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

InfoVQA Leaderboard

InfoVQA dataset with 30,000 questions and 5,000 infographic images requiring joint reasoning over document layout, textual content, graphical elements, and data visualizations with elementary reasoning and arithmetic skills

Updated Aug 17, 2026

Models10
Model coverage10
MetricScore
EvidenceB

On this page

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

InfoVQA Ranking

Higher score ranks better on this benchmark.

10 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelACQwen2.5 VL 32B InstructAlibaba Cloud / Qwen TeamScore83.4%Percentile100.0%Participants10EvidenceCEvaluatedAug 17, 2026
Rank02ModelACQwen2.5 VL 7B InstructAlibaba Cloud / Qwen TeamScore82.6%Percentile88.9%Participants10EvidenceCEvaluatedAug 17, 2026
Rank03ModelDEDeepSeek VL2DeepSeekScore78.1%Percentile77.8%Participants10EvidenceCEvaluatedAug 17, 2026
Rank04ModelDEDeepSeek VL2 SmallDeepSeekScore75.8%Percentile66.7%Participants10EvidenceCEvaluatedAug 17, 2026
Rank05ModelMIPhi-4-multimodal-instructMicrosoftScore72.7%Percentile55.6%Participants10EvidenceCEvaluatedAug 17, 2026
Rank06ModelGOGemma 3 27BGoogleScore70.6%Percentile44.4%Participants10EvidenceCEvaluatedAug 17, 2026
Rank07ModelDEDeepSeek VL2 TinyDeepSeekScore66.1%Percentile33.3%Participants10EvidenceCEvaluatedAug 17, 2026
Rank08ModelCONorth Micro Vision InstructCohereScore65.2%Percentile22.2%Participants10EvidenceCEvaluatedAug 17, 2026
Rank09ModelGOGemma 3 12BGoogleScore64.9%Percentile11.1%Participants10EvidenceCEvaluatedAug 17, 2026
Rank10ModelGOGemma 3 4BGoogleScore50.0%Percentile0.0%Participants10EvidenceCEvaluatedAug 17, 2026

InfoVQA Highlights

The leading models and scores on this benchmark.

Rank #1Qwen2.5 VL 32B Instruct83.4%Rank #2Qwen2.5 VL 7B Instruct82.6%Rank #3DeepSeek VL278.1%Rank #4DeepSeek VL2 Small75.8%

InfoVQA Score Distribution

A closer view of the leading scores on this benchmark.

InfoVQA

The Top AI Models for InfoVQA

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

Ranking basisThis infovqa 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
    AC
    Qwen2.5 VL 32B InstructAlibaba Cloud / Qwen Team
    Score
    83.4%

    Strengths

    • Ranks #1 of 10 compared models
    • 100th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures InfoVQA, not total model capability
  2. 02
    AC
    Qwen2.5 VL 7B InstructAlibaba Cloud / Qwen Team
    Score
    82.6%
    Price
    $0.35 input / $1.1 output per 1M tokens

    Strengths

    • Ranks #2 of 10 compared models
    • 89th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures InfoVQA, not total model capability
  3. 03
    DE
    DeepSeek VL2DeepSeek
    Score
    78.1%
    Speed
    Up to 22 tok/s via Replicate

    Strengths

    • Ranks #3 of 10 compared models
    • 78th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures InfoVQA, not total model capability
  4. 04
    DE
    DeepSeek VL2 SmallDeepSeek
    Score
    75.8%
    Speed
    Up to 22 tok/s via Replicate

    Strengths

    • Ranks #4 of 10 compared models
    • 67th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures InfoVQA, not total model capability
  5. 05
    MI
    Phi-4-multimodal-instructMicrosoft
    Score
    72.7%
    Speed
    Up to 25 tok/s via DeepInfra

    Strengths

    • Ranks #5 of 10 compared models
    • 56th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures InfoVQA, not total model capability

Selection summary

Best AI Models for InfoVQA

Qwen2.5 VL 32B Instruct currently leads InfoVQA with 83.4%. 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 #1Qwen2.5 VL 32B Instruct83.4%Benchmark rank #2Qwen2.5 VL 7B Instruct82.6% · $0.35 input / $1.1 output per 1M tokensBenchmark rank #3DeepSeek VL278.1% · Up to 22 tok/s via Replicate

What is InfoVQA?

What InfoVQA measures and how its scores work.

InfoVQA dataset with 30,000 questions and 5,000 infographic images requiring joint reasoning over document layout, textual content, graphical elements, and data visualizations with elementary reasoning and arithmetic skills

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

Family
InfoVQA
Modality
multimodal
Primary category
multimodal
Score direction
higher
LLMBoard eligible
Yes
Evaluation key
infovqa|llm-stats-current

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

FAQ

Common questions about InfoVQA.

Which model scores highest on InfoVQA?

Qwen2.5 VL 32B Instruct is currently ranked first with 83.4%.

What does InfoVQA measure?

InfoVQA dataset with 30,000 questions and 5,000 infographic images requiring joint reasoning over document layout, textual content, graphical elements, and data visualizations with elementary reasoning and arithmetic skills

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

10 model results are currently shown.

Does this benchmark affect the overall score?

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