i

E5 Base v2

Feb 2024
iE5 Base v2
Compare in
on
$0.005per 1M tokens
49.7MTEB English v2
Feb 2024released
768Dimensions
1K tokensMax input
enLanguages

Rankingconfiguration unstated?

Full ranking →
1Giga Embeddings Instruct 3B 082668.32Giga Embeddings Instruct 10B A1.8B 0826683FRIDA67.54Giga Embeddings Instruct67.55Qwen 3 Embedding 8B66.7
···
102Nomic Embed Text v1 Unsupervised19.2103E5 Base v219.2104Mxbai Embed Large v119.2

Strong at

C
Embeddings & Retrieval#108 of 200

Alternatives?

ModelScoreCostPriceWhat changes
CheaperEmbeddingGemma 300MunstatedOpen×3.1-60%$0.002Languages: not verified+1aOpenGiga Embeddings Instruct 3B 0826unstated×3.6——Memory (4-bit): 0.1 GB → 1.9 GBBetterQwen 3 Embedding 8BunstatedOpen×3.5+100%$0.01Languages: not verified+1iBetterMultilingual E5 Large InstructunstatedOpen×3.3+100%$0.01Memory (4-bit): 0.1 GB → 0.3 GBBetterQwen 3 Embedding 0.6BunstatedOpen×3.1+100%$0.01Languages: not verified+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
LicenceMITfree for commercial use

History

2 versions
14161820Jan 23Apr 23Jul 23Oct 23Jan 24Release dateMTEB Russian · ClusteringE5 · DecE5 · Feb
14161820Jan 23Jul 23Jan 24Release dateMTEB Russian · ClusteringE5 · Dec

