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

TextVQA Leaderboard

TextVQA contains 45,336 questions on 28,408 images that require reasoning about text to answer. Introduced to benchmark VQA models' ability to read and reason about text within images, particularly for assistive technologies for visually impaired users. The dataset addresses the gap where existing VQA datasets had few text-based questions or were too small.

Updated Aug 17, 2026

Models16
Model coverage16
MetricScore
EvidenceB

On this page

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

TextVQA Ranking

Higher score ranks better on this benchmark.

16 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelACQwen2-VL-72B-InstructAlibaba Cloud / Qwen TeamScore85.5%Percentile100.0%Participants16EvidenceCEvaluatedAug 17, 2026
Rank02ModelACQwen2.5 VL 7B InstructAlibaba Cloud / Qwen TeamScore84.9%Percentile93.3%Participants16EvidenceCEvaluatedAug 17, 2026
Rank03ModelACQwen2.5-Omni-7BAlibaba Cloud / Qwen TeamScore84.4%Percentile86.7%Participants16EvidenceCEvaluatedAug 17, 2026
Rank04ModelLALFM2.5-VL-3BLiquid AIScore84.3%Percentile80.0%Participants16EvidenceCEvaluatedAug 17, 2026
Rank05ModelDEDeepSeek VL2DeepSeekScore84.2%Percentile73.3%Participants16EvidenceCEvaluatedAug 17, 2026
Rank06ModelDEDeepSeek VL2 SmallDeepSeekScore83.4%Percentile66.7%Participants16EvidenceCEvaluatedAug 17, 2026
Rank07ModelAMNova ProAmazonScore81.5%Percentile60.0%Participants16EvidenceCEvaluatedAug 17, 2026
Rank08ModelDEDeepSeek VL2 TinyDeepSeekScore80.7%Percentile53.3%Participants16EvidenceCEvaluatedAug 17, 2026
Rank09ModelAMNova LiteAmazonScore80.2%Percentile46.7%Participants16EvidenceCEvaluatedAug 17, 2026
Rank10ModelXAGrok-1.5VxAIScore78.1%Percentile40.0%Participants16EvidenceCEvaluatedAug 17, 2026
Rank11ModelMIPhi-4-multimodal-instructMicrosoftScore75.6%Percentile33.3%Participants16EvidenceCEvaluatedAug 17, 2026
Rank12ModelMELlama 3.2 90B InstructMetaScore73.5%Percentile26.7%Participants16EvidenceCEvaluatedAug 17, 2026
Rank13ModelMIPhi-3.5-vision-instructMicrosoftScore72.0%Percentile20.0%Participants16EvidenceCEvaluatedAug 17, 2026
Rank14ModelGOGemma 3 12BGoogleScore67.7%Percentile13.3%Participants16EvidenceCEvaluatedAug 17, 2026
Rank15ModelGOGemma 3 27BGoogleScore65.1%Percentile6.7%Participants16EvidenceCEvaluatedAug 17, 2026
Rank16ModelGOGemma 3 4BGoogleScore57.8%Percentile0.0%Participants16EvidenceCEvaluatedAug 17, 2026

TextVQA Highlights

The leading models and scores on this benchmark.

Rank #1Qwen2-VL-72B-Instruct85.5%Rank #2Qwen2.5 VL 7B Instruct84.9%Rank #3Qwen2.5-Omni-7B84.4%Rank #4LFM2.5-VL-3B84.3%

TextVQA Score Distribution

A closer view of the leading scores on this benchmark.

TextVQA

The Top AI Models for TextVQA

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

Ranking basisThis textvqa 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-VL-72B-InstructAlibaba Cloud / Qwen Team
    Score
    85.5%

    Strengths

    • Ranks #1 of 16 compared models
    • 100th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures TextVQA, not total model capability
  2. 02
    AC
    Qwen2.5 VL 7B InstructAlibaba Cloud / Qwen Team
    Score
    84.9%
    Price
    $0.35 input / $1.1 output per 1M tokens

    Strengths

    • Ranks #2 of 16 compared models
    • 93th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures TextVQA, not total model capability
  3. 03
    AC
    Qwen2.5-Omni-7BAlibaba Cloud / Qwen Team
    Score
    84.4%
    Price
    $0.10 input / $0.40 output per 1M tokens

    Strengths

    • Ranks #3 of 16 compared models
    • 87th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures TextVQA, not total model capability
  4. 04
    LA
    LFM2.5-VL-3BLiquid AI
    Score
    84.3%

    Strengths

    • Ranks #4 of 16 compared models
    • 80th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures TextVQA, not total model capability
  5. 05
    DE
    DeepSeek VL2DeepSeek
    Score
    84.2%
    Speed
    Up to 22 tok/s via Replicate

    Strengths

    • Ranks #5 of 16 compared models
    • 73th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures TextVQA, not total model capability

Selection summary

Best AI Models for TextVQA

Qwen2-VL-72B-Instruct currently leads TextVQA with 85.5%. 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-VL-72B-Instruct85.5%Benchmark rank #2Qwen2.5 VL 7B Instruct84.9% · $0.35 input / $1.1 output per 1M tokensBenchmark rank #3Qwen2.5-Omni-7B84.4% · $0.10 input / $0.40 output per 1M tokens

What is TextVQA?

What TextVQA measures and how its scores work.

TextVQA contains 45,336 questions on 28,408 images that require reasoning about text to answer. Introduced to benchmark VQA models' ability to read and reason about text within images, particularly for assistive technologies for visually impaired users. The dataset addresses the gap where existing VQA datasets had few text-based questions or were too small.

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

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

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

FAQ

Common questions about TextVQA.

Which model scores highest on TextVQA?

Qwen2-VL-72B-Instruct is currently ranked first with 85.5%.

What does TextVQA measure?

TextVQA contains 45,336 questions on 28,408 images that require reasoning about text to answer. Introduced to benchmark VQA models' ability to read and reason about text within images, particularly for assistive technologies for visually impaired users. The dataset addresses the gap where existing VQA datasets had few text-based questions or were too small.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

16 model results are currently shown.

Does this benchmark affect the overall score?

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