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

semantic similarity benchmark

MIEB(eng) Semantic Similarity 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) Semantic Similarity 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
Rank01ModelJIjina-embeddings-v5-omni-smallJinaaiOfficial leaderboard task-type mean63.9%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank02ModelROe5-vRoyokongOfficial leaderboard task-type mean62.8%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank03ModelVOvoyage-multimodal-3VoyageaiOfficial leaderboard task-type mean62.7%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank04ModelQUEVA02-CLIP-bigE-14-plusQuansunOfficial leaderboard task-type mean58.8%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank05ModelLACLIP-ViT-bigG-14-laion2B-39B-b160kLaionOfficial leaderboard task-type mean56.6%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank06ModelOPclip-vit-base-patch16OpenAIOfficial leaderboard task-type mean55.6%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank07ModelQUEVA02-CLIP-bigE-14QuansunOfficial leaderboard task-type mean55.6%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank08ModelLACLIP-ViT-g-14-laion2B-s34B-b88KLaionOfficial leaderboard task-type mean55.5%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank09ModelJIjina-embeddings-v5-omni-nanoJinaaiOfficial leaderboard task-type mean54.8%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank10ModelOPclip-vit-large-patch14OpenAIOfficial leaderboard task-type mean54.6%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank11ModelGOsiglip-large-patch16-384GoogleOfficial leaderboard task-type mean54.6%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank12ModelLACLIP-ViT-L-14-DataComp.XL-s13B-b90KLaionOfficial leaderboard task-type mean54.5%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank13ModelSAblip-itm-base-cocoSalesforceOfficial leaderboard task-type mean54.3%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank14ModelGOsiglip-so400m-patch14-384GoogleOfficial leaderboard task-type mean54.2%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank15ModelGOsiglip-large-patch16-256GoogleOfficial leaderboard task-type mean54.1%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank16ModelTLVLM2Vec-FullTiger LabOfficial leaderboard task-type mean54.0%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank17ModelJIjina-clip-v1JinaaiOfficial leaderboard task-type mean53.9%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank18ModelLACLIP-ViT-H-14-laion2B-s32B-b79KLaionOfficial leaderboard task-type mean53.8%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank19ModelTLVLM2Vec-LoRATiger LabOfficial leaderboard task-type mean53.6%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank20ModelQUEVA02-CLIP-L-14QuansunOfficial leaderboard task-type mean53.6%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank21ModelLACLIP-ViT-B-16-DataComp.XL-s13B-b90KLaionOfficial leaderboard task-type mean53.6%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank22ModelSAblip-itm-base-flickrSalesforceOfficial leaderboard task-type mean53.5%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank23ModelLACLIP-ViT-L-14-laion2B-s32B-b82KLaionOfficial leaderboard task-type mean53.3%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank24ModelGOsiglip-base-patch16-256GoogleOfficial leaderboard task-type mean52.8%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank25ModelGOsiglip-base-patch16-384GoogleOfficial leaderboard task-type mean52.8%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank26ModelGOsiglip-base-patch16-512GoogleOfficial leaderboard task-type mean52.6%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank27ModelGOsiglip-base-patch16-224GoogleOfficial leaderboard task-type mean52.0%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank28ModelGOsiglip-base-patch16-256-multilingualGoogleOfficial leaderboard task-type mean51.8%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank29ModelSAblip-itm-large-cocoSalesforceOfficial leaderboard task-type mean51.7%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank30ModelKAalign-baseKakaobrainOfficial leaderboard task-type mean51.5%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank31ModelLACLIP-ViT-B-32-laion2B-s34B-b79KLaionOfficial leaderboard task-type mean50.1%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank32ModelSAblip-itm-large-flickrSalesforceOfficial leaderboard task-type mean49.8%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank33ModelOPclip-vit-base-patch32OpenAIOfficial leaderboard task-type mean49.7%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank34ModelBAbge-visualized-m3BaaiOfficial leaderboard task-type mean48.2%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank35ModelLACLIP-ViT-B-32-DataComp.XL-s13B-b90KLaionOfficial leaderboard task-type mean48.1%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank36ModelBAbge-visualized-baseBaaiOfficial leaderboard task-type mean46.8%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank37ModelSAblip-image-captioning-largeSalesforceOfficial leaderboard task-type mean44.6%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank38ModelQUEVA02-CLIP-B-16QuansunOfficial leaderboard task-type mean43.8%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank39ModelSAblip-image-captioning-baseSalesforceOfficial leaderboard task-type mean41.5%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank40ModelSAblip2-opt-6.7b-cocoSalesforceOfficial leaderboard task-type mean39.9%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank41ModelSAblip2-opt-2.7bSalesforceOfficial leaderboard task-type mean36.9%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank42ModelNAnomic-embed-vision-v1.5Nomic AiOfficial leaderboard task-type mean33.3%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank43ModelFAdinov2-baseFacebookOfficial leaderboard task-type mean16.8%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank44ModelFAdinov2-giantFacebookOfficial leaderboard task-type mean15.0%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank45ModelNVmoco-v3-vit-bNyu VisionxOfficial leaderboard task-type mean14.9%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank46ModelNVmoco-v3-vit-lNyu VisionxOfficial leaderboard task-type mean14.7%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank47ModelFAdinov2-largeFacebookOfficial leaderboard task-type mean13.8%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026
Rank48ModelFAdinov2-smallFacebookOfficial leaderboard task-type mean13.0%PercentileN/AParticipants48EvidenceAEvaluatedAug 18, 2026

