c

Rubert Tiny

May 2021
cRubert Tiny
Compare in
on
price not verifiedprice
6.3MