t

Gte Large

Jul 2023
tGte Large
Compare in
on
$0.01per 1M tokens
53.3MTEB English v2
Jul 2023released
1,024Dimensions
1K tokensMax input
enLanguages

Rankingconfiguration unstated?

Full ranking →
1Gemini Embedding 2 Preview95.82Jina Embeddings v5 Omni Small862Jina Embeddings v5 Text Small864Jina Embeddings v5 Omni Nano864Jina Embeddings v5 Text Nano86
···
120Dfm Sentence Encoder Medium62.2121Gte Large62.2122Bilingual Embedding Base62

Strong at

B
Embeddings & Retrieval#78 of 200

Alternatives?

ModelScoreCostPriceWhat changes
iCheaperE5 Base v2unstatedOpen+5%-50%$0.005OpenJina Embeddings v5 Text Smallunstated+38%+400%$0.05Languages: not verified+1sCheaperAll MiniLM L12 v2unstatedOpen+2%-50%$0.005Max input: 1K tokens → 0K tokensCheaperEmbeddingGemma 300MunstatedOpensame-80%$0.002Languages: not verifiedtCheaperGte BaseunstatedOpensame-50%$0.005

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 · English52.2#74
BEIR · Mean over task types · English52.2#74
BEIR · Retrieval · English52.2#74
MTEB Persian v2 · Reranking · Persian37.1#83
JMTEB v2 · Clustering · Japanese19.8#95
JMTEB v2 · STS · Japanese62.7#93
LongEmbed · Mean over tasks · English38.7#84
LongEmbed · Mean over task types · English38.7#84
LongEmbed · Retrieval · English38.7#84
MTEB German v1 · Mean over tasks · German43.1#41
MTEB German v1 · Mean over task types · German42.3#42
MTEB German v1 · Clustering · German27.8#59
MTEB German v1 · Retrieval · German42#39
MTEB German v1 · Classification · German50.1#91
MTEB German v1 · STS · German54.7#62
MTEB German v1 · Pair Classification · German50#86
MTEB German v1 · Reranking · German29.3#69
MTEB Europe v1 · Retrieval · multilingual (25 languages)42.1#68
MTEB Europe v1 · Bitext Mining · multilingual (28 languages)41.4#109
MTEB Europe v1 · Classification · multilingual (23 languages)51#73
MTEB Europe v1 · Clustering · multilingual (29 languages)37.2#83
MTEB Europe v1 · Instruction Reranking · English-1.3#96
MTEB Europe v1 · Pair Classification · multilingual (11 languages)83.6#76
MTEB Europe v1 · Reranking · multilingual (12 languages)53.2#79
MTEB Europe v1 · Multilabel Classification · multilingual (23 languages)13.4#85
MTEB French v1 · Mean over tasks · multilingual (2 languages)51.5#38
MTEB French v1 · Mean over task types · multilingual (2 languages)53.1#36
MTEB French v1 · STS · French75.1#36
MTEB French v1 · Retrieval · multilingual (2 languages)40.7#54
MTEB French v1 · Reranking · French71.5#56
MTEB French v1 · Clustering · French43.1#36
MTEB French v1 · Classification · French54.5#76
MTEB French v1 · Summarization · French29.1#120
MTEB French v1 · Pair Classification · French57.5#101
MTEB Indic v1 · Mean over tasks · multilingual (25 languages)31.3#110
MTEB Indic v1 · Mean over task types · multilingual (25 languages)22.3#99
MTEB Indic v1 · Classification · multilingual (8 languages)41.4#122
MTEB Indic v1 · Retrieval · multilingual (14 languages)12.2#112
MTEB Indic v1 · Bitext Mining · multilingual (20 languages)2.2#141
MTEB Indic v1 · Reranking · multilingual (2 languages)45.8#141
MTEB Indic v1 · Pair Classification · Hindi50.4#178
MTEB Indic v1 · STS · multilingual (13 languages)1.5#156
MTEB Indic v1 · Clustering · multilingual (21 languages)2.6#178
MTEB Korean v2 · Reranking · Korean14.2#82
MTEB Korean v2 · Classification · Korean21.5#109
MTEB Dutch v1 · Reranking · Dutch79.3#123
