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

classification benchmark

MIEB(eng) Classification Leaderboard

Direct model-level leaderboard results from MTEB.

Updated Aug 18, 2026

Models48
Model coverage48
MetricOfficial leaderboard task-type mean
EvidenceA

On this page

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

MIEB(eng) Classification Ranking

Higher official leaderboard task-type mean ranks better on this benchmark.

30 of 48 rows
Columns

Show columns

Sort by
Rank
Model
Official leaderboard task-type mean
Percentile
Participants
Evidence
Evaluated
Rank01ModelFAdinov2-giantFacebookOfficial leaderboard task-type mean78.9%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank02ModelQUEVA02-CLIP-bigE-14-plusQuansunOfficial leaderboard task-type mean78.4%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank03ModelFAdinov2-largeFacebookOfficial leaderboard task-type mean78.0%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank04ModelGOsiglip-so400m-patch14-384GoogleOfficial leaderboard task-type mean77.7%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank05ModelQUEVA02-CLIP-bigE-14QuansunOfficial leaderboard task-type mean76.9%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank06ModelFAdinov2-baseFacebookOfficial leaderboard task-type mean76.6%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank07ModelLACLIP-ViT-bigG-14-laion2B-39B-b160kLaionOfficial leaderboard task-type mean76.5%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank08ModelGOsiglip-large-patch16-384GoogleOfficial leaderboard task-type mean75.9%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank09ModelLACLIP-ViT-g-14-laion2B-s34B-b88KLaionOfficial leaderboard task-type mean75.3%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank10ModelLACLIP-ViT-L-14-DataComp.XL-s13B-b90KLaionOfficial leaderboard task-type mean75.2%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank11ModelGOsiglip-large-patch16-256GoogleOfficial leaderboard task-type mean75.1%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank12ModelLACLIP-ViT-H-14-laion2B-s32B-b79KLaionOfficial leaderboard task-type mean75.0%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank13ModelFAdinov2-smallFacebookOfficial leaderboard task-type mean73.6%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank14ModelLACLIP-ViT-L-14-laion2B-s32B-b82KLaionOfficial leaderboard task-type mean73.5%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank15ModelGOsiglip-base-patch16-512GoogleOfficial leaderboard task-type mean72.5%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank16ModelGOsiglip-base-patch16-384GoogleOfficial leaderboard task-type mean72.3%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank17ModelGOsiglip-base-patch16-256GoogleOfficial leaderboard task-type mean71.4%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank18ModelOPclip-vit-large-patch14OpenAIOfficial leaderboard task-type mean71.1%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank19ModelGOsiglip-base-patch16-224GoogleOfficial leaderboard task-type mean71.0%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank20ModelLACLIP-ViT-B-16-DataComp.XL-s13B-b90KLaionOfficial leaderboard task-type mean70.6%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank21ModelGOsiglip-base-patch16-256-multilingualGoogleOfficial leaderboard task-type mean70.0%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank22ModelJIjina-embeddings-v5-omni-smallJinaaiOfficial leaderboard task-type mean69.1%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank23ModelLACLIP-ViT-B-32-laion2B-s34B-b79KLaionOfficial leaderboard task-type mean67.3%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank24ModelLACLIP-ViT-B-32-DataComp.XL-s13B-b90KLaionOfficial leaderboard task-type mean67.3%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank25ModelQUEVA02-CLIP-L-14QuansunOfficial leaderboard task-type mean67.2%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank26ModelOPclip-vit-base-patch16OpenAIOfficial leaderboard task-type mean65.7%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank27ModelVOvoyage-multimodal-3VoyageaiOfficial leaderboard task-type mean64.8%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank28ModelNVmoco-v3-vit-lNyu VisionxOfficial leaderboard task-type mean62.7%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank29ModelOPclip-vit-base-patch32OpenAIOfficial leaderboard task-type mean62.5%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank30ModelNAnomic-embed-vision-v1.5Nomic AiOfficial leaderboard task-type mean62.4%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank31ModelSAblip-itm-large-cocoSalesforceOfficial leaderboard task-type mean62.3%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank32ModelROe5-vRoyokongOfficial leaderboard task-type mean62.3%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank33ModelJIjina-clip-v1JinaaiOfficial leaderboard task-type mean61.4%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank34ModelNVmoco-v3-vit-bNyu VisionxOfficial leaderboard task-type mean61.3%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank35ModelSAblip-itm-large-flickrSalesforceOfficial leaderboard task-type mean61.2%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank36ModelKAalign-baseKakaobrainOfficial leaderboard task-type mean60.9%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank37ModelSAblip2-opt-2.7bSalesforceOfficial leaderboard task-type mean60.9%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank38ModelSAblip2-opt-6.7b-cocoSalesforceOfficial leaderboard task-type mean60.0%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank39ModelBAbge-visualized-baseBaaiOfficial leaderboard task-type mean59.5%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank40ModelQUEVA02-CLIP-B-16QuansunOfficial leaderboard task-type mean58.0%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank41ModelSAblip-itm-base-cocoSalesforceOfficial leaderboard task-type mean57.9%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank42ModelBAbge-visualized-m3BaaiOfficial leaderboard task-type mean56.5%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank43ModelSAblip-itm-base-flickrSalesforceOfficial leaderboard task-type mean54.5%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank44ModelTLVLM2Vec-FullTiger LabOfficial leaderboard task-type mean54.1%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank45ModelTLVLM2Vec-LoRATiger LabOfficial leaderboard task-type mean54.1%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank46ModelJIjina-embeddings-v5-omni-nanoJinaaiOfficial leaderboard task-type mean53.5%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank47ModelSAblip-image-captioning-largeSalesforceOfficial leaderboard task-type mean37.8%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank48ModelSAblip-image-captioning-baseSalesforceOfficial leaderboard task-type mean33.8%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026

