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

multimodal benchmark

VideoMMMU Leaderboard

VideoMMMU evaluates Large Multimodal Models' ability to acquire knowledge from expert-level professional videos across six disciplines through perception, comprehension, and adaptation.

Updated Sep 5, 2026

Models26
Model coverage26
MetricScore
EvidenceB

On this page

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

VideoMMMU Ranking

Higher score ranks better on this benchmark.

26 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelGOGemini 3 ProGoogleScore87.60%Percentile100.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank02ModelGOGemini 3 FlashGoogleScore86.90%Percentile96.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank03ModelMAKimi K2.5Moonshot AIScore86.60%Percentile92.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank04ModelOPGPT-5.2OpenAIScore85.90%Percentile88.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank05ModelACQwen3.7-PlusAlibaba Cloud / Qwen TeamScore85.40%Percentile84.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank06ModelGOGemini 3.1 Flash-LiteGoogleScore84.80%Percentile80.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank07ModelOPGPT-5OpenAIScore84.60%Percentile76.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank08ModelMIMiniMax M3MiniMaxScore84.60%Percentile72.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank09ModelACQwen3.6-27BAlibaba Cloud / Qwen TeamScore84.40%Percentile68.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank10ModelACQwen3.6 PlusAlibaba Cloud / Qwen TeamScore84.00%Percentile64.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank11ModelACQwen3.6-35B-A3BAlibaba Cloud / Qwen TeamScore83.70%Percentile60.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank12ModelGOGemini 2.5 Pro Preview 06-05GoogleScore83.60%Percentile56.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank13ModelOPo3OpenAIScore83.30%Percentile52.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank14ModelACQwen3.5-27BAlibaba Cloud / Qwen TeamScore82.30%Percentile48.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank15ModelACQwen3.5-122B-A10BAlibaba Cloud / Qwen TeamScore82.00%Percentile44.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank16ModelACQwen3.5-35B-A3BAlibaba Cloud / Qwen TeamScore80.40%Percentile40.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank17ModelACQwen3 VL 235B A22B ThinkingAlibaba Cloud / Qwen TeamScore80.00%Percentile36.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank18ModelACQwen3 VL 32B ThinkingAlibaba Cloud / Qwen TeamScore79.00%Percentile32.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank19ModelACQwen3 VL 30B A3B ThinkingAlibaba Cloud / Qwen TeamScore75.00%Percentile28.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank20ModelACQwen3 VL 235B A22B InstructAlibaba Cloud / Qwen TeamScore74.70%Percentile24.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank21ModelACQwen3 VL 8B ThinkingAlibaba Cloud / Qwen TeamScore72.80%Percentile20.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank22ModelACQwen3 VL 4B ThinkingAlibaba Cloud / Qwen TeamScore69.40%Percentile16.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank23ModelACQwen3 VL 30B A3B InstructAlibaba Cloud / Qwen TeamScore68.70%Percentile12.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank24ModelACQwen3 VL 8B InstructAlibaba Cloud / Qwen TeamScore65.30%Percentile8.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank25ModelOPGPT-4oOpenAIScore61.20%Percentile4.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank26ModelACQwen3 VL 4B InstructAlibaba Cloud / Qwen TeamScore56.20%Percentile0.00%Participants26EvidenceCEvaluatedSep 8, 2026

VideoMMMU Highlights

The leading models and scores on this benchmark.

VideoMMMU Score Distribution

A closer view of the leading scores on this benchmark.

VideoMMMU

The Top AI Models for VideoMMMU

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

What is VideoMMMU?

What VideoMMMU measures and how its scores work.

VideoMMMU is a multimodal benchmark containing 300 videos and 900 human-annotated questions spanning Art, Business, Science, Medicine, Humanities, and Engineering.

It measures Large Multimodal Models' ability to acquire knowledge from expert-level professional videos across the cognitive stages of perception, comprehension, and adaptation, reported as a Score in ratio units.

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

Family
VideoMMMU
Modality
multimodal
Primary category
multimodal
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 VideoMMMU.

Which model scores highest on VideoMMMU?

Gemini 3 Pro is currently ranked first with 87.60%.

What are the top three models on VideoMMMU?

The current leaders are Gemini 3 Pro (87.60%), Gemini 3 Flash (86.90%), and Kimi K2.5 (86.60%).

Which VideoMMMU model has the lowest official input price?

Qwen3.6-35B-A3B has the lowest matched official input price at $0.25 input / $1.5 output per 1M tokens.

Which models are fastest among VideoMMMU results?

The fastest matched records are GPT-4o (132.00 tok/s via OpenAI), Gemini 3 Flash (124.32 tok/s via Google), and GPT-5.2 (100.00 tok/s via OpenAI).

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 VideoMMMU measure?

It measures Large Multimodal Models' ability to acquire knowledge from expert-level professional videos across the cognitive stages of perception, comprehension, and adaptation, reported as a Score in ratio units.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

26 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 #1Gemini 3 Pro87.60%
Rank #2Gemini 3 Flash86.90%
Rank #3Kimi K2.586.60%
Rank #4GPT-5.285.90%

Ranking basisThis videommmu 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
    GO
    Gemini 3 ProGoogle
    Score
    87.60%
    Speed
    Up to 90.00 tok/s via Google

    Strengths

    • Ranks #1 of 26 compared models
    • 100th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures VideoMMMU, not total model capability
  2. 02
    GO
    Gemini 3 FlashGoogle
    Score
    86.90%
    Price
    $0.50 input / $3.0 output per 1M tokens
    Speed
    Up to 124.32 tok/s via Google

    Strengths

    • Ranks #2 of 26 compared models
    • 96th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures VideoMMMU, not total model capability
  3. 03
    MA
    Moonshot AI
    Score
    86.60%

    Strengths

    • Ranks #3 of 26 compared models
    • 92th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures VideoMMMU, not total model capability
  4. 04
    OP
    OpenAI
    Score
    85.90%
    Price
    $1.8 input / $14 output per 1M tokens
    Speed
    Up to 100.00 tok/s via OpenAI

    Strengths

    • Ranks #4 of 26 compared models
    • 88th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures VideoMMMU, not total model capability
  5. 05
    AC
    Alibaba Cloud / Qwen Team
    Score
    85.40%
    Price
    $0.50 input / $3.0 output per 1M tokens

    Strengths

    • Ranks #5 of 26 compared models
    • 84th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures VideoMMMU, not total model capability

Selection summary

Best AI Models for VideoMMMU

Gemini 3 Pro currently leads VideoMMMU with 87.60%. 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.

Kimi K2.5
GPT-5.2
Qwen3.7-Plus
Benchmark rank #1Gemini 3 Pro87.60% · Up to 90.00 tok/s via Google
Benchmark rank #2Gemini 3 Flash86.90% · $0.50 input / $3.0 output per 1M tokens
Benchmark rank #3Kimi K2.586.60%