Gte Multilingual Base

Jul 2024
Gte Multilingual Base
Compare in
on
self-host onlyprice
50.9MTEB English v2
Jul 2024released
768Dimensions
8K tokensMax input
en, es, Estonian +69Languages

Rankingconfiguration unstated?

Full ranking →
1Uibk Embedding v191.52GTE ModernColBERT v190.63UltraBERT Embed 150M79.34Voyage Multilingual 279.25Voyage Law 278.8
···
32Jina Embeddings v5 Text Nano63.734Gte Multilingual Base62.135Jasper En Vision Language v160.9

Strong at

B
Embeddings & Retrieval#99 of 200

Alternatives?

ModelScoreCostPriceWhat changes
VBetterVoyage 3 Liteunstated+15%—$0.02Languages: not verifiedDOpenUibk Embedding v1unstated+47%——Max input: 8K tokens → 0K tokens+1BetterJina Embeddings v5 Text SmallunstatedOpen+7%—$0.05Languages: not verified+1VBetterVoyage 3unstated+19%—$0.06Languages: not verifiedVBetterVoyage Multilingual 2unstated+27%—$0.12Languages: not verified

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 · English51.1#94
BEIR · Mean over task types · English51.1#94
BEIR · Retrieval · English51.1#94
BEIR-NL · Mean over tasks · Dutch43.4#7
BEIR-NL · Mean over task types · Dutch43.4#7
BEIR-NL · Retrieval · Dutch43.4#7
MTEB Mandarin Chinese v1 · Retrieval · Mandarin Chinese71.9#37
MTEB Mandarin Chinese v1 · STS · Mandarin Chinese50.7#43
MTEB Mandarin Chinese v1 · Reranking · Mandarin Chinese68.2#21
MTEB Mandarin Chinese v1 · Clustering · Mandarin Chinese47.5#54
MTEB Persian v2 · STS · Persian78.9#13
MTEB Persian v2 · Clustering · Persian57.3#32
MTEB Persian v2 · Bitext Mining · Persian60.9#17
MTEB Persian v2 · Pair Classification · Persian82.6#17
JMTEB v2 · STS · Japanese80.4#36
LongEmbed · Mean over tasks · English62.1#34
LongEmbed · Mean over task types · English62.1#34
LongEmbed · Retrieval · English62.1#34
MTEB German v1 · Clustering · German33.3#30
MTEB German v1 · STS · German72#14
MTEB German v1 · Pair Classification · German52.6#53
MTEB German v1 · Reranking · German49.6#32
MTEB Europe v1 · STS · multilingual (8 languages)73.7#20
MTEB Europe v1 · Bitext Mining · multilingual (28 languages)86.9#45
MTEB Europe v1 · Instruction Reranking · English-0.7#78
MTEB Europe v1 · Pair Classification · multilingual (11 languages)89.8#16
MTEB French v1 · Retrieval · multilingual (2 languages)58.8#20
MTEB French v1 · Reranking · French81.6#19
MTEB French v1 · Clustering · French42.1#48
MTEB French v1 · Summarization · French29.7#94
MTEB French v1 · Pair Classification · French58.8#82
MTEB Indic v1 · Bitext Mining · multilingual (20 languages)68.6#23
MTEB Indic v1 · Pair Classification · Hindi75.8#33
MTEB Indic v1 · STS · multilingual (13 languages)41.4#50
MTEB Korean v2 · STS · Korean80.9#26
MTEB Korean v2 · Reranking · Korean56.4#25
MTEB Korean v2 · Classification · Korean60.5#21
MTEB Dutch v1 · Mean over tasks · Dutch53.6#39
MTEB Dutch v1 · Mean over task types · Dutch60.2#41
MTEB Dutch v1 · Classification · Dutch59.5#44
MTEB Dutch v1 · Clustering · Dutch31.3#49
MTEB Dutch v1 · Retrieval · Dutch56.8#39
MTEB Dutch v1 · STS · Dutch79.4#28
MTEB Dutch v1 · Multilabel Classification · Dutch34.2#55
MTEB Dutch v1 · Pair Classification · Dutch77.8#35
MTEB Dutch v1 · Reranking · Dutch82.4#98
MTEB Polish v1 · Pair Classification · Polish85.5#19
MTEB Polish v1 · STS · Polish68.9#16
MTEB Portuguese v1 · Mean over tasks · Portuguese69.7#5
MTEB Portuguese v1 · Mean over task types · Portuguese63.6#5