MIEB(eng) Classification Highlights

The leading models and scores on this benchmark.

Rank #1dinov2-giant78.9%Rank #2EVA02-CLIP-bigE-14-plus78.4%Rank #3dinov2-large78.0%Rank #4siglip-so400m-patch14-38477.7%

MIEB(eng) Classification Score Distribution

A closer view of the leading scores on this benchmark.

MIEB(eng) Classification

The Top AI Models for MIEB(eng) Classification

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

Ranking basisThis mieb(eng) classification AI model leaderboard uses descending official leaderboard task-type mean in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.

  1. 01
    FA
    dinov2-giantFacebook
    Official leaderboard task-type mean
    78.9%

    Strengths

    • Ranks #1 of 48 compared models
    • A evidence result

    Considerations

    • This result measures MIEB(eng) Classification, not total model capability
  2. 02
    QU
    EVA02-CLIP-bigE-14-plusQuansun
    Official leaderboard task-type mean
    78.4%

    Strengths

    • Ranks #2 of 48 compared models
    • A evidence result

    Considerations

    • This result measures MIEB(eng) Classification, not total model capability
  3. 03
    FA
    dinov2-largeFacebook
    Official leaderboard task-type mean
    78.0%

    Strengths

    • Ranks #3 of 48 compared models
    • A evidence result

    Considerations

    • This result measures MIEB(eng) Classification, not total model capability
  4. 04
    GO
    siglip-so400m-patch14-384Google
    Official leaderboard task-type mean
    77.7%

    Strengths

    • Ranks #4 of 48 compared models
    • A evidence result

    Considerations

    • This result measures MIEB(eng) Classification, not total model capability
  5. 05
    QU
    EVA02-CLIP-bigE-14Quansun
    Official leaderboard task-type mean
    76.9%

    Strengths

    • Ranks #5 of 48 compared models
    • A evidence result

    Considerations

    • This result measures MIEB(eng) Classification, not total model capability

Selection summary

Best AI Models for MIEB(eng) Classification

dinov2-giant currently leads MIEB(eng) Classification with 78.9%. 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 #1dinov2-giant78.9%Benchmark rank #2EVA02-CLIP-bigE-14-plus78.4%Benchmark rank #3dinov2-large78.0%

What is MIEB(eng) Classification?

What MIEB(eng) Classification measures and how its scores work.

Direct model-level leaderboard results from MTEB.

Scores are shown in ratio. This benchmark is verified and has an evidence level of A.

Family
MIEB(eng):classification
Modality
multimodal
Primary category
classification
Score direction
higher
LLMBoard eligible
Yes
Evaluation key
mteb-mieb-eng-classification|mteb|current

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

FAQ

Common questions about MIEB(eng) Classification.

Which model scores highest on MIEB(eng) Classification?

dinov2-giant is currently ranked first with 78.9%.

What does MIEB(eng) Classification measure?

Direct model-level leaderboard results from MTEB.

Is a higher official leaderboard task-type mean better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

48 model results are currently shown.

Does this benchmark affect the overall score?

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