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

reranking benchmark

MTEB(eng, v2) Reranking Leaderboard

Direct model-level leaderboard results from MTEB.

Updated Aug 18, 2026

Models100
Model coverage237
MetricOfficial leaderboard task-type mean
EvidenceA

On this page

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

MTEB(eng, v2) Reranking 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
Rank01ModelIEYuan-embedding-2.0-enIeityuanOfficial leaderboard task-type mean53.3%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank02ModelKLQZhou-EmbeddingKingsoft LlmOfficial leaderboard task-type mean51.8%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank03ModelACQwen3-Embedding-8BAlibaba Cloud / Qwen TeamOfficial leaderboard task-type mean51.6%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank04ModelJCingot-8b-r3JcornersOfficial leaderboard task-type mean50.9%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank05ModelACQwen3-Embedding-4BAlibaba Cloud / Qwen TeamOfficial leaderboard task-type mean50.8%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank06ModelSESeed1.5-EmbeddingOfficial leaderboard task-type mean50.7%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank07ModelINJasper-Token-Compression-600MInfgradOfficial leaderboard task-type mean50.6%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank08ModelANgte-Qwen2-7B-instructAlibaba NlpOfficial leaderboard task-type mean50.5%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank09ModelCAF2LLM-v2-14BCodefuse AiOfficial leaderboard task-type mean50.3%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank10ModelHCspeed-embedding-7b-instructHaon ChenOfficial leaderboard task-type mean50.3%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank11ModelBYSeed1.6-embeddingByteDanceOfficial leaderboard task-type mean50.3%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank12ModelCAF2LLM-v2-8BCodefuse AiOfficial leaderboard task-type mean50.2%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank13ModelNOstella_en_1.5B_v5NovasearchOfficial leaderboard task-type mean50.2%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank14ModelSASFR-Embedding-MistralSalesforceOfficial leaderboard task-type mean50.2%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank15ModelVOvoyage-large-2-instructVoyageaiOfficial leaderboard task-type mean50.1%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank16ModelCAF2LLM-v2-4BCodefuse AiOfficial leaderboard task-type mean50.1%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank17ModelCAF2LLM-4BCodefuse AiOfficial leaderboard task-type mean50.0%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank18ModelNOjasper_en_vision_language_v1NovasearchOfficial leaderboard task-type mean50.0%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank19ModelCAF2LLM-1.7BCodefuse AiOfficial leaderboard task-type mean49.8%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank20ModelINe5-mistral-7b-instructIntfloatOfficial leaderboard task-type mean49.8%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank21ModelASGiga-Embeddings-instructAi SageOfficial leaderboard task-type mean49.7%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank22ModelNVNV-Embed-v2NVIDIAOfficial leaderboard task-type mean49.6%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank23ModelNOstella_en_400M_v5NovasearchOfficial leaderboard task-type mean49.6%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank24ModelGRGritLM-7BGritlmOfficial leaderboard task-type mean49.6%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank25ModelITICT-TIME-and-Querit-embedding-v1Ict Time And QueritOfficial leaderboard task-type mean49.5%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank26ModelKINano-Em1-0.6B-v2.1KitefishaiOfficial leaderboard task-type mean49.5%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank27ModelLALinq-Embed-MistralLinq Ai ResearchOfficial leaderboard task-type mean49.4%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank28ModelJIjina-embeddings-v5-omni-smallJinaaiOfficial leaderboard task-type mean49.4%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank29ModelJIjina-embeddings-v5-text-smallJinaaiOfficial leaderboard task-type mean49.4%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank30ModelIGgranite-embedding-125m-englishIbm GraniteOfficial leaderboard task-type mean49.4%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank31ModelITBOOM_4B_v1Ict Time And QueritOfficial leaderboard task-type mean49.3%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank32ModelANgte-Qwen2-1.5B-instructAlibaba NlpOfficial leaderboard task-type mean49.2%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank33ModelCAF2LLM-v2-1.7BCodefuse AiOfficial leaderboard task-type mean49.2%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank34ModelJIjina-embeddings-v5-omni-nanoJinaaiOfficial leaderboard task-type mean49.2%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank35ModelJIjina-embeddings-v5-text-nanoJinaaiOfficial leaderboard task-type mean49.2%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank36ModelGRGritLM-8x7BGritlmOfficial leaderboard task-type mean49.2%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank37ModelQUQuerit-4BQueritOfficial leaderboard task-type mean49.2%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank38ModelNVNV-Embed-v1NVIDIAOfficial leaderboard task-type mean49.2%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank39ModelANLGAI-Embedding-PreviewAnnamodelsOfficial leaderboard task-type mean49.1%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank40ModelIGgranite-embedding-english-r2Ibm GraniteOfficial leaderboard task-type mean49.1%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank41ModelTEConan-embedding-v2TencentbacOfficial leaderboard task-type mean49.1%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank42ModelANgme-Qwen2-VL-7B-InstructAlibaba NlpOfficial leaderboard task-type mean49.0%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank43ModelSASFR-Embedding-2_RSalesforceOfficial leaderboard task-type mean49.0%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank44ModelMNLLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervisedMcgill NlpOfficial leaderboard task-type mean48.9%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank45ModelGOtext-embedding-005GoogleOfficial leaderboard task-type mean48.8%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank46ModelAVGIST-large-Embedding-v0AvsolatorioOfficial leaderboard task-type mean48.8%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank47ModelINmultilingual-e5-large-instructIntfloatOfficial leaderboard task-type mean48.7%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank48ModelYILENS-d4000YibinleiOfficial leaderboard task-type mean48.7%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank49ModelYILENS-d8000YibinleiOfficial leaderboard task-type