MTEB Portuguese v1 · Classification · Portuguese58.3#11
MTEB Portuguese v1 · Retrieval · Portuguese76.9#4
MTEB Portuguese v1 · Multilabel Classification · Portuguese18#141
MTEB Portuguese v1 · STS · Portuguese80.4#9
MTEB Portuguese v1 · Reranking · Portuguese84.2#7
MTEB Law v1 · Mean over tasks · multilingual (3 languages)54.5#39
MTEB Law v1 · Mean over task types · multilingual (3 languages)54.5#39
MTEB Law v1 · Retrieval · multilingual (3 languages)54.5#39
MTEB Medical v1 · Clustering · English35.9#105
MTEB Medical v1 · Reranking · Mandarin Chinese87.4#25
FollowIR · Mean over tasks · English-0.7#78
FollowIR · Mean over task types · English-0.7#78
FollowIR · Instruction Reranking · English-0.7#78
MTEB Spanish v1 · Pair Classification · Spanish69.3#40
MTEB Spanish v1 · Clustering · Spanish45#37
MTEB Spanish v1 · Reranking · Spanish61#26
MTEB Thai v1 · Pair Classification · Thai75.1#41
MTEB Scandinavian v1 · Clustering · multilingual (2 languages)39.6#52
MTEB Scandinavian v1 · Bitext Mining · multilingual (3 languages)68.7#58
VN-MTEB Vietnamese v1 · Mean over tasks · Vietnamese52.4#10
VN-MTEB Vietnamese v1 · Mean over task types · Vietnamese63.7#7
VN-MTEB Vietnamese v1 · Classification · Vietnamese62.7#17
VN-MTEB Vietnamese v1 · STS · Vietnamese81.5#7
VN-MTEB Vietnamese v1 · Retrieval · Vietnamese38.4#11
VN-MTEB Vietnamese v1 · Clustering · Vietnamese50.2#9
VN-MTEB Vietnamese v1 · Reranking · Vietnamese65.1#9
VN-MTEB Vietnamese v1 · Pair Classification · Vietnamese84.5#6
MTEB Russian v1.1 · STS · Russian75.6#8
MTEB Russian v1.1 · Reranking · Russian66.2#27
MTEB Russian v1.1 · Clustering · Russian53.5#48
MTEB Russian v1.1 · Pair Classification · Russian65.8#15
MTEB Russian v1.1 · Multilabel Classification · Russian35#47
RTEB Finnish beta · Mean over tasks · English55.3#54
RTEB French beta · Mean over tasks · multilingual (2 languages)48#49
RTEB German beta · Mean over tasks · German45.7#71
RTEB Health beta · Mean over tasks · multilingual (4 languages)57.6#38
RTEB Law beta · Mean over tasks · multilingual (4 languages)44.8#67
MTEB multilingual v2 · STS · multilingual (35 languages)72.9#41
MTEB multilingual v2 · Pair Classification · multilingual (24 languages)80.5#34
MTEB multilingual v2 · Instruction Reranking · English-0.7#78

FAQ

How much does Gte Multilingual Base cost?›

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

Is Gte Multilingual Base free to use?›

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

How good is Gte Multilingual Base, and what is it best at?›

#99 of 200 in Embeddings.

Is Gte Multilingual Base better than Jina Embeddings v5 Text Nano?›

On LongEmbed · Mean over tasks · English, Gte Multilingual Base scores 62.1 vs 63.7 — lower.

When was Gte Multilingual Base released? Is there a newer version?›

Released 2024-07-20. It is the current version in its line.

Is Gte Multilingual Base open source?›

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

Can I run Gte Multilingual Base locally?›

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

What is Gte Multilingual Base?›

Gte Multilingual Base is an open-weights embeddings & retrieval model from Alibaba (Qwen), released Jul 2024.

What are the best alternatives to Gte Multilingual Base?›

Voyage 3 Lite (better), Uibk Embedding v1 (open weights).