Jina Embedding S En v1

Jul 2023
Jina Embedding S En v1
Compare in
on
self-host onlyprice
41.7MTEB English v2
Jul 2023released
1K tokensMax input
enLanguages

Rankingconfiguration unstated?

Full ranking →
1Ja Embed Sts85.62F2LLM v2 8B85.43F2LLM v2 14B85.14Harrier OSS v1 0.6B84.85F2LLM v2 4B84.7
···
161Mmlw Roberta Base4.1162Jina Embedding S En v14163Jina Embedding B En v14

Strong at

C
Embeddings & Retrieval#141 of 200

Alternatives?

ModelScoreCostPriceWhat changes
BetterEmbeddingGemma 300MunstatedOpen×21.2—$0.002Languages: not verified+1NOpenJa Embed Sts×21.4——Memory (4-bit): 0 GB → 0.2 GBsBetterAll Mpnet Base v2unstatedOpen×16.8—$0.005Max input: 1K tokens → 0K tokens+1sBetterAll MiniLM L6 v2unstatedOpen×16.8—$0.005Max input: 1K tokens → 0K tokenssBetterAll MiniLM L12 v2unstatedOpen×16.7—$0.005Max input: 1K tokens → 0K tokens

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 · English38.9#149
BEIR · Mean over task types · English38.9#149
BEIR · Retrieval · English38.9#149
JMTEB v2 · STS · Japanese4#162
LongEmbed · Mean over tasks · English34.3#108
LongEmbed · Mean over task types · English34.3#108
LongEmbed · Retrieval · English34.3#108
MTEB German v1 · Clustering · German21.9#104
MTEB German v1 · Retrieval · German37#58
MTEB German v1 · STS · German50.3#79
MTEB German v1 · Pair Classification · German50.3#79
MTEB German v1 · Reranking · German27.9#75
MTEB Europe v1 · Bitext Mining · multilingual (28 languages)40.5#115
MTEB Europe v1 · Instruction Reranking · English-3.2#171
MTEB Europe v1 · Pair Classification · multilingual (11 languages)79.6#119
MTEB French v1 · Retrieval · multilingual (2 languages)38.6#65
MTEB French v1 · Reranking · French66.8#80
MTEB French v1 · Clustering · French35.5#90
MTEB French v1 · Summarization · French25.8#151
MTEB French v1 · Pair Classification · French57.6#99
MTEB Indic v1 · Bitext Mining · multilingual (20 languages)6.3#79
MTEB Indic v1 · Pair Classification · Hindi52.4#153
MTEB Indic v1 · STS · multilingual (13 languages)4.7#127
MTEB Korean v2 · Reranking · Korean6.2#126
MTEB Korean v2 · Classification · Korean19.4#135
MTEB Dutch v1 · Mean over tasks · Dutch32.2#111
MTEB Dutch v1 · Mean over task types · Dutch42.6#109
MTEB Dutch v1 · Classification · Dutch40.2#119
MTEB Dutch v1 · Clustering · Dutch12.8#116
MTEB Dutch v1 · Retrieval · Dutch26.2#105
MTEB Dutch v1 · STS · Dutch57.6#97
MTEB Dutch v1 · Multilabel Classification · Dutch24.4#114
MTEB Dutch v1 · Pair Classification · Dutch62.8#86
MTEB Dutch v1 · Reranking · Dutch74.1#161
MTEB Polish v1 · Pair Classification · Polish59.4#136
MTEB Polish v1 · STS · Polish48.9#106
MTEB Portuguese v1 · Multilabel Classification · Portuguese15.8#178
MTEB Law v1 · Mean over tasks · multilingual (3 languages)37.9#101
MTEB Law v1 · Mean over task types · multilingual (3 languages)37.9#101
MTEB Law v1 · Retrieval · multilingual (3 languages)37.9#101
MTEB Medical v1 · Mean over tasks · multilingual (10 languages)28.4#104
MTEB Medical v1 · Mean over task types · multilingual (10 languages)23.2#111
MTEB Medical v1 · Retrieval · multilingual (10 languages)30.2#104
MTEB Medical v1 · Clustering · English29.6#201
MTEB Medical v1 · Reranking · Mandarin Chinese10#183
FollowIR · Mean over tasks · English-3.2#171
FollowIR · Mean over task types · English-3.2#171
FollowIR · Instruction Reranking · English-3.2#171
MTEB Spanish v1 · Pair Classification · Spanish56.5#144
MTEB Spanish v1 · Clustering · Spanish33#116
MTEB Spanish v1 · Reranking · Spanish24.7#110
MTEB Thai v1 · Pair Classification · Thai51.7#135
MTEB Scandinavian v1 · Clustering · multilingual (2 languages)23#148
MTEB Scandinavian v1 · Bitext Mining · multilingual (3 languages)60.4#138
MTEB Russian v1.1 · STS · Russian34.8#117
MTEB Russian v1.1 · Reranking · Russian15.4#131
MTEB Russian v1.1 · Clustering · Russian13.8#137
MTEB Russian v1.1 · Pair Classification · Russian50.6#131
MTEB Russian v1.1 · Retrieval · Russian1.8#86
MTEB Russian v1.1 · Multilabel Classification · Russian24.7#147
RTEB French beta · Mean over tasks · multilingual (2 languages)17.7#138
RTEB German beta · Mean over tasks · German23.6#114
RTEB Law beta · Mean over tasks · multilingual (4 languages)31.6#133
MTEB multilingual v2 · Pair Classification · multilingual (24 languages)71.5#137
MTEB multilingual v2 · Bitext Mining · multilingual (1026 languages)24.8#123
MTEB multilingual v2 · Instruction Reranking · English-3.2#171

FAQ

How much does Jina Embedding S En v1 cost?›

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

Is Jina Embedding S En v1 free to use?›

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

How good is Jina Embedding S En v1, and what is it best at?›

#141 of 200 in Embeddings.

Is Jina Embedding S En v1 better than Mmlw Roberta Base?›

On JMTEB v2 · STS · Japanese, Jina Embedding S En v1 scores 4 vs 4.1 — about the same.

When was Jina Embedding S En v1 released? Is there a newer version?›

Released 2023-07-07. It is the current version in its line.

Is Jina Embedding S En v1 open source?›

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

Can I run Jina Embedding S En v1 locally?›

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

What is Jina Embedding S En v1?›

Jina Embedding S En v1 is an open-weights embeddings & retrieval model from Jina AI, released Jul 2023.

What are the best alternatives to Jina Embedding S En v1?›

EmbeddingGemma 300M (better), Ja Embed Sts (open weights).