MIEB(eng) Semantic Similarity Highlights

The leading models and scores on this benchmark.

Rank #1jina-embeddings-v5-omni-small63.9%Rank #2e5-v62.8%Rank #3voyage-multimodal-362.7%Rank #4EVA02-CLIP-bigE-14-plus58.8%

MIEB(eng) Semantic Similarity Score Distribution

A closer view of the leading scores on this benchmark.

MIEB(eng) Semantic Similarity

The Top AI Models for MIEB(eng) Semantic Similarity

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) semantic similarity 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
    JI
    jina-embeddings-v5-omni-smallJinaai
    Official leaderboard task-type mean
    63.9%

    Strengths

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

    Considerations

    • This result measures MIEB(eng) Semantic Similarity, not total model capability
  2. 02
    RO
    e5-vRoyokong
    Official leaderboard task-type mean
    62.8%

    Strengths

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

    Considerations

    • This result measures MIEB(eng) Semantic Similarity, not total model capability
  3. 03
    VO
    voyage-multimodal-3Voyageai
    Official leaderboard task-type mean
    62.7%

    Strengths

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

    Considerations

    • This result measures MIEB(eng) Semantic Similarity, not total model capability
  4. 04
    QU
    EVA02-CLIP-bigE-14-plusQuansun
    Official leaderboard task-type mean
    58.8%

    Strengths

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

    Considerations

    • This result measures MIEB(eng) Semantic Similarity, not total model capability
  5. 05
    LA
    CLIP-ViT-bigG-14-laion2B-39B-b160kLaion
    Official leaderboard task-type mean
    56.6%

    Strengths

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

    Considerations

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

Selection summary

Best AI Models for MIEB(eng) Semantic Similarity

jina-embeddings-v5-omni-small currently leads MIEB(eng) Semantic Similarity with 63.9%. 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 #1jina-embeddings-v5-omni-small63.9%Benchmark rank #2e5-v62.8%Benchmark rank #3voyage-multimodal-362.7%

What is MIEB(eng) Semantic Similarity?

What MIEB(eng) Semantic Similarity 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):semantic_similarity
Modality
multimodal
Primary category
semantic similarity
Score direction
higher
LLMBoard eligible
Yes
Evaluation key
mteb-mieb-eng-semantic_similarity|mteb|current

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

FAQ

Common questions about MIEB(eng) Semantic Similarity.

Which model scores highest on MIEB(eng) Semantic Similarity?

jina-embeddings-v5-omni-small is currently ranked first with 63.9%.

What does MIEB(eng) Semantic Similarity 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.