t

Gte Base

Jul 2023
tGte Base
Compare in
on
$0.005per 1M tokens
51.9MTEB English v2
Jul 2023released
768Dimensions
1K tokensMax input
enLanguages

Rankingconfiguration unstated?

Full ranking →
1Jina Embeddings v5 Text Nano78.12STS Multilingual Mpnet Base v276.63Bilingual Embedding Large75.94F2LLM v2 14B75.25Jina Embeddings v374.7
···
80Gte Small50.281Gte Base50.182Bge Small En v1.549.9

Strong at

B
Embeddings & Retrieval#91 of 200

Alternatives?

ModelScoreCostPriceWhat changes
iBetterMultilingual E5 Large InstructunstatedOpen+47%+100%$0.01Memory (4-bit): 0.1 GB → 0.3 GBOpenJina Embeddings v5 Text Nanounstated+56%+300%$0.02Languages: not verifiediBetterMultilingual E5 LargeunstatedOpen+43%+100%$0.01Memory (4-bit): 0.1 GB → 0.3 GBiBetterE5 Large v2unstatedOpen+12%+100%$0.01Memory (4-bit): 0.1 GB → 0.2 GBtBetterGte LargeunstatedOpen+9%+100%$0.01Memory (4-bit): 0.1 GB → 0.2 GB