mean48.6%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank50ModelW6b1ade-embedW601SxsOfficial leaderboard task-type mean48.6%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank51ModelGOGemini Embedding 001GoogleOfficial leaderboard task-type mean48.6%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank52ModelGOtext-embedding-004GoogleOfficial leaderboard task-type mean48.5%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank53ModelSTall-mpnet-base-v2Sentence TransformersOfficial leaderboard task-type mean48.4%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank54ModelZAZeta-Alpha-E5-MistralZeta Alpha AiOfficial leaderboard task-type mean48.4%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank55ModelLLember-v1LlmrailsOfficial leaderboard task-type mean48.4%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank56ModelWHUAE-Large-V1WhereisaiOfficial leaderboard task-type mean48.4%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank57ModelGRGeoEmbeddingGeogpt Research ProjectOfficial leaderboard task-type mean48.3%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank58ModelVOvoyage-3-m-expVoyageaiOfficial leaderboard task-type mean48.3%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank59ModelQUQueritQueritOfficial leaderboard task-type mean48.3%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank60ModelBAbge-large-en-v1.5BaaiOfficial leaderboard task-type mean48.3%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank61ModelBAbge-multilingual-gemma2BaaiOfficial leaderboard task-type mean48.2%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank62ModelACQwen3-Embedding-0.6BAlibaba Cloud / Qwen TeamOfficial leaderboard task-type mean48.2%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank63ModelMAmxbai-embed-large-v1Mixedbread AiOfficial leaderboard task-type mean48.1%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank64ModelJIjina-embeddings-v3JinaaiOfficial leaderboard task-type mean47.9%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank65ModelVPSearchMap_PreviewVplabsOfficial leaderboard task-type mean47.9%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank66ModelCAF2LLM-0.6BCodefuse AiOfficial leaderboard task-type mean47.9%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank67ModelBAbge-en-iclBaaiOfficial leaderboard task-type mean47.9%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank68ModelTHgte-largeThenlperOfficial leaderboard task-type mean47.8%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank69ModelBIBidirLM-Omni-2.5B-EmbeddingBidirlmOfficial leaderboard task-type mean47.8%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank70ModelMAmxbai-embed-2d-large-v1Mixedbread AiOfficial leaderboard task-type mean47.8%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank71ModelTATarka-Embedding-350M-V1Tarka AirOfficial leaderboard task-type mean47.8%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank72ModelMNLLM2Vec-Mistral-7B-Instruct-v2-mntp-supervisedMcgill NlpOfficial leaderboard task-type mean47.7%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank73ModelCAF2LLM-v2-0.6BCodefuse AiOfficial leaderboard task-type mean47.7%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank74ModelSDmmlw-e5-largeSdadasOfficial leaderboard task-type mean47.6%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank75ModelANgte-modernbert-baseAlibaba NlpOfficial leaderboard task-type mean47.6%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank76ModelIGgranite-embedding-small-english-r2Ibm GraniteOfficial leaderboard task-type mean47.6%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank77ModelSDmmlw-roberta-largeSdadasOfficial leaderboard task-type mean47.6%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank78ModelSTall-MiniLM-L12-v2Sentence TransformersOfficial leaderboard task-type mean47.5%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank79ModelAVGIST-Embedding-v0AvsolatorioOfficial leaderboard task-type mean47.5%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank80ModelIGgranite-embedding-30m-englishIbm GraniteOfficial leaderboard task-type mean47.5%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank81ModelBAbge-large-enBaaiOfficial leaderboard task-type mean47.5%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank82ModelGOtext-multilingual-embedding-002GoogleOfficial leaderboard task-type mean47.5%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank83ModelSNsnowflake-arctic-embed-l-v2.0SnowflakeOfficial leaderboard task-type mean47.5%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank84ModelGOembeddinggemma-300mGoogleOfficial leaderboard task-type mean47.4%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank85ModelKEKaLM-embedding-multilingual-mini-instruct-v2.5Kalm EmbeddingOfficial leaderboard task-type mean47.4%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank86ModelVOvoyage-multilingual-2VoyageaiOfficial leaderboard task-type mean47.4%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank87ModelCOCohere-embed-multilingual-v3.0CohereOfficial leaderboard task-type mean47.4%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank88ModelAVGIST-small-Embedding-v0AvsolatorioOfficial leaderboard task-type mean47.3%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank89ModelINstella-base-en-v2InfgradOfficial leaderboard task-type mean47.3%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank90ModelMOmdbr-leaf-mtMongodbOfficial leaderboard task-type mean47.3%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank91ModelAMTitan-text-embeddings-v2AmazonOfficial leaderboard task-type mean47.3%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank92ModelABMedEmbed-small-v0.1AbhinandOfficial leaderboard task-type mean47.2%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank93ModelCOCohere-embed-english-v3.0CohereOfficial leaderboard task-type mean47.2%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank94ModelTHgte-baseThenlperOfficial leaderboard task-type mean47.2%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank95ModelSTall-MiniLM-L6-v2Sentence TransformersOfficial leaderboard task-type mean47.1%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank96ModelBRslx-v0.1BrahmairesearchOfficial leaderboard task-type mean47.1%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank97ModelAVGIST-all-MiniLM-L6-v2AvsolatorioOfficial leaderboard task-type mean47.1%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank98ModelHTKaLM-embedding-multilingual-mini-instruct-v2Hit TmgOfficial leaderboard task-type mean47.1%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank99ModelANgme-Qwen2-VL-2B-InstructAlibaba NlpOfficial leaderboard task-type mean47.0%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026
Rank100ModelAVNoInstruct-small-Embedding-v0AvsolatorioOfficial leaderboard task-type mean47.0%PercentileN/AParticipants237EvidenceAEvaluatedAug 18, 2026

