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
1438 models809 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

math benchmark

MathVision Leaderboard

MathVision is a math benchmark for multimodal mathematical reasoning.

Updated Nov 13, 2026

Models40
Model coverage40
MetricScore
EvidenceB

On this page

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

MathVision Ranking

Higher score ranks better on this benchmark.

30 of 40 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelMAKimi K3Moonshot AIScore97.80%Percentile100.00%Participants40EvidenceCEvaluatedNov 12, 2026
Rank02ModelMELongCat-2.5MeituanScore96.50%Percentile97.44%Participants40EvidenceCEvaluatedNov 12, 2026
Rank03ModelACQwen3.8-Flash-NextAlibaba Cloud / Qwen TeamScore95.70%Percentile94.87%Participants40EvidenceCEvaluatedNov 12, 2026
Rank04ModelACQwen3.8 FlashAlibaba Cloud / Qwen TeamScore95.70%Percentile92.31%Participants40EvidenceCEvaluatedNov 12, 2026
Rank05ModelACQwen3.8-27BAlibaba Cloud / Qwen TeamScore94.60%Percentile89.74%Participants40EvidenceCEvaluatedNov 12, 2026
Rank06ModelBYSeed 2.1 ProByteDanceScore94.50%Percentile87.18%Participants40EvidenceCEvaluatedNov 12, 2026
Rank07ModelMAKimi K2.6Moonshot AIScore93.20%Percentile84.62%Participants40EvidenceCEvaluatedNov 12, 2026
Rank08ModelBYSeed 2.1 TurboByteDanceScore92.70%Percentile82.05%Participants40EvidenceCEvaluatedNov 12, 2026
Rank09ModelACQwen3.7-PlusAlibaba Cloud / Qwen TeamScore90.30%Percentile79.49%Participants40EvidenceCEvaluatedNov 12, 2026
Rank10ModelACQwen3.6 PlusAlibaba Cloud / Qwen TeamScore88.00%Percentile76.92%Participants40EvidenceCEvaluatedNov 12, 2026
Rank11ModelACQwen3.5-122B-A10BAlibaba Cloud / Qwen TeamScore86.20%Percentile74.36%Participants40EvidenceCEvaluatedNov 12, 2026
Rank12ModelACQwen3.5-27BAlibaba Cloud / Qwen TeamScore86.00%Percentile71.79%Participants40EvidenceCEvaluatedNov 12, 2026
Rank13ModelGOGemma 4 31BGoogleScore85.60%Percentile69.23%Participants40EvidenceCEvaluatedNov 12, 2026
Rank14ModelMAKimi K2.5Moonshot AIScore84.20%Percentile66.67%Participants40EvidenceCEvaluatedNov 12, 2026
Rank15ModelACQwen3.5-35B-A3BAlibaba Cloud / Qwen TeamScore83.90%Percentile64.10%Participants40EvidenceCEvaluatedNov 12, 2026
Rank16ModelGOGemma 4 26B-A4BGoogleScore82.40%Percentile61.54%Participants40EvidenceCEvaluatedNov 12, 2026
Rank17ModelBYSeed 1.8ByteDanceScore81.30%Percentile58.97%Participants40EvidenceCEvaluatedNov 12, 2026
Rank18ModelGOGemma 4 12BGoogleScore79.70%Percentile56.41%Participants40EvidenceCEvaluatedNov 12, 2026
Rank19ModelNVNemotron 3.5 Super VL (120B A12B)NVIDIAScore78.16%Percentile53.85%Participants40EvidenceCEvaluatedNov 12, 2026
Rank20ModelBYSeed 2.0 MiniByteDanceScore78.10%Percentile51.28%Participants40EvidenceCEvaluatedNov 12, 2026
Rank21ModelACQwen3 VL 235B A22B ThinkingAlibaba Cloud / Qwen TeamScore74.60%Percentile48.72%Participants40EvidenceCEvaluatedNov 12, 2026
Rank22ModelSTStep3-VL-10BStepFunScore70.80%Percentile46.15%Participants40EvidenceCEvaluatedNov 12, 2026
Rank23ModelGODiffusionGemma 26B-A4BGoogleScore70.50%Percentile43.59%Participants40EvidenceCEvaluatedNov 12, 2026
Rank24ModelACQwen3 VL 32B ThinkingAlibaba Cloud / Qwen TeamScore70.20%Percentile41.03%Participants40EvidenceCEvaluatedNov 12, 2026
Rank25ModelACQwen3 VL 235B A22B InstructAlibaba Cloud / Qwen TeamScore66.50%Percentile38.46%Participants40EvidenceCEvaluatedNov 12, 2026
Rank26ModelACQwen3 VL 30B A3B ThinkingAlibaba Cloud / Qwen TeamScore65.70%Percentile35.90%Participants40EvidenceCEvaluatedNov 12, 2026
Rank27ModelACQwen3 VL 32B InstructAlibaba Cloud / Qwen TeamScore63.40%Percentile33.33%Participants40EvidenceCEvaluatedNov 12, 2026
Rank28ModelACQwen3 VL 8B ThinkingAlibaba Cloud / Qwen TeamScore62.70%Percentile30.77%Participants40EvidenceCEvaluatedNov 12, 2026
Rank29ModelACQwen3 VL 30B A3B InstructAlibaba Cloud / Qwen TeamScore60.20%Percentile28.21%Participants40EvidenceCEvaluatedNov 12, 2026
Rank30ModelACQwen3 VL 4B ThinkingAlibaba Cloud / Qwen TeamScore60.00%Percentile25.64%Participants40EvidenceCEvaluatedNov 12, 2026

