Jina Embeddings v2 Small En

Sep 2023
Jina Embeddings v2 Small En
Compare in
on
self-host onlyprice
26.5MTEB English v2
Sep 2023released
512Dimensions
8K tokensMax input
enLanguages

Rankingconfiguration unstated?

Full ranking →
1Qwen Indic v194.92FlowVec v192.43F2LLM v2 14B91.84F2LLM v2 8B90.95F2LLM v2 4B89.1
···
145Sbert Large Nlu Ru2.5146Jina Embeddings v2 Small En2.4147Ternary Weight Embedding2.4

Strong at

C
Embeddings & Retrieval#170 of 200

Alternatives?

ModelScoreCostPriceWhat changes
iBetterE5 Base v2unstatedOpen×9.9—$0.005Max input: 8K tokens → 1K tokens+1LOpenQwen Indic v1×39.7——Memory (4-bit): 0 GB → 4.5 GBBetterBge Base En v1.5unstatedOpen×7—$0.005Max input: 8K tokens → 1K tokens+1sBetterAll MiniLM L12 v2unstatedOpen×5.8—$0.005Max input: 8K tokens → 0K tokenssBetterAll Mpnet Base v2unstatedOpen×5.4—$0.005Max input: 8K tokens → 0K tokens+1

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 · English45.1#130
BEIR · Mean over task types · English45.1#130
BEIR · Retrieval · English45.1#130
JMTEB v2 · Clustering · Japanese9.6#153
JMTEB v2 · STS · Japanese53.3#132
LongEmbed · Mean over tasks · English5.5#169
LongEmbed · Mean over task types · English5.5#169
LongEmbed · Retrieval · English5.5#169
MTEB German v1 · Classification · German43.8#138
MTEB Europe v1 · Retrieval · multilingual (25 languages)11.1#133
MTEB Europe v1 · Bitext Mining · multilingual (28 languages)15.7#173
MTEB Europe v1 · Classification · multilingual (23 languages)43.8#124
MTEB Europe v1 · Clustering · multilingual (29 languages)20.3#165
MTEB Europe v1 · Instruction Reranking · English-0.7#80
MTEB Europe v1 · Pair Classification · multilingual (11 languages)74.9#134
MTEB Europe v1 · Reranking · multilingual (12 languages)26.8#179
MTEB Europe v1 · Multilabel Classification · multilingual (23 languages)2.4#175
MTEB French v1 · Pair Classification · French49.9#180
MTEB Indic v1 · Retrieval · multilingual (14 languages)2.4#146
MTEB Indic v1 · Bitext Mining · multilingual (20 languages)1.2#149
MTEB Indic v1 · Reranking · multilingual (2 languages)35#172
MTEB Indic v1 · Pair Classification · Hindi51.5#164
MTEB Indic v1 · STS · multilingual (13 languages)6.3#122
MTEB Indic v1 · Clustering · multilingual (21 languages)2.5#182
MTEB Dutch v1 · Reranking · Dutch42.5#205
MTEB Portuguese v1 · Multilabel Classification · Portuguese18#142
MTEB Law v1 · Mean over tasks · multilingual (3 languages)16#154
MTEB Law v1 · Mean over task types · multilingual (3 languages)16#154
MTEB Law v1 · Retrieval · multilingual (3 languages)16#154
MTEB Medical v1 · Mean over tasks · multilingual (10 languages)21#122
MTEB Medical v1 · Mean over task types · multilingual (10 languages)18.4#123
MTEB Medical v1 · Retrieval · multilingual (10 languages)21.5#123
MTEB Medical v1 · Clustering · English24.1#219
MTEB Medical v1 · Reranking · Mandarin Chinese9.4#188
FollowIR · Mean over tasks · English-0.7#80
FollowIR · Mean over task types · English-0.7#80
FollowIR · Instruction Reranking · English-0.7#80
MTEB Spanish v1 · Pair Classification · Spanish52.3#171
MTEB Thai v1 · Clustering · Thai2.4#186
MTEB Thai v1 · Pair Classification · Thai51.3#153
MTEB Scandinavian v1 · Clustering · multilingual (2 languages)18#168
MTEB Scandinavian v1 · Bitext Mining · multilingual (3 languages)49.4#187
MTEB Russian v1.1 · Pair Classification · Russian47.9#153
RTEB Finnish beta · Mean over tasks · English45.8#75
RTEB French beta · Mean over tasks · multilingual (2 languages)8.3#164
RTEB German beta · Mean over tasks · German2.9#209
RTEB Health beta · Mean over tasks · multilingual (4 languages)32.5#75
RTEB Law beta · Mean over tasks · multilingual (4 languages)21.6#189
MTEB multilingual v2 · Classification · multilingual (119 languages)43.8#142
MTEB multilingual v2 · Clustering · multilingual (208 languages)27.3#155
MTEB multilingual v2 · Pair Classification · multilingual (24 languages)70.8#156
MTEB multilingual v2 · Retrieval · multilingual (120 languages)13.5#166
MTEB multilingual v2 · Bitext Mining · multilingual (1026 languages)12.6#173
MTEB multilingual v2 · Instruction Reranking · English-0.7#80
MTEB multilingual v2 · Multilabel Classification · multilingual (25 languages)11.9#170
MTEB multilingual v2 · Reranking · multilingual (22 languages)27.6#178

FAQ

How much does Jina Embeddings v2 Small En cost?›

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

Is Jina Embeddings v2 Small En free to use?›

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

How good is Jina Embeddings v2 Small En, and what is it best at?›

#170 of 200 in Embeddings.

Is Jina Embeddings v2 Small En better than Sbert Large Nlu Ru?›

On MTEB Indic v1 · Retrieval · multilingual (14 languages), Jina Embeddings v2 Small En scores 2.4 vs 2.5 — about the same.

When was Jina Embeddings v2 Small En released? Is there a newer version?›

Released 2023-09-27. It is the current version in its line.

Is Jina Embeddings v2 Small En open source?›

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

Can I run Jina Embeddings v2 Small En locally?›

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

What is Jina Embeddings v2 Small En?›

Jina Embeddings v2 Small En is an open-weights embeddings & retrieval model from Jina AI, released Sep 2023.

What are the best alternatives to Jina Embeddings v2 Small En?›

E5 Base v2 (better), Qwen Indic v1 (open weights).