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

POPE Leaderboard

Polling-based Object Probing Evaluation (POPE) is a benchmark for evaluating object hallucination in Large Vision-Language Models (LVLMs). POPE addresses the problem where LVLMs generate objects inconsistent with target images by using a polling-based query method that asks yes/no questions about object presence in images, providing more stable and flexible evaluation of object hallucination.

Updated Aug 17, 2026

Models3
Model coverage3
MetricScore
EvidenceB

On this page

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

POPE Ranking

Higher score ranks better on this benchmark.

3 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelLALFM2.5-VL-3BLiquid AIScore88.7%Percentile100.0%Participants3EvidenceCEvaluatedAug 17, 2026
Rank02ModelMIPhi-3.5-vision-instructMicrosoftScore86.1%Percentile50.0%Participants3EvidenceCEvaluatedAug 17, 2026
Rank03ModelMIPhi-4-multimodal-instructMicrosoftScore85.6%Percentile0.0%Participants3EvidenceCEvaluatedAug 17, 2026

POPE Highlights

The leading models and scores on this benchmark.

Rank #1LFM2.5-VL-3B88.7%Rank #2Phi-3.5-vision-instruct86.1%Rank #3Phi-4-multimodal-instruct85.6%

POPE Score Distribution

A closer view of the leading scores on this benchmark.

POPE

The Top AI Models for POPE

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

Ranking basisThis pope 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
    LA
    LFM2.5-VL-3BLiquid AI
    Score
    88.7%

    Strengths

    • Ranks #1 of 3 compared models
    • 100th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures POPE, not total model capability
  2. 02
    MI
    Phi-3.5-vision-instructMicrosoft
    Score
    86.1%

    Strengths

    • Ranks #2 of 3 compared models
    • 50th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures POPE, not total model capability
  3. 03
    MI
    Phi-4-multimodal-instructMicrosoft
    Score
    85.6%
    Speed
    Up to 25 tok/s via DeepInfra

    Strengths

    • Ranks #3 of 3 compared models
    • 0th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures POPE, not total model capability

Selection summary

Best AI Models for POPE

LFM2.5-VL-3B currently leads POPE with 88.7%. 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 #1LFM2.5-VL-3B88.7%Benchmark rank #2Phi-3.5-vision-instruct86.1%Benchmark rank #3Phi-4-multimodal-instruct85.6% · Up to 25 tok/s via DeepInfra

What is POPE?

What POPE measures and how its scores work.

Polling-based Object Probing Evaluation (POPE) is a benchmark for evaluating object hallucination in Large Vision-Language Models (LVLMs). POPE addresses the problem where LVLMs generate objects inconsistent with target images by using a polling-based query method that asks yes/no questions about object presence in images, providing more stable and flexible evaluation of object hallucination.

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

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

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

FAQ

Common questions about POPE.

Which model scores highest on POPE?

LFM2.5-VL-3B is currently ranked first with 88.7%.

What does POPE measure?

Polling-based Object Probing Evaluation (POPE) is a benchmark for evaluating object hallucination in Large Vision-Language Models (LVLMs). POPE addresses the problem where LVLMs generate objects inconsistent with target images by using a polling-based query method that asks yes/no questions about object presence in images, providing more stable and flexible evaluation of object hallucination.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

3 model results are currently shown.

Does this benchmark affect the overall score?

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