYSeed 2.0 ProByteDanceScore94.2%Percentile55.0%Participants21EvidenceCEvaluatedAug 17, 2026
Rank11ModelACQwen3.6-27BAlibaba Cloud / Qwen TeamScore94.1%Percentile50.0%Participants21EvidenceCEvaluatedAug 17, 2026
Rank12ModelACQwen3.6-35B-A3BAlibaba Cloud / Qwen TeamScore92.7%Percentile45.0%Participants21EvidenceCEvaluatedAug 17, 2026
Rank13ModelMIMAI-Code-1-FlashMicrosoftScore92.5%Percentile40.0%Participants21EvidenceCEvaluatedAug 17, 2026
Rank14ModelACQwen3.5-397B-A17BAlibaba Cloud / Qwen TeamScore91.3%Percentile35.0%Participants21EvidenceCEvaluatedAug 17, 2026
Rank15ModelGOGemma 4 31BGoogleScore89.2%Percentile30.0%Participants21EvidenceCEvaluatedAug 17, 2026
Rank16ModelGOGemma 4 26B-A4BGoogleScore88.3%Percentile25.0%Participants21EvidenceCEvaluatedAug 17, 2026
Rank17ModelBYSeed 2.0 LiteByteDanceScore88.3%Percentile20.0%Participants21EvidenceCEvaluatedAug 17, 2026
Rank18ModelGOGemma 4 12BGoogleScore77.5%Percentile15.0%Participants21EvidenceCEvaluatedAug 17, 2026
Rank19ModelGODiffusionGemma 26B-A4BGoogleScore69.1%Percentile10.0%Participants21EvidenceCEvaluatedAug 17, 2026
Rank20ModelGOGemma 4 E4BGoogleScore42.5%Percentile5.0%Participants21EvidenceCEvaluatedAug 17, 2026
Rank21ModelGOGemma 4 E2BGoogleScore37.5%Percentile0.0%Participants21EvidenceCEvaluatedAug 17, 2026

AIME 2026 Highlights

The leading models and scores on this benchmark.

Rank #1GLM-5.299.2%Rank #2Sakana Namazu96.7%Rank #3Kimi K2.696.4%Rank #4Inkling-Small95.5%

AIME 2026 Score Distribution

A closer view of the leading scores on this benchmark.

AIME 2026

The Top AI Models for AIME 2026

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

Ranking basisThis aime 2026 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
    ZA
    GLM-5.2Zhipu AI
    Score
    99.2%
    Price
    $1.4 input / $4.4 output per 1M tokens

    Strengths

    • Ranks #1 of 21 compared models
    • 100th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures AIME 2026, not total model capability
  2. 02
    SA
    Sakana NamazuSakana AI
    Score
    96.7%

    Strengths

    • Ranks #2 of 21 compared models
    • 95th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures AIME 2026, not total model capability
  3. 03
    MA
    Kimi K2.6Moonshot AI
    Score
    96.4%
    Price
    $0.95 input / $4.0 output per 1M tokens
    Speed
    Up to 285 tok/s via Fireworks

    Strengths

    • Ranks #3 of 21 compared models
    • 90th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures AIME 2026, not total model capability
  4. 04
    TM
    Inkling-SmallThinking Machines Lab
    Score
    95.5%

    Strengths

    • Ranks #4 of 21 compared models
    • 85th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures AIME 2026, not total model capability
  5. 05
    ZA
    GLM-5.1Zhipu AI
    Score
    95.3%
    Price
    $1.4 input / $4.4 output per 1M tokens

    Strengths

    • Ranks #5 of 21 compared models
    • 80th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures AIME 2026, not total model capability

Selection summary

Best AI Models for AIME 2026

GLM-5.2 currently leads AIME 2026 with 99.2%. 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 #1GLM-5.299.2% · $1.4 input / $4.4 output per 1M tokensBenchmark rank #2Sakana Namazu96.7%Benchmark rank #3Kimi K2.696.4% · $0.95 input / $4.0 output per 1M tokens

What is AIME 2026?

What AIME 2026 measures and how its scores work.

All 30 problems from the 2026 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.

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

Family
AIME 2026
Modality
text
Primary category
math
Score direction
higher
LLMBoard eligible
Yes
Evaluation key
aime-2026|llm-stats-current

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

FAQ

Common questions about AIME 2026.

Which model scores highest on AIME 2026?

GLM-5.2 is currently ranked first with 99.2%.

What does AIME 2026 measure?

All 30 problems from the 2026 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

21 model results are currently shown.

Does this benchmark affect the overall score?

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