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

clustering benchmark

MTEB(eng, v2) Clustering Leaderboard

Direct model-level leaderboard results from MTEB.

Updated Aug 18, 2026

Models100
Model coverage213
MetricOfficial leaderboard task-type mean
EvidenceA

On this page

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

MTEB(eng, v2) Clustering Ranking

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

30 of 100 rows
Columns

Show columns

Sort by
Rank
Model
Official leaderboard task-type mean
Percentile
Participants
Evidence
Evaluated
Rank01ModelCAF2LLM-4BCodefuse AiOfficial leaderboard task-type mean68.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank02ModelCAF2LLM-1.7BCodefuse AiOfficial leaderboard task-type mean64.1%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank03ModelCAF2LLM-v2-14BCodefuse AiOfficial leaderboard task-type mean63.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank04ModelCAF2LLM-v2-8BCodefuse AiOfficial leaderboard task-type mean62.8%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank05ModelCAF2LLM-v2-4BCodefuse AiOfficial leaderboard task-type mean62.0%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank06ModelKLQZhou-EmbeddingKingsoft LlmOfficial leaderboard task-type mean61.6%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank07ModelCAF2LLM-v2-1.7BCodefuse AiOfficial leaderboard task-type mean60.9%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank08ModelANgte-Qwen1.5-7B-instructAlibaba NlpOfficial leaderboard task-type mean60.9%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank09ModelSESeed1.5-EmbeddingOfficial leaderboard task-type mean60.8%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank10ModelNOjasper_en_vision_language_v1NovasearchOfficial leaderboard task-type mean60.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank11ModelCAF2LLM-0.6BCodefuse AiOfficial leaderboard task-type mean60.4%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank12ModelINJasper-Token-Compression-600MInfgradOfficial leaderboard task-type mean59.4%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank13ModelGOGemini Embedding 001GoogleOfficial leaderboard task-type mean59.4%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank14ModelSASFR-Embedding-2_RSalesforceOfficial leaderboard task-type mean59.4%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank15ModelANLGAI-Embedding-PreviewAnnamodelsOfficial leaderboard task-type mean59.3%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank16ModelBYSeed1.6-embeddingByteDanceOfficial leaderboard task-type mean59.2%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank17ModelANgte-Qwen2-7B-instructAlibaba NlpOfficial leaderboard task-type mean59.0%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank18ModelACQwen3-Embedding-8BAlibaba Cloud / Qwen TeamOfficial leaderboard task-type mean58.6%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank19ModelJCingot-8b-r3JcornersOfficial leaderboard task-type mean58.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank20ModelCAF2LLM-v2-0.6BCodefuse AiOfficial leaderboard task-type mean58.2%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank21ModelKEKaLM-embedding-multilingual-mini-instruct-v2.5Kalm EmbeddingOfficial leaderboard task-type mean58.1%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank22ModelNOstella_en_400M_v5NovasearchOfficial leaderboard task-type mean57.7%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank23ModelACQwen3-Embedding-4BAlibaba Cloud / Qwen TeamOfficial leaderboard task-type mean57.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank24ModelNOstella_en_1.5B_v5NovasearchOfficial leaderboard task-type mean57.1%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank25ModelITBOOM_4B_v1Ict Time And QueritOfficial leaderboard task-type mean56.6%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank26ModelGOembeddinggemma-300mGoogleOfficial leaderboard task-type mean56.6%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank27ModelCAF2LLM-v2-330MCodefuse AiOfficial leaderboard task-type mean56.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank28ModelGRGeoEmbeddingGeogpt Research ProjectOfficial leaderboard task-type mean56.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank29ModelITICT-TIME-and-Querit-embedding-v1Ict Time And QueritOfficial leaderboard task-type mean56.3%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank30ModelASGiga-Embeddings-instructAi SageOfficial leaderboard task-type mean56.2%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank31ModelTATarka-Embedding-350M-V1Tarka AirOfficial leaderboard task-type mean55.7%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank32ModelKINano-Em1-0.6B-v2.1KitefishaiOfficial leaderboard task-type mean55.4%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank33ModelSASFR-Embedding-MistralSalesforceOfficial leaderboard task-type mean54.9%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank34ModelJIjina-embeddings-v5-omni-smallJinaaiOfficial leaderboard task-type mean54.7%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank35ModelJIjina-embeddings-v5-text-smallJinaaiOfficial leaderboard task-type mean54.7%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank36ModelLALinq-Embed-MistralLinq Ai ResearchOfficial leaderboard task-type mean54.1%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank37ModelACQwen3-Embedding-0.6BAlibaba Cloud / Qwen TeamOfficial leaderboard task-type mean54.1%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank38ModelANgte-Qwen2-1.5B-instructAlibaba NlpOfficial leaderboard task-type mean53.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank39ModelJIjina-embeddings-v5-omni-nanoJinaaiOfficial leaderboard task-type mean53.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank40ModelJIjina-embeddings-v5-text-nanoJinaaiOfficial leaderboard task-type mean53.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank41ModelKINano-Em1-0.6B-v2KitefishaiOfficial leaderboard task-type mean52.9%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank42ModelCAF2LLM-v2-160MCodefuse AiOfficial leaderboard task-type mean52.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank43ModelTATarka-Embedding-150M-V1Tarka AirOfficial leaderboard task-type mean52.0%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank44ModelGOtext-embedding-005GoogleOfficial leaderboard task-type mean51.9%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank45ModelIEYuan-embedding-2.0-enIeityuanOfficial leaderboard task-type mean51.7%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank46ModelBIBidirLM-Omni-2.5B-EmbeddingBidirlmOfficial leaderboard task-type mean51.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank47ModelGOtext-embedding-004GoogleOfficial leaderboard task-type mean51.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank48ModelGRGritLM-8x7BGritlmOfficial leaderboard task-type mean51.