L

Bilingual Embedding Base

Jun 2024
LBilingual Embedding Base
Compare in
on
self-host onlyprice
43.2MTEB English v2
Jun 2024released
768Dimensions
1K tokensMax input

Rankingconfiguration unstated?

Full ranking →
1Nemotron 3 Embed 8B Legal702Nemotron 3 Embed 8B BF1669.83F2LLM v2 14B67.24Llama Embed Nemotron 8B675Qwen 3 Embedding 8B66.8
···
48USER Base54.949Bilingual Embedding Base54.850Granite Embedding 97M Multilingual R254.7

Strong at

C
Embeddings & Retrieval#134 of 200

Run it yourself

estimate
Fits on✓ 8 GB (phone, laptop) · full quality✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use

Benchmarks

in Embeddings & Retrieval
BEIR · Mean over tasks · English43.8#137
BEIR · Mean over task types · English43.8#137
BEIR · Retrieval · English43.8#137
MTEB Persian v2 · Reranking · Persian68.4#33
JMTEB v2 · Clustering · Japanese48.3#43
JMTEB v2 · STS · Japanese80.2#39
LongEmbed · Mean over tasks · English40.6#67
LongEmbed · Mean over task types · English40.6#67
LongEmbed · Retrieval · English40.6#67
MTEB German v1 · Mean over tasks · German54#19
MTEB German v1 · Mean over task types · German53.3#18
MTEB German v1 · Clustering · German34.1#26
MTEB German v1 · Retrieval · German48.6#25
MTEB German v1 · Classification · German66.6#36
MTEB German v1 · STS · German71.7#15
MTEB German v1 · Pair Classification · German53#43
MTEB German v1 · Reranking · German46#42
MTEB Europe v1 · Retrieval · multilingual (25 languages)52.5#36
MTEB Europe v1 · Bitext Mining · multilingual (28 languages)84.9#56
MTEB Europe v1 · Classification · multilingual (23 languages)57.3#35
MTEB Europe v1 · Clustering · multilingual (29 languages)41.2#54
MTEB Europe v1 · Instruction Reranking · English-3.8#191
MTEB Europe v1 · Pair Classification · multilingual (11 languages)87.2#39
MTEB Europe v1 · Reranking · multilingual (12 languages)54.7#75
MTEB Europe v1 · Multilabel Classification · multilingual (23 languages)16.5#51
MTEB French v1 · Retrieval · multilingual (2 languages)50#34
MTEB French v1 · Reranking · French77.1#35
MTEB French v1 · Classification · French66.9#33
MTEB French v1 · Summarization · French30.2#75
MTEB French v1 · Pair Classification · French59#81
MTEB Indic v1 · Mean over tasks · multilingual (25 languages)66.6#14
MTEB Indic v1 · Mean over task types · multilingual (25 languages)64.5#16
MTEB Indic v1 · Classification · multilingual (8 languages)66#12
MTEB Indic v1 · Retrieval · multilingual (14 languages)79.4#23
MTEB Indic v1 · Bitext Mining · multilingual (20 languages)73.8#16
MTEB Indic v1 · Reranking · multilingual (2 languages)83.2#60
MTEB Indic v1 · Pair Classification · Hindi69.7#60
MTEB Indic v1 · STS · multilingual (13 languages)45.2#40
MTEB Indic v1 · Clustering · multilingual (21 languages)34.5#52
MTEB Korean v2 · Reranking · Korean48.9#47
MTEB Korean v2 · Classification · Korean60.4#22
MTEB Dutch v1 · Mean over tasks · Dutch53.6#40
MTEB Dutch v1 · Mean over task types · Dutch60.4#37
MTEB Dutch v1 · Classification · Dutch59.7#43
MTEB Dutch v1 · Clustering · Dutch34.2#38
MTEB Dutch v1 · Retrieval · Dutch54.8#49
MTEB Dutch v1 · STS · Dutch77.9#40
MTEB Dutch v1 · Multilabel Classification · Dutch36.2#30
MTEB Dutch v1 · Pair Classification · Dutch74#53
MTEB Dutch v1 · Reranking · Dutch86.1#80
MTEB Polish v1 · Pair Classification · Polish80.6#46
MTEB Polish v1 · Classification · Polish55.4#47