MTEB Polish v1 · Pair Classification · Polish65.8#84
MTEB Polish v1 · Classification · Polish40.5#103
MTEB Polish v1 · STS · Polish59.5#53
MTEB Portuguese v1 · Multilabel Classification · Portuguese22.1#34
MTEB Law v1 · Mean over tasks · multilingual (3 languages)41.2#77
MTEB Law v1 · Mean over task types · multilingual (3 languages)41.2#77
MTEB Law v1 · Retrieval · multilingual (3 languages)41.2#77
MTEB Medical v1 · Mean over tasks · multilingual (10 languages)42.1#51
MTEB Medical v1 · Mean over task types · multilingual (10 languages)34.6#56
MTEB Medical v1 · Retrieval · multilingual (10 languages)45.7#52
MTEB Medical v1 · Clustering · English36.1#96
MTEB Medical v1 · Reranking · Mandarin Chinese22.2#122
FollowIR · Mean over tasks · English-1.3#96
FollowIR · Mean over task types · English-1.3#96
FollowIR · Instruction Reranking · English-1.3#96
MTEB Spanish v1 · Pair Classification · Spanish59.1#116
MTEB Spanish v1 · Clustering · Spanish42.4#61
MTEB Spanish v1 · Reranking · Spanish43.2#65
MTEB Thai v1 · Clustering · Thai3#184
MTEB Thai v1 · Pair Classification · Thai51.5#143
MTEB Scandinavian v1 · Clustering · multilingual (2 languages)34.4#84
MTEB Scandinavian v1 · Classification · multilingual (6 languages)47.6#122
MTEB Scandinavian v1 · Bitext Mining · multilingual (3 languages)62.2#121
MTEB Russian v1.1 · Classification · Russian33.7#100
MTEB Russian v1.1 · STS · Russian48.8#80
MTEB Russian v1.1 · Reranking · Russian33.8#84
MTEB Russian v1.1 · Clustering · Russian22.3#99
MTEB Russian v1.1 · Pair Classification · Russian48.5#144
MTEB Russian v1.1 · Multilabel Classification · Russian27.2#92
RTEB French beta · Mean over tasks · multilingual (2 languages)27.7#100
RTEB German beta · Mean over tasks · German19.8#125
RTEB Law beta · Mean over tasks · multilingual (4 languages)34.3#107
MTEB multilingual v2 · Classification · multilingual (119 languages)47.6#110
MTEB multilingual v2 · Clustering · multilingual (208 languages)41.4#79
MTEB multilingual v2 · Pair Classification · multilingual (24 languages)71.7#119
MTEB multilingual v2 · Retrieval · multilingual (120 languages)38.2#109
MTEB multilingual v2 · Bitext Mining · multilingual (1026 languages)26.2#115
MTEB multilingual v2 · Instruction Reranking · English-1.3#96
MTEB multilingual v2 · Multilabel Classification · multilingual (25 languages)17.9#80
MTEB multilingual v2 · Reranking · multilingual (22 languages)48.9#90

FAQ

How much does Gte Large cost?›

$0.01 per 1M tokens.

Is Gte Large free to use?›

There is no free API; the cheapest paid price is $0.01 per 1M input tokens. The weights are open, so you can run it yourself.

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

#78 of 200 in Embeddings.

Is Gte Large better than Dfm Sentence Encoder Medium?›

On MTEB Scandinavian v1 · Bitext Mining · multilingual (3 languages), Gte Large scores 62.2 vs 62.2 — about the same.

How can I use Gte Large?›

Through the thenlper API.

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

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

Is Gte Large open source?›

Yes, the weights are open (MIT licence).

Can I run Gte Large locally?›

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

What is Gte Large?›

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

What are the best alternatives to Gte Large?›

E5 Base v2 (cheaper), Jina Embeddings v5 Text Small (open weights).