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank49ModelINe5-mistral-7b-instructIntfloatOfficial leaderboard task-type mean51.4%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank50ModelGRGritLM-7BGritlmOfficial leaderboard task-type mean50.8%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank51ModelCAF2LLM-v2-80MCodefuse AiOfficial leaderboard task-type mean50.7%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank52ModelGOtext-multilingual-embedding-002GoogleOfficial leaderboard task-type mean50.4%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank53ModelVOvoyage-large-2-instructVoyageaiOfficial leaderboard task-type mean50.0%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank54ModelINmultilingual-e5-large-instructIntfloatOfficial leaderboard task-type mean49.9%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank55ModelNVNV-Embed-v1NVIDIAOfficial leaderboard task-type mean49.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank56ModelCOCohere-embed-english-v3.0CohereOfficial leaderboard task-type mean49.3%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank57ModelOPtext-embedding-3-largeOpenAIOfficial leaderboard task-type mean48.9%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank58ModelAVGIST-large-Embedding-v0AvsolatorioOfficial leaderboard task-type mean48.8%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank59ModelVOvoyage-code-3VoyageaiOfficial leaderboard task-type mean48.6%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank60ModelAVGIST-Embedding-v0AvsolatorioOfficial leaderboard task-type mean48.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank61ModelVPSearchMap_PreviewVplabsOfficial leaderboard task-type mean48.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank62ModelSDmmlw-e5-largeSdadasOfficial leaderboard task-type mean48.3%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank63ModelTHgte-largeThenlperOfficial leaderboard task-type mean48.2%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank64ModelVOvoyage-law-2VoyageaiOfficial leaderboard task-type mean48.1%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank65ModelCOCohere-embed-multilingual-v3.0CohereOfficial leaderboard task-type mean48.1%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank66ModelBAbge-large-en-v1.5BaaiOfficial leaderboard task-type mean48.0%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank67ModelVOvoyage-large-2VoyageaiOfficial leaderboard task-type mean48.0%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank68ModelVOvoyage-code-2VoyageaiOfficial leaderboard task-type mean48.0%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank69ModelAVGIST-small-Embedding-v0AvsolatorioOfficial leaderboard task-type mean48.0%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank70ModelAVNoInstruct-small-Embedding-v0AvsolatorioOfficial leaderboard task-type mean47.9%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank71ModelPRmini-gtePrdevOfficial leaderboard task-type mean47.9%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank72ModelSDmmlw-roberta-largeSdadasOfficial leaderboard task-type mean47.9%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank73ModelWHUAE-Large-V1WhereisaiOfficial leaderboard task-type mean47.9%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank74ModelTHgte-baseThenlperOfficial leaderboard task-type mean47.7%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank75ModelNVNV-Embed-v2NVIDIAOfficial leaderboard task-type mean47.7%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank76ModelCOCohere-embed-english-light-v3.0CohereOfficial leaderboard task-type mean47.6%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank77ModelNAnomic-embed-text-v1.5Nomic AiOfficial leaderboard task-type mean47.6%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank78ModelINstella-base-en-v2InfgradOfficial leaderboard task-type mean47.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank79ModelMAmxbai-embed-large-v1Mixedbread AiOfficial leaderboard task-type mean47.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank80ModelOPtext-embedding-3-smallOpenAIOfficial leaderboard task-type mean47.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank81ModelBAbge-base-en-v1.5BaaiOfficial leaderboard task-type mean47.4%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank82ModelJIjina-embeddings-v3JinaaiOfficial leaderboard task-type mean47.4%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank83ModelTHgte-smallThenlperOfficial leaderboard task-type mean47.4%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank84ModelIGgranite-embedding-english-r2Ibm GraniteOfficial leaderboard task-type mean47.2%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank85ModelIGgranite-embedding-125m-englishIbm GraniteOfficial leaderboard task-type mean47.2%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank86ModelSDmmlw-e5-baseSdadasOfficial leaderboard task-type mean47.1%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank87ModelABMedEmbed-small-v0.1AbhinandOfficial leaderboard task-type mean47.0%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank88ModelBAbge-small-en-v1.5BaaiOfficial leaderboard task-type mean47.0%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank89ModelMOmdbr-leaf-mtMongodbOfficial leaderboard task-type mean46.7%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank90ModelTEOmniEmbed-v0.1TevatronOfficial leaderboard task-type mean46.7%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank91ModelNAnomic-embed-text-v1Nomic AiOfficial leaderboard task-type mean46.6%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank92ModelVOvoyage-finance-2VoyageaiOfficial leaderboard task-type mean46.6%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank93ModelSTall-mpnet-base-v2Sentence TransformersOfficial leaderboard task-type mean46.6%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank94ModelIGgranite-embedding-small-english-r2Ibm GraniteOfficial leaderboard task-type mean46.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank95ModelLAbilingual-embedding-largeLajavanessOfficial leaderboard task-type mean46.5%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank96ModelVOvoyage-2VoyageaiOfficial leaderboard task-type mean46.4%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank97ModelSDmmlw-roberta-baseSdadasOfficial leaderboard task-type mean46.3%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank98ModelAVGIST-all-MiniLM-L6-v2AvsolatorioOfficial leaderboard task-type mean46.2%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank99ModelNAnomic-embed-text-v1-ablatedNomic AiOfficial leaderboard task-type mean46.1%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026
Rank100ModelIGgranite-embedding-30m-englishIbm GraniteOfficial leaderboard task-type mean46.1%PercentileN/AParticipants213EvidenceAEvaluatedAug 18, 2026

