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
1224 models729 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

language benchmark

MMLU Leaderboard

MMLU is a language benchmark testing knowledge across 57 diverse subjects, including STEM, humanities, social sciences, and professional domains.

Updated Sep 5, 2026

Models100
Model coverage101
MetricScore
EvidenceB

On this page

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

MMLU Ranking

Higher score ranks better on this benchmark.

30 of 100 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelOPGPT-5OpenAIScore92.50%Percentile100.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank02ModelOPo1OpenAIScore91.80%Percentile99.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank03ModelOPGPT-4.5OpenAIScore90.80%Percentile98.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank04ModelOPo1-previewOpenAIScore90.80%Percentile97.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank05ModelACQwen3 VL 235B A22B ThinkingAlibaba Cloud / Qwen TeamScore90.60%Percentile96.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank06ModelSASarvam-105BSarvam AIScore90.60%Percentile95.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank07ModelANClaude 3.5 SonnetAnthropicScore90.40%Percentile94.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank08ModelANClaude 3.5 SonnetAnthropicScore90.40%Percentile93.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank09ModelOPGPT-4.1OpenAIScore90.20%Percentile92.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank10ModelMAKimi K2 0905Moonshot AIScore90.20%Percentile91.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank11ModelOPGPT OSS 120BOpenAIScore90.00%Percentile90.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank12ModelMELongCat-Flash-ChatMeituanScore89.71%Percentile89.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank13ModelMAKimi K2 InstructMoonshot AIScore89.50%Percentile88.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank14ModelMAKimi K2-Instruct-0905Moonshot AIScore89.50%Percentile87.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank15ModelXIMiMo-V2.5-ProXiaomiScore89.40%Percentile86.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank16ModelACQwen3 VL 235B A22B InstructAlibaba Cloud / Qwen TeamScore88.80%Percentile85.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank17ModelOPGPT-4oOpenAIScore88.70%Percentile84.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank18ModelACQwen3 VL 32B ThinkingAlibaba Cloud / Qwen TeamScore88.70%Percentile83.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank19ModelDEDeepSeek-V3DeepSeekScore88.50%Percentile82.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank20ModelACQwen3 235B A22BAlibaba Cloud / Qwen TeamScore87.81%Percentile81.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank21ModelMAKimi K2 BaseMoonshot AIScore87.80%Percentile80.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank22ModelACQwen3 VL 30B A3B ThinkingAlibaba Cloud / Qwen TeamScore87.60%Percentile79.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank23ModelOPGPT-4.1 miniOpenAIScore87.50%Percentile78.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank24ModelXAGrok-2xAIScore87.50%Percentile77.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank25ModelMAKimi-k1.5Moonshot AIScore87.40%Percentile76.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank26ModelMELlama 3.1 405B InstructMetaScore87.30%Percentile75.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank27ModelOPo3-miniOpenAIScore86.90%Percentile74.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank28ModelANClaude 3 OpusAnthropicScore86.80%Percentile73.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank29ModelOPGPT-4 TurboOpenAIScore86.50%Percentile72.00%Participants101EvidenceCEvaluatedSep 8, 2026
Rank30ModelOPGPT-4OpenAIScore86.40%Percentile71.00%Participants101EvidenceCEvaluatedSep 8, 2026

MMLU Highlights

The leading models and scores on this benchmark.

MMLU Score Distribution

A closer view of the leading scores on this benchmark.

MMLU

The Top AI Models for MMLU

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

What is MMLU?

What MMLU measures and how its scores work.

MMLU is a benchmark for evaluating language model knowledge across 57 diverse subjects, including STEM, humanities, social sciences, and professional domains.

MMLU measures knowledge performance using the Score metric, reported as a ratio, across 57 diverse subjects.

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

Family
MMLU
Modality
text
Primary category
language
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 MMLU.

Which model scores highest on MMLU?

GPT-5 is currently ranked first with 92.50%.

What are the top three models on MMLU?

The current leaders are GPT-5 (92.50%), o1 (91.80%), and GPT-4.5 (90.80%).

Which MMLU model has the lowest official input price?

Nova Micro has the lowest matched official input price at $0.04 input / $0.14 output per 1M tokens.

Which models are fastest among MMLU results?

The fastest matched records are Llama 3.3 70B Instruct (2,220.00 tok/s via Cerebras), Llama 3.1 8B Instruct (2,047.00 tok/s via Cerebras), and Llama 3.1 70B Instruct (1,204.00 tok/s via Cerebras).

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 MMLU measure?

MMLU measures knowledge performance using the Score metric, reported as a ratio, across 57 diverse subjects.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

100 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 #1GPT-592.50%
Rank #2o191.80%
Rank #3GPT-4.590.80%
Rank #4o1-preview90.80%

Ranking basisThis mmlu 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
    OP
    GPT-5OpenAI
    Score
    92.50%
    Price
    $1.3 input / $10 output per 1M tokens
    Speed
    Up to 100.00 tok/s via OpenAI

    Strengths

    • Ranks #1 of 101 compared models
    • 100th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures MMLU, not total model capability
  2. 02
    OP
    o1OpenAI
    Score
    91.80%
    Price
    $15 input / $60 output per 1M tokens
    Speed
    Up to 66.00 tok/s via OpenAI

    Strengths

    • Ranks #2 of 101 compared models
    • 99th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures MMLU, not total model capability
  3. 03
    OP
    OpenAI
    Score
    90.80%
    Speed
    Up to 50.00 tok/s via OpenAI

    Strengths

    • Ranks #3 of 101 compared models
    • 98th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures MMLU, not total model capability
  4. 04
    OP
    OpenAI
    Score
    90.80%
    Price
    $15 input / $60 output per 1M tokens
    Speed
    Up to 66.00 tok/s via OpenAI

    Strengths

    • Ranks #4 of 101 compared models
    • 97th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures MMLU, not total model capability
  5. 05
    AC
    Alibaba Cloud / Qwen Team
    Score
    90.60%

    Strengths

    • Ranks #5 of 101 compared models
    • 96th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures MMLU, not total model capability

Selection summary

Best AI Models for MMLU

GPT-5 currently leads MMLU with 92.50%. 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.

GPT-4.5
o1-preview
Qwen3 VL 235B A22B Thinking
Benchmark rank #1GPT-592.50% · $1.3 input / $10 output per 1M tokens
Benchmark rank #2o191.80% · $15 input / $60 output per 1M tokens
Benchmark rank #3GPT-4.590.80% · Up to 50.00 tok/s via OpenAI