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

ScreenSpot Leaderboard

ScreenSpot is the first realistic GUI grounding benchmark that encompasses mobile, desktop, and web environments. The dataset comprises over 1,200 instructions from iOS, Android, macOS, Windows and Web environments, along with annotated element types (text and icon/widget), designed to evaluate visual GUI agents' ability to accurately locate screen elements based on natural language instructions.

Updated Aug 17, 2026

Models16
Model coverage16
MetricScore
EvidenceB

On this page

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

ScreenSpot Ranking

Higher score ranks better on this benchmark.

16 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelACQwen3 VL 32B InstructAlibaba Cloud / Qwen TeamScore95.8%Percentile100.0%Participants16EvidenceCEvaluatedAug 17, 2026
Rank02ModelACQwen3 VL 32B ThinkingAlibaba Cloud / Qwen TeamScore95.7%Percentile93.3%Participants16EvidenceCEvaluatedAug 17, 2026
Rank03ModelACQwen3 VL 235B A22B InstructAlibaba Cloud / Qwen TeamScore95.4%Percentile86.7%Participants16EvidenceCEvaluatedAug 17, 2026
Rank04ModelACQwen3 VL 235B A22B ThinkingAlibaba Cloud / Qwen TeamScore95.4%Percentile80.0%Participants16EvidenceCEvaluatedAug 17, 2026
Rank05ModelACQwen3 VL 30B A3B InstructAlibaba Cloud / Qwen TeamScore94.7%Percentile73.3%Participants16EvidenceCEvaluatedAug 17, 2026
Rank06ModelACQwen3 VL 30B A3B ThinkingAlibaba Cloud / Qwen TeamScore94.7%Percentile66.7%Participants16EvidenceCEvaluatedAug 17, 2026
Rank07ModelACQwen3 VL 8B InstructAlibaba Cloud / Qwen TeamScore94.4%Percentile60.0%Participants16EvidenceCEvaluatedAug 17, 2026
Rank08ModelACQwen3 VL 4B InstructAlibaba Cloud / Qwen TeamScore94.0%Percentile53.3%Participants16EvidenceCEvaluatedAug 17, 2026
Rank09ModelACQwen3 VL 8B ThinkingAlibaba Cloud / Qwen TeamScore93.6%Percentile46.7%Participants16EvidenceCEvaluatedAug 17, 2026
Rank10ModelACQwen3 VL 4B ThinkingAlibaba Cloud / Qwen TeamScore92.9%Percentile40.0%Participants16EvidenceCEvaluatedAug 17, 2026
Rank11ModelACQwen2.5 VL 32B InstructAlibaba Cloud / Qwen TeamScore88.5%Percentile33.3%Participants16EvidenceCEvaluatedAug 17, 2026
Rank12ModelAMNova 2 ProAmazonScore88.1%Percentile26.7%Participants16EvidenceCEvaluatedAug 17, 2026
Rank13ModelACQwen2.5 VL 72B InstructAlibaba Cloud / Qwen TeamScore87.1%Percentile20.0%Participants16EvidenceCEvaluatedAug 17, 2026
Rank14ModelAMNova 2 OmniAmazonScore85.4%Percentile13.3%Participants16EvidenceCEvaluatedAug 17, 2026
Rank15ModelACQwen2.5 VL 7B InstructAlibaba Cloud / Qwen TeamScore84.7%Percentile6.7%Participants16EvidenceCEvaluatedAug 17, 2026
Rank16ModelAMNova 2 LiteAmazonScore83.3%Percentile0.0%Participants16EvidenceCEvaluatedAug 17, 2026

ScreenSpot Highlights

The leading models and scores on this benchmark.

Rank #1Qwen3 VL 32B Instruct95.8%Rank #2Qwen3 VL 32B Thinking95.7%Rank #3Qwen3 VL 235B A22B Instruct95.4%Rank #4Qwen3 VL 235B A22B Thinking95.4%

ScreenSpot Score Distribution

A closer view of the leading scores on this benchmark.

ScreenSpot

The Top AI Models for ScreenSpot

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

Ranking basisThis screenspot 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
    Qwen3 VL 32B InstructAlibaba Cloud / Qwen Team
    Score
    95.8%

    Strengths

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

    Considerations

    • This result measures ScreenSpot, not total model capability
  2. 02
    AC
    Qwen3 VL 32B ThinkingAlibaba Cloud / Qwen Team
    Score
    95.7%

    Strengths

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

    Considerations

    • This result measures ScreenSpot, not total model capability
  3. 03
    AC
    Qwen3 VL 235B A22B InstructAlibaba Cloud / Qwen Team
    Score
    95.4%

    Strengths

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

    Considerations

    • This result measures ScreenSpot, not total model capability
  4. 04
    AC
    Qwen3 VL 235B A22B ThinkingAlibaba Cloud / Qwen Team
    Score
    95.4%

    Strengths

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

    Considerations

    • This result measures ScreenSpot, not total model capability
  5. 05
    AC
    Qwen3 VL 30B A3B InstructAlibaba Cloud / Qwen Team
    Score
    94.7%

    Strengths

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

    Considerations

    • This result measures ScreenSpot, not total model capability

Selection summary

Best AI Models for ScreenSpot

Qwen3 VL 32B Instruct currently leads ScreenSpot with 95.8%. 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 #1Qwen3 VL 32B Instruct95.8%Benchmark rank #2Qwen3 VL 32B Thinking95.7%Benchmark rank #3Qwen3 VL 235B A22B Instruct95.4%

What is ScreenSpot?

What ScreenSpot measures and how its scores work.

ScreenSpot is the first realistic GUI grounding benchmark that encompasses mobile, desktop, and web environments. The dataset comprises over 1,200 instructions from iOS, Android, macOS, Windows and Web environments, along with annotated element types (text and icon/widget), designed to evaluate visual GUI agents' ability to accurately locate screen elements based on natural language instructions.

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

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

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

FAQ

Common questions about ScreenSpot.

Which model scores highest on ScreenSpot?

Qwen3 VL 32B Instruct is currently ranked first with 95.8%.

What does ScreenSpot measure?

ScreenSpot is the first realistic GUI grounding benchmark that encompasses mobile, desktop, and web environments. The dataset comprises over 1,200 instructions from iOS, Android, macOS, Windows and Web environments, along with annotated element types (text and icon/widget), designed to evaluate visual GUI agents' ability to accurately locate screen elements based on natural language instructions.

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.