Benchmarks

in Embeddings & Retrieval
BEIR · Mean over tasks · English50.3#99
BEIR · Mean over task types · English50.3#99
BEIR · Retrieval · English50.3#99
ChemTEB · Mean over tasks · multilingual (13 languages)68.3#38
ChemTEB · Mean over task types · multilingual (13 languages)48.1#35
ChemTEB · Classification · English79.8#37
ChemTEB · Retrieval · English72.3#23
ChemTEB · Pair Classification · multilingual (13 languages)55#34
ChemTEB · Clustering · English33#37
ChemTEB · Bitext Mining · English0.1#34
MTEB Persian v2 · Reranking · Persian35.1#91
JMTEB v2 · Clustering · Japanese19.9#94
JMTEB v2 · STS · Japanese65.9#79
LongEmbed · Mean over tasks · English41.1#65
LongEmbed · Mean over task types · English41.1#65
LongEmbed · Retrieval · English41.1#65
MTEB German v1 · Mean over tasks · German42.4#47
MTEB German v1 · Mean over task types · German40.7#48
MTEB German v1 · Clustering · German27.1#63
MTEB German v1 · Retrieval · German39.7#47
MTEB German v1 · Classification · German52.5#80
MTEB German v1 · STS · German50.6#78
MTEB German v1 · Pair Classification · German48.4#150
MTEB German v1 · Reranking · German25.6#82
MTEB Europe v1 · Mean over tasks · multilingual (29 languages)49.4#36
MTEB Europe v1 · Mean over task types · multilingual (29 languages)43.3#38
MTEB Europe v1 · Retrieval · multilingual (25 languages)44.9#49
MTEB Europe v1 · STS · multilingual (8 languages)67.8#45
MTEB Europe v1 · Bitext Mining · multilingual (28 languages)45.9#102
MTEB Europe v1 · Classification · multilingual (23 languages)52#61
MTEB Europe v1 · Clustering · multilingual (29 languages)36.5#92
MTEB Europe v1 · Instruction Reranking · English-3.9#192
MTEB Europe v1 · Pair Classification · multilingual (11 languages)84.4#66
MTEB Europe v1 · Reranking · multilingual (12 languages)51.3#96
MTEB Europe v1 · Multilabel Classification · multilingual (23 languages)11.3#114
MTEB French v1 · Mean over tasks · multilingual (2 languages)51.1#39
MTEB French v1 · Mean over task types · multilingual (2 languages)52.6#38
MTEB French v1 · STS · French73.2#46
MTEB French v1 · Retrieval · multilingual (2 languages)40#59
MTEB French v1 · Reranking · French70.7#57
MTEB French v1 · Clustering · French42.6#41
MTEB French v1 · Classification · French55.5#70
MTEB French v1 · Summarization · French31.9#9
MTEB French v1 · Pair Classification · French54.3#159
MTEB Indic v1 · Mean over tasks · multilingual (25 languages)36.3#62
MTEB Indic v1 · Mean over task types · multilingual (25 languages)26.9#61
MTEB Indic v1 · Classification · multilingual (8 languages)46.2#66
MTEB Indic v1 · Retrieval · multilingual (14 languages)23.7#75
MTEB Indic v1 · Bitext Mining · multilingual (20 languages)6.5#75
MTEB Indic v1 · Reranking · multilingual (2 languages)54.4#117
MTEB Indic v1 · Pair Classification · Hindi54.6#118
MTEB Indic v1 · STS · multilingual (13 languages)-1.3#174
MTEB Indic v1 · Clustering · multilingual (21 languages)4.1#118
MTEB Korean v2 · STS · Korean40.1#59
MTEB Korean v2 · Reranking · Korean9.7#108
MTEB Korean v2 · Classification · Korean22.9#84
MTEB Dutch v1 · Mean over tasks · Dutch42.2#73
MTEB Dutch v1 · Mean over task types · Dutch49.9#73
MTEB Dutch v1 · Classification · Dutch49.2#80
MTEB Dutch v1 · Clustering · Dutch23.6#79
MTEB Dutch v1 · Retrieval · Dutch40.5#69
MTEB Dutch v1 · STS · Dutch64.6#75
MTEB Dutch v1 · Multilabel Classification · Dutch31.5#73
MTEB Dutch v1 · Pair Classification · Dutch59.5#105
MTEB Dutch v1 · Reranking · Dutch80.2#116
MTEB Polish v1 · Pair Classification · Polish69.3#73
MTEB Polish v1 · Classification · Polish42.8#78
MTEB Polish v1 · STS · Polish58.4#57
MTEB Portuguese v1 · Multilabel Classification · Portuguese18.6#127
MTEB Law v1 · Mean over tasks · multilingual (3 languages)39.5#90
MTEB Law v1 · Mean over task types · multilingual (3 languages)39.5#90
MTEB Law v1 · Retrieval · multilingual (3 languages)39.5#90
MTEB Medical v1 · Mean over tasks · multilingual (10 languages)40.1#64
MTEB Medical v1 · Mean over task types · multilingual (10 languages)33.7#70
MTEB Medical v1 · Retrieval · multilingual (10 languages)43.2#66
MTEB Medical v1 · Clustering · English34.4#138
MTEB Medical v1 · Reranking · Mandarin Chinese23.5#116
FollowIR · Mean over tasks · English-3.9#192
FollowIR · Mean over task types · English-3.9#192
FollowIR · Instruction Reranking · English-3.9#192
MTEB Spanish v1 · Pair Classification · Spanish59.1#117
MTEB Spanish v1 · STS · multilingual (2 languages)68.9#42
MTEB Spanish v1 · Clustering · Spanish42.4#62
MTEB Spanish v1 · Reranking · Spanish38.5#77
MTEB Thai v1 · Clustering · Thai3.6#146
MTEB Thai v1 · Pair Classification · Thai51.4#151
MTEB Scandinavian v1 · Clustering · multilingual (2 languages)32.7#101
MTEB Scandinavian v1 · Classification · multilingual (6 languages)49.9#75
MTEB Scandinavian v1 · Bitext Mining · multilingual (3 languages)65.6#85
MTEB Russian v1.1 · Mean over tasks · Russian31.6#63
MTEB Russian v1.1 · Mean over task types · Russian31.7#63
MTEB Russian v1.1 · Classification · Russian36#92
MTEB Russian v1.1 · STS · Russian47#84
MTEB Russian v1.1 · Reranking · Russian30.7#90
MTEB Russian v1.1 · Clustering · Russian19.2#103
MTEB Russian v1.1 · Pair Classification · Russian49.1#137
MTEB Russian v1.1 · Retrieval · Russian14.1#60
MTEB Russian v1.1 · Multilabel Classification · Russian26.1#114
RTEB Code beta · Mean over tasks · multilingual (6 languages)47#4
RTEB English beta · Mean over tasks · multilingual (5 languages)46.7#4
RTEB Finnish beta · Mean over tasks · English54#58
RTEB French beta · Mean over tasks · multilingual (2 languages)25.4#111
RTEB German beta · Mean over tasks · German22.3#117
RTEB Health beta · Mean over tasks · multilingual (4 languages)41.5#65
RTEB Law beta · Mean over tasks · multilingual (4 languages)32#129
MTEB multilingual v2 · Mean over tasks · multilingual (1037 languages)46#64
MTEB multilingual v2 · Mean over task types · multilingual (1037 languages)39.3#65
MTEB multilingual v2 · Classification · multilingual (119 languages)49.5#88
MTEB multilingual v2 · Clustering · multilingual (208 languages)40.1#99
MTEB multilingual v2 · STS · multilingual (35 languages)60.7#74
MTEB multilingual v2 · Pair Classification · multilingual (24 languages)72.6#104
MTEB multilingual v2 · Retrieval · multilingual (120 languages)40.5#90
MTEB multilingual v2 · Bitext Mining · multilingual (1026 languages)31#97
MTEB multilingual v2 · Instruction Reranking · English-3.9#192
MTEB multilingual v2 · Multilabel Classification · multilingual (25 languages)16.1#115
MTEB multilingual v2 · Reranking · multilingual (22 languages)47.5#100

FAQ

How much does E5 Base v2 cost?›

$0.005 per 1M tokens.

Is E5 Base v2 free to use?›

There is no free API; the cheapest paid price is $0.005 per 1M input tokens. The weights are open, so you can run it yourself.

How good is E5 Base v2, and what is it best at?›

#108 of 200 in Embeddings.

Is E5 Base v2 better than Nomic Embed Text v1 Unsupervised?›

On MTEB Russian v1.1 · Clustering · Russian, E5 Base v2 scores 19.2 vs 19.2 — about the same.

How can I use E5 Base v2?›

Through the intfloat API.

When was E5 Base v2 released? Is there a newer version?›

Released 2024-02-08. It is the current version in its line.

Is E5 Base v2 open source?›

Yes, the weights are open (MIT licence).

Can I run E5 Base v2 locally?›

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

What is E5 Base v2?›

E5 Base v2 is an open-weights embeddings & retrieval model from intfloat, released Feb 2024.

What are the best alternatives to E5 Base v2?›

EmbeddingGemma 300M (cheaper), Giga Embeddings Instruct 3B 0826 (open weights).