MTEB(eng, v2) Clustering Highlights

The leading models and scores on this benchmark.

Rank #1F2LLM-4B68.5%Rank #2F2LLM-1.7B64.1%Rank #3F2LLM-v2-14B63.5%Rank #4F2LLM-v2-8B62.8%

MTEB(eng, v2) Clustering Score Distribution

A closer view of the leading scores on this benchmark.

MTEB(eng, v2) Clustering

The Top AI Models for MTEB(eng, v2) Clustering

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

Ranking basisThis mteb(eng, v2) clustering 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
    CA
    F2LLM-4BCodefuse Ai
    Official leaderboard task-type mean
    68.5%

    Strengths

    • Ranks #1 of 213 compared models
    • A evidence result

    Considerations

    • This result measures MTEB(eng, v2) Clustering, not total model capability
  2. 02
    CA
    F2LLM-1.7BCodefuse Ai
    Official leaderboard task-type mean
    64.1%

    Strengths

    • Ranks #2 of 213 compared models
    • A evidence result

    Considerations

    • This result measures MTEB(eng, v2) Clustering, not total model capability
  3. 03
    CA
    F2LLM-v2-14BCodefuse Ai
    Official leaderboard task-type mean
    63.5%

    Strengths

    • Ranks #3 of 213 compared models
    • A evidence result

    Considerations

    • This result measures MTEB(eng, v2) Clustering, not total model capability
  4. 04
    CA
    F2LLM-v2-8BCodefuse Ai
    Official leaderboard task-type mean
    62.8%

    Strengths

    • Ranks #4 of 213 compared models
    • A evidence result

    Considerations

    • This result measures MTEB(eng, v2) Clustering, not total model capability
  5. 05
    CA
    F2LLM-v2-4BCodefuse Ai
    Official leaderboard task-type mean
    62.0%

    Strengths

    • Ranks #5 of 213 compared models
    • A evidence result

    Considerations

    • This result measures MTEB(eng, v2) Clustering, not total model capability

Selection summary

Best AI Models for MTEB(eng, v2) Clustering

F2LLM-4B currently leads MTEB(eng, v2) Clustering with 68.5%. 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 #1F2LLM-4B68.5%Benchmark rank #2F2LLM-1.7B64.1%Benchmark rank #3F2LLM-v2-14B63.5%

What is MTEB(eng, v2) Clustering?

What MTEB(eng, v2) Clustering 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
MTEB(eng, v2):clustering
Modality
multimodal
Primary category
clustering
Score direction
higher
LLMBoard eligible
Yes
Evaluation key
mteb-mteb-eng-v2-clustering|mteb|current

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

FAQ

Common questions about MTEB(eng, v2) Clustering.

Which model scores highest on MTEB(eng, v2) Clustering?

F2LLM-4B is currently ranked first with 68.5%.

What does MTEB(eng, v2) Clustering 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?

100 model results are currently shown.

Does this benchmark affect the overall score?

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