MTEB Polish v1 · STS · Polish66.6#29
MTEB Portuguese v1 · Multilabel Classification · Portuguese19.2#106
MTEB Law v1 · Mean over tasks · multilingual (3 languages)49#52
MTEB Law v1 · Mean over task types · multilingual (3 languages)49#52
MTEB Law v1 · Retrieval · multilingual (3 languages)49#52
MTEB Medical v1 · Mean over tasks · multilingual (10 languages)50.6#40
MTEB Medical v1 · Mean over task types · multilingual (10 languages)51.8#38
MTEB Medical v1 · Retrieval · multilingual (10 languages)52.2#40
MTEB Medical v1 · Clustering · English33.9#145
MTEB Medical v1 · Reranking · Mandarin Chinese69.2#76
FollowIR · Mean over tasks · English-3.8#191
FollowIR · Mean over task types · English-3.8#191
FollowIR · Instruction Reranking · English-3.8#191
MTEB Spanish v1 · Pair Classification · Spanish63.5#68
MTEB Spanish v1 · Reranking · Spanish53.6#45
MTEB Thai v1 · Clustering · Thai40.2#74
MTEB Thai v1 · Pair Classification · Thai68.5#65
MTEB Scandinavian v1 · Clustering · multilingual (2 languages)41#43
MTEB Scandinavian v1 · Classification · multilingual (6 languages)60.8#33
MTEB Scandinavian v1 · Bitext Mining · multilingual (3 languages)62#122
MTEB Russian v1.1 · Mean over tasks · Russian58.2#34
MTEB Russian v1.1 · Mean over task types · Russian57.1#33
MTEB Russian v1.1 · Classification · Russian58.2#56
MTEB Russian v1.1 · STS · Russian71.8#36
MTEB Russian v1.1 · Reranking · Russian62#48
MTEB Russian v1.1 · Clustering · Russian55#42
MTEB Russian v1.1 · Pair Classification · Russian56#79
MTEB Russian v1.1 · Retrieval · Russian61.2#34
MTEB Russian v1.1 · Multilabel Classification · Russian35.2#45
RTEB French beta · Mean over tasks · multilingual (2 languages)40#71
RTEB German beta · Mean over tasks · German45.4#72
RTEB Law beta · Mean over tasks · multilingual (4 languages)38.5#85
MTEB multilingual v2 · Pair Classification · multilingual (24 languages)77.4#63
MTEB multilingual v2 · Retrieval · multilingual (120 languages)53#74
MTEB multilingual v2 · Bitext Mining · multilingual (1026 languages)70#36
MTEB multilingual v2 · Instruction Reranking · English-3.8#191
MTEB multilingual v2 · Multilabel Classification · multilingual (25 languages)20.7#55
MTEB multilingual v2 · Reranking · multilingual (22 languages)59.4#70

FAQ

How much does Bilingual Embedding Base cost?›

There is no per-unit API price: self-host only.

Is Bilingual Embedding Base free to use?›

There is no free API. The weights are open, so you can run it yourself.

How good is Bilingual Embedding Base, and what is it best at?›

#134 of 200 in Embeddings.

Is Bilingual Embedding Base better than USER Base?›

On MTEB Dutch v1 · Retrieval · Dutch, Bilingual Embedding Base scores 54.8 vs 54.9 — about the same.

When was Bilingual Embedding Base released? Is there a newer version?›

Released 2024-06-26. It is the current version in its line.

Is Bilingual Embedding Base open source?›

Yes, the weights are open (Apache-2.0 licence).

Can I run Bilingual Embedding Base locally?›

The weights are open and can be self-hosted; hardware needs are not confirmed yet.

What is Bilingual Embedding Base?›

Bilingual Embedding Base is an open-weights embeddings & retrieval model from Lajavaness, released Jun 2024.

What are the best alternatives to Bilingual Embedding Base?›

EmbeddingGemma 300M (better), Nemotron 3 Embed 8B Legal (open weights).