MathVision Highlights

The leading models and scores on this benchmark.

MathVision Score Distribution

A closer view of the leading scores on this benchmark.

MathVision

The Top AI Models for MathVision

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

What is MathVision?

What MathVision measures and how its scores work.

MathVision is a dataset designed to measure multimodal mathematical reasoning capabilities.

It measures how well models solve mathematical problems requiring both visual understanding and mathematical reasoning, 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
MathVision
Modality
multimodal
Primary category
math
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 MathVision.

Which model scores highest on MathVision?

Kimi K3 is currently ranked first with 97.80%.

What are the top three models on MathVision?

The current leaders are Kimi K3 (97.80%), LongCat-2.5 (96.50%), and Qwen3.8-Flash-Next (95.70%).

Which MathVision model has the lowest official input price?

Qwen2.5-Omni-7B has the lowest matched official input price at $0.10 input / $0.40 output per 1M tokens.

Which models are fastest among MathVision results?

No matched runtime record is currently available.

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 MathVision measure?

It measures how well models solve mathematical problems requiring both visual understanding and mathematical reasoning, 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?

40 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 #1Kimi K397.80%
Rank #2LongCat-2.596.50%
Rank #3Qwen3.8-Flash-Next95.70%
Rank #4Qwen3.8 Flash95.70%

Ranking basisThis mathvision 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
    MA
    Kimi K3Moonshot AI
    Score
    97.80%
    Price
    $3.0 input / $15 output per 1M tokens

    Strengths

    • Ranks #1 of 40 compared models
    • 100th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures MathVision, not total model capability
  2. 02
    ME
    LongCat-2.5Meituan
    Score
    96.50%

    Strengths

    • Ranks #2 of 40 compared models
    • 97th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures MathVision, not total model capability
  3. 03
    AC
    Alibaba Cloud / Qwen Team
    Score
    95.70%

    Strengths

    • Ranks #3 of 40 compared models
    • 95th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures MathVision, not total model capability
  4. 04
    AC
    Alibaba Cloud / Qwen Team
    Score
    95.70%
    Price
    $0.15 input / $0.47 output per 1M tokens

    Strengths

    • Ranks #4 of 40 compared models
    • 92th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures MathVision, not total model capability
  5. 05
    AC
    Alibaba Cloud / Qwen Team
    Score
    94.60%

    Strengths

    • Ranks #5 of 40 compared models
    • 90th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures MathVision, not total model capability

Selection summary

Best AI Models for MathVision

Kimi K3 currently leads MathVision with 97.80%. 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.

Qwen3.8-Flash-Next
Qwen3.8 Flash
Qwen3.8-27B
Benchmark rank #1Kimi K397.80% · $3.0 input / $15 output per 1M tokens
Benchmark rank #2LongCat-2.596.50%
Benchmark rank #3Qwen3.8-Flash-Next95.70%