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

reasoning benchmark

CountBench Leaderboard

CountBench evaluates object counting capabilities in visual understanding.

Updated Aug 17, 2026

Models7
Model coverage7
MetricScore
EvidenceB

On this page

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

CountBench Ranking

Higher score ranks better on this benchmark.

7 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelACQwen3.5-27BAlibaba Cloud / Qwen TeamScore0.978 pointsPercentile100.0%Participants7EvidenceCEvaluatedAug 17, 2026
Rank02ModelACQwen3.5-35B-A3BAlibaba Cloud / Qwen TeamScore0.978 pointsPercentile83.3%Participants7EvidenceCEvaluatedAug 17, 2026
Rank03ModelACQwen3.6-27BAlibaba Cloud / Qwen TeamScore0.978 pointsPercentile66.7%Participants7EvidenceCEvaluatedAug 17, 2026
Rank04ModelACQwen3.6 PlusAlibaba Cloud / Qwen TeamScore0.976 pointsPercentile50.0%Participants7EvidenceCEvaluatedAug 17, 2026
Rank05ModelACQwen3.5-122B-A10BAlibaba Cloud / Qwen TeamScore0.97 pointsPercentile33.3%Participants7EvidenceCEvaluatedAug 17, 2026
Rank06ModelACQwen3 VL 235B A22B ThinkingAlibaba Cloud / Qwen TeamScore0.937 pointsPercentile16.7%Participants7EvidenceCEvaluatedAug 17, 2026
Rank07ModelCONorth Micro Vision InstructCohereScore0.725 pointsPercentile0.0%Participants7EvidenceCEvaluatedAug 17, 2026

CountBench Highlights

The leading models and scores on this benchmark.

Rank #1Qwen3.5-27B0.978 pointsRank #2Qwen3.5-35B-A3B0.978 pointsRank #3Qwen3.6-27B0.978 pointsRank #4Qwen3.6 Plus0.976 points

CountBench Score Distribution

A closer view of the leading scores on this benchmark.

CountBench

The Top AI Models for CountBench

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

Ranking basisThis countbench 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
    Qwen3.5-27BAlibaba Cloud / Qwen Team
    Score
    0.978 points
    Price
    $0.30 input / $2.4 output per 1M tokens
    Speed
    Up to 6.7 tok/s via Novita

    Strengths

    • Ranks #1 of 7 compared models
    • 100th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures CountBench, not total model capability
  2. 02
    AC
    Qwen3.5-35B-A3BAlibaba Cloud / Qwen Team
    Score
    0.978 points
    Price
    $0.25 input / $2.0 output per 1M tokens

    Strengths

    • Ranks #2 of 7 compared models
    • 83th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures CountBench, not total model capability
  3. 03
    AC
    Qwen3.6-27BAlibaba Cloud / Qwen Team
    Score
    0.978 points
    Price
    $0.60 input / $3.6 output per 1M tokens
    Speed
    Up to 6.1 tok/s via Novita

    Strengths

    • Ranks #3 of 7 compared models
    • 67th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures CountBench, not total model capability
  4. 04
    AC
    Qwen3.6 PlusAlibaba Cloud / Qwen Team
    Score
    0.976 points
    Price
    $0.50 input / $3.0 output per 1M tokens
    Speed
    Up to 16 tok/s via Together

    Strengths

    • Ranks #4 of 7 compared models
    • 50th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures CountBench, not total model capability
  5. 05
    AC
    Qwen3.5-122B-A10BAlibaba Cloud / Qwen Team
    Score
    0.97 points
    Price
    $0.40 input / $3.2 output per 1M tokens

    Strengths

    • Ranks #5 of 7 compared models
    • 33th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures CountBench, not total model capability

Selection summary

Best AI Models for CountBench

Qwen3.5-27B currently leads CountBench with 0.978 points. 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 #1Qwen3.5-27B0.978 points · $0.30 input / $2.4 output per 1M tokensBenchmark rank #2Qwen3.5-35B-A3B0.978 points · $0.25 input / $2.0 output per 1M tokensBenchmark rank #3Qwen3.6-27B0.978 points · $0.60 input / $3.6 output per 1M tokens

What is CountBench?

What CountBench measures and how its scores work.

CountBench evaluates object counting capabilities in visual understanding.

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

Family
CountBench
Modality
image
Primary category
reasoning
Score direction
higher
LLMBoard eligible
Yes
Evaluation key
countbench|llm-stats-current

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

FAQ

Common questions about CountBench.

Which model scores highest on CountBench?

Qwen3.5-27B is currently ranked first with 0.978 points.

What does CountBench measure?

CountBench evaluates object counting capabilities in visual understanding.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

7 model results are currently shown.

Does this benchmark affect the overall score?

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