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

ChartQA Leaderboard

ChartQA is a large-scale multimodal benchmark with 9.6K human-written questions and 23.1K questions generated from human-written chart summaries.

Updated Sep 5, 2026

Models26
Model coverage26
MetricScore
EvidenceB

On this page

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

ChartQA Ranking

Higher score ranks better on this benchmark.

26 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelANClaude 3.5 SonnetAnthropicScore90.80%Percentile100.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank02ModelMELlama 4 MaverickMetaScore90.00%Percentile96.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank03ModelACQwen2.5 VL 72B InstructAlibaba Cloud / Qwen TeamScore89.50%Percentile92.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank04ModelAMNova ProAmazonScore89.20%Percentile88.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank05ModelMELlama 4 ScoutMetaScore88.80%Percentile84.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank06ModelACQwen2-VL-72B-InstructAlibaba Cloud / Qwen TeamScore88.30%Percentile80.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank07ModelMAPixtral LargeMistral AIScore88.10%Percentile76.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank08ModelMAMistral Small 3.2 24B InstructMistral AIScore87.40%Percentile72.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank09ModelACQwen2.5 VL 7B InstructAlibaba Cloud / Qwen TeamScore87.30%Percentile68.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank10ModelAMNova LiteAmazonScore86.80%Percentile64.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank11ModelDEDeepSeek VL2DeepSeekScore86.00%Percentile60.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank12ModelOPGPT-4oOpenAIScore85.70%Percentile56.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank13ModelMELlama 3.2 90B InstructMetaScore85.50%Percentile52.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank14ModelACQwen2.5-Omni-7BAlibaba Cloud / Qwen TeamScore85.30%Percentile48.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank15ModelDEDeepSeek VL2 SmallDeepSeekScore84.50%Percentile44.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank16ModelMELlama 3.2 11B InstructMetaScore83.40%Percentile40.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank17ModelMIPhi-3.5-vision-instructMicrosoftScore81.80%Percentile36.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank18ModelMAPixtral-12BMistral AIScore81.80%Percentile32.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank19ModelMIPhi-4-multimodal-instructMicrosoftScore81.40%Percentile28.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank20ModelLALFM2.5-VL-3BLiquid AIScore81.30%Percentile24.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank21ModelDEDeepSeek VL2 TinyDeepSeekScore81.00%Percentile20.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank22ModelCONorth Micro Vision InstructCohereScore80.80%Percentile16.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank23ModelGOGemma 3 27BGoogleScore78.00%Percentile12.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank24ModelXAGrok-1.5VxAIScore76.10%Percentile8.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank25ModelGOGemma 3 12BGoogleScore75.70%Percentile4.00%Participants26EvidenceCEvaluatedSep 8, 2026
Rank26ModelGOGemma 3 4BGoogleScore68.80%Percentile0.00%Participants26EvidenceCEvaluatedSep 8, 2026

ChartQA Highlights

The leading models and scores on this benchmark.

ChartQA Score Distribution

A closer view of the leading scores on this benchmark.

ChartQA

The Top AI Models for ChartQA

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

What is ChartQA?

What ChartQA measures and how its scores work.

ChartQA is a benchmark for evaluating models on questions about charts.

It measures models' abilities in visual and logical reasoning over charts using the Score metric, reported as a ratio.

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

Family
ChartQA
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 ChartQA.

Which model scores highest on ChartQA?

Claude 3.5 Sonnet is currently ranked first with 90.80%.

What are the top three models on ChartQA?

The current leaders are Claude 3.5 Sonnet (90.80%), Llama 4 Maverick (90.00%), and Qwen2.5 VL 72B Instruct (89.50%).

Which ChartQA model has the lowest official input price?

Nova Lite has the lowest matched official input price at $0.06 input / $0.24 output per 1M tokens.

Which models are fastest among ChartQA results?

The fastest matched records are Llama 4 Scout (776.10 tok/s via Groq), Llama 4 Maverick (307.30 tok/s via Groq), and GPT-4o (132.00 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 ChartQA measure?

It measures models' abilities in visual and logical reasoning over charts using the Score metric, reported as a ratio.

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 #1Claude 3.5 Sonnet90.80%
Rank #2Llama 4 Maverick90.00%
Rank #3Qwen2.5 VL 72B Instruct89.50%
Rank #4Nova Pro89.20%

Ranking basisThis chartqa 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
    AN
    Claude 3.5 SonnetAnthropic
    Score
    90.80%
    Speed
    Up to 100.00 tok/s via Anthropic

    Strengths

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

    Considerations

    • This result measures ChartQA, not total model capability
  2. 02
    ME
    Llama 4 MaverickMeta
    Score
    90.00%
    Speed
    Up to 307.30 tok/s via Groq

    Strengths

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

    Considerations

    • This result measures ChartQA, not total model capability
  3. 03
    AC
    Alibaba Cloud / Qwen Team
    Score
    89.50%

    Strengths

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

    Considerations

    • This result measures ChartQA, not total model capability
  4. 04
    AM
    Amazon
    Score
    89.20%
    Price
    $0.80 input / $3.2 output per 1M tokens

    Strengths

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

    Considerations

    • This result measures ChartQA, not total model capability
  5. 05
    ME
    Meta
    Score
    88.80%
    Speed
    Up to 776.10 tok/s via Groq

    Strengths

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

    Considerations

    • This result measures ChartQA, not total model capability

Selection summary

Best AI Models for ChartQA

Claude 3.5 Sonnet currently leads ChartQA with 90.80%. 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.

Qwen2.5 VL 72B Instruct
Nova Pro
Llama 4 Scout
Benchmark rank #1Claude 3.5 Sonnet90.80% · Up to 100.00 tok/s via Anthropic
Benchmark rank #2Llama 4 Maverick90.00% · Up to 307.30 tok/s via Groq
Benchmark rank #3Qwen2.5 VL 72B Instruct89.50%