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

multimodal benchmark

MMT-Bench Leaderboard

MMT-Bench is a comprehensive multimodal benchmark for evaluating Large Vision-Language Models towards multitask AGI. It comprises 31,325 meticulously curated multi-choice visual questions from various multimodal scenarios such as vehicle driving and embodied navigation, covering 32 core meta-tasks and 162 subtasks in multimodal understanding.

Updated Aug 17, 2026

Models4
Model coverage4
MetricScore
EvidenceB

On this page

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

MMT-Bench Ranking

Higher score ranks better on this benchmark.

4 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelDEDeepSeek VL2DeepSeekScore63.6%Percentile100.0%Participants4EvidenceCEvaluatedAug 17, 2026
Rank02ModelACQwen2.5 VL 7B InstructAlibaba Cloud / Qwen TeamScore63.6%Percentile66.7%Participants4EvidenceCEvaluatedAug 17, 2026
Rank03ModelDEDeepSeek VL2 SmallDeepSeekScore62.9%Percentile33.3%Participants4EvidenceCEvaluatedAug 17, 2026
Rank04ModelDEDeepSeek VL2 TinyDeepSeekScore53.2%Percentile0.0%Participants4EvidenceCEvaluatedAug 17, 2026

MMT-Bench Highlights

The leading models and scores on this benchmark.

Rank #1DeepSeek VL263.6%Rank #2Qwen2.5 VL 7B Instruct63.6%Rank #3DeepSeek VL2 Small62.9%Rank #4DeepSeek VL2 Tiny53.2%

MMT-Bench Score Distribution

A closer view of the leading scores on this benchmark.

MMT-Bench

The Top AI Models for MMT-Bench

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

Ranking basisThis mmt-bench 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
    DE
    DeepSeek VL2DeepSeek
    Score
    63.6%
    Speed
    Up to 22 tok/s via Replicate

    Strengths

    • Ranks #1 of 4 compared models
    • 100th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures MMT-Bench, not total model capability
  2. 02
    AC
    Qwen2.5 VL 7B InstructAlibaba Cloud / Qwen Team
    Score
    63.6%
    Price
    $0.35 input / $1.1 output per 1M tokens

    Strengths

    • Ranks #2 of 4 compared models
    • 67th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures MMT-Bench, not total model capability
  3. 03
    DE
    DeepSeek VL2 SmallDeepSeek
    Score
    62.9%
    Speed
    Up to 22 tok/s via Replicate

    Strengths

    • Ranks #3 of 4 compared models
    • 33th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures MMT-Bench, not total model capability
  4. 04
    DE
    DeepSeek VL2 TinyDeepSeek
    Score
    53.2%
    Speed
    Up to 22 tok/s via Replicate

    Strengths

    • Ranks #4 of 4 compared models
    • 0th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures MMT-Bench, not total model capability

Selection summary

Best AI Models for MMT-Bench

DeepSeek VL2 currently leads MMT-Bench with 63.6%. 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 #1DeepSeek VL263.6% · Up to 22 tok/s via ReplicateBenchmark rank #2Qwen2.5 VL 7B Instruct63.6% · $0.35 input / $1.1 output per 1M tokensBenchmark rank #3DeepSeek VL2 Small62.9% · Up to 22 tok/s via Replicate

What is MMT-Bench?

What MMT-Bench measures and how its scores work.

MMT-Bench is a comprehensive multimodal benchmark for evaluating Large Vision-Language Models towards multitask AGI. It comprises 31,325 meticulously curated multi-choice visual questions from various multimodal scenarios such as vehicle driving and embodied navigation, covering 32 core meta-tasks and 162 subtasks in multimodal understanding.

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

Family
MMT-Bench
Modality
multimodal
Primary category
multimodal
Score direction
higher
LLMBoard eligible
Yes
Evaluation key
mmt-bench|llm-stats-current

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

FAQ

Common questions about MMT-Bench.

Which model scores highest on MMT-Bench?

DeepSeek VL2 is currently ranked first with 63.6%.

What does MMT-Bench measure?

MMT-Bench is a comprehensive multimodal benchmark for evaluating Large Vision-Language Models towards multitask AGI. It comprises 31,325 meticulously curated multi-choice visual questions from various multimodal scenarios such as vehicle driving and embodied navigation, covering 32 core meta-tasks and 162 subtasks in multimodal understanding.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

4 model results are currently shown.

Does this benchmark affect the overall score?

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