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

Benchmarks

in Embeddings & Retrieval
BEIR · Mean over tasks · English51.1#92
BEIR · Mean over task types · English51.1#92
BEIR · Retrieval · English51.1#92
MTEB Persian v2 · Reranking · Persian35#92
JMTEB v2 · Clustering · Japanese20#92
JMTEB v2 · STS · Japanese62.4#97
LongEmbed · Mean over tasks · English34.8#101
LongEmbed · Mean over task types · English34.8#101
LongEmbed · Retrieval · English34.8#101
MTEB German v1 · Mean over tasks · German40.9#51
MTEB German v1 · Mean over task types · German39.6#52
MTEB German v1 · Clustering · German25.5#75
MTEB German v1 · Retrieval · German39.1#49
MTEB German v1 · Classification · German49.1#98
MTEB German v1 · STS · German50.1#81
MTEB German v1 · Pair Classification · German49.5#101
MTEB German v1 · Reranking · German24.3#87
MTEB Europe v1 · Retrieval · multilingual (25 languages)38.9#83
MTEB Europe v1 · Bitext Mining · multilingual (28 languages)36.8#124
MTEB Europe v1 · Classification · multilingual (23 languages)50.8#79
MTEB Europe v1 · Clustering · multilingual (29 languages)37.4#80
MTEB Europe v1 · Instruction Reranking · English-2.4#144
MTEB Europe v1 · Pair Classification · multilingual (11 languages)83.4#80
MTEB Europe v1 · Reranking · multilingual (12 languages)51.6#92
MTEB Europe v1 · Multilabel Classification · multilingual (23 languages)12.4#102
MTEB French v1 · Mean over tasks · multilingual (2 languages)49.6#48
MTEB French v1 · Mean over task types · multilingual (2 languages)51.7#44
MTEB French v1 · STS · French73.4#44
MTEB French v1 · Retrieval · multilingual (2 languages)36.5#74
MTEB French v1 · Reranking · French71.6#55
MTEB French v1 · Clustering · French41.3#54
MTEB French v1 · Classification · French53.2#83
MTEB French v1 · Summarization · French29.4#111
MTEB French v1 · Pair Classification · French56.5#117
MTEB Indic v1 · Mean over tasks · multilingual (25 languages)32#98
MTEB Indic v1 · Mean over task types · multilingual (25 languages)23.7#84
MTEB Indic v1 · Classification · multilingual (8 languages)41.7#117
MTEB Indic v1 · Retrieval · multilingual (14 languages)12.1#113
MTEB Indic v1 · Bitext Mining · multilingual (20 languages)2.4#136
MTEB Indic v1 · Reranking · multilingual (2 languages)48.7#128
MTEB Indic v1 · Pair Classification · Hindi52.9#140
MTEB Indic v1 · STS · multilingual (13 languages)5.7#124
MTEB Indic v1 · Clustering · multilingual (21 languages)2.1#186
MTEB Korean v2 · Reranking · Korean14.3#81
MTEB Korean v2 · Classification · Korean21.6#103
MTEB Dutch v1 · Reranking · Dutch79.3#122
MTEB Polish v1 · Pair Classification · Polish63.8#103
MTEB Polish v1 · Classification · Polish42#85
MTEB Polish v1 · STS · Polish58.8#54
MTEB Portuguese v1 · Multilabel Classification · Portuguese18.5#132
MTEB Law v1 · Mean over tasks · multilingual (3 languages)40#84
MTEB Law v1 · Mean over task types · multilingual (3 languages)40#84
MTEB Law v1 · Retrieval · multilingual (3 languages)40#84
MTEB Medical v1 · Mean over tasks · multilingual (10 languages)40.4#62
MTEB Medical v1 · Mean over task types · multilingual (10 languages)33.6#71
MTEB Medical v1 · Retrieval · multilingual (10 languages)43.6#64
MTEB Medical v1 · Clustering · English35.7#113
MTEB Medical v1 · Reranking · Mandarin Chinese21.6#130
FollowIR · Mean over tasks · English-2.4#144
FollowIR · Mean over task types · English-2.4#144
FollowIR · Instruction Reranking · English-2.4#144
MTEB Spanish v1 · Pair Classification · Spanish58.6#125
MTEB Spanish v1 · Clustering · Spanish41.4#71
MTEB Spanish v1 · Reranking · Spanish35.6#86
MTEB Thai v1 · Clustering · Thai3.1#180
MTEB Thai v1 · Pair Classification · Thai51.7#134
MTEB Scandinavian v1 · Clustering · multilingual (2 languages)33.9#88
MTEB Scandinavian v1 · Classification · multilingual (6 languages)47.6#123
MTEB Scandinavian v1 · Bitext Mining · multilingual (3 languages)62.4#115
MTEB Russian v1.1 · Classification · Russian31.1#109
MTEB Russian v1.1 · STS · Russian44.9#90
MTEB Russian v1.1 · Reranking · Russian28.9#92
MTEB Russian v1.1 · Clustering · Russian17#114
MTEB Russian v1.1 · Pair Classification · Russian46.9#168
MTEB Russian v1.1 · Multilabel Classification · Russian26.2#113
RTEB French beta · Mean over tasks · multilingual (2 languages)23.9#114
RTEB German beta · Mean over tasks · German15.7#146
RTEB Law beta · Mean over tasks · multilingual (4 languages)32.4#126
MTEB multilingual v2 · Classification · multilingual (119 languages)47.2#116
MTEB multilingual v2 · Clustering · multilingual (208 languages)41.5#75
MTEB multilingual v2 · Pair Classification · multilingual (24 languages)71.4#142
MTEB multilingual v2 · Retrieval · multilingual (120 languages)35.9#124
MTEB multilingual v2 · Bitext Mining · multilingual (1026 languages)25.3#119
MTEB multilingual v2 · Instruction Reranking · English-2.4#144
MTEB multilingual v2 · Multilabel Classification · multilingual (25 languages)16.1#113
MTEB multilingual v2 · Reranking · multilingual (22 languages)46.9#103

FAQ

How much does Gte Base cost?›

$0.005 per 1M tokens.

Is Gte Base 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 Gte Base, and what is it best at?›

#91 of 200 in Embeddings.

Is Gte Base better than Gte Small?›

On MTEB German v1 · STS · German, Gte Base scores 50.1 vs 50.2 — about the same.

How can I use Gte Base?›

Through the thenlper API.

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

Released 2023-07-27. It is the current version in its line.

Is Gte Base open source?›

Yes, the weights are open (MIT licence).

Can I run Gte Base locally?›

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

What is Gte Base?›

Gte Base is an open-weights embeddings & retrieval model from thenlper, released Jul 2023.

What are the best alternatives to Gte Base?›

Multilingual E5 Large Instruct (better), Jina Embeddings v5 Text Nano (open weights).