MTEB(eng, v2) Reranking Highlights

The leading models and scores on this benchmark.

Rank #1Yuan-embedding-2.0-en53.3%Rank #2QZhou-Embedding51.8%Rank #3Qwen3-Embedding-8B51.6%Rank #4ingot-8b-r350.9%

MTEB(eng, v2) Reranking Score Distribution

A closer view of the leading scores on this benchmark.

MTEB(eng, v2) Reranking

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

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) reranking 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
    IE
    Yuan-embedding-2.0-enIeityuan
    Official leaderboard task-type mean
    53.3%

    Strengths

    • Ranks #1 of 237 compared models
    • A evidence result

    Considerations

    • This result measures MTEB(eng, v2) Reranking, not total model capability
  2. 02
    KL
    QZhou-EmbeddingKingsoft Llm
    Official leaderboard task-type mean
    51.8%

    Strengths

    • Ranks #2 of 237 compared models
    • A evidence result

    Considerations

    • This result measures MTEB(eng, v2) Reranking, not total model capability
  3. 03
    AC
    Qwen3-Embedding-8BAlibaba Cloud / Qwen Team
    Official leaderboard task-type mean
    51.6%

    Strengths

    • Ranks #3 of 237 compared models
    • A evidence result

    Considerations

    • This result measures MTEB(eng, v2) Reranking, not total model capability
  4. 04
    JC
    ingot-8b-r3Jcorners
    Official leaderboard task-type mean
    50.9%

    Strengths

    • Ranks #4 of 237 compared models
    • A evidence result

    Considerations

    • This result measures MTEB(eng, v2) Reranking, not total model capability
  5. 05
    AC
    Qwen3-Embedding-4BAlibaba Cloud / Qwen Team
    Official leaderboard task-type mean
    50.8%

    Strengths

    • Ranks #5 of 237 compared models
    • A evidence result

    Considerations

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

Selection summary

Best AI Models for MTEB(eng, v2) Reranking

Yuan-embedding-2.0-en currently leads MTEB(eng, v2) Reranking with 53.3%. 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 #1Yuan-embedding-2.0-en53.3%Benchmark rank #2QZhou-Embedding51.8%Benchmark rank #3Qwen3-Embedding-8B51.6%

What is MTEB(eng, v2) Reranking?

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

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

FAQ

Common questions about MTEB(eng, v2) Reranking.

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

Yuan-embedding-2.0-en is currently ranked first with 53.3%.

What does MTEB(eng, v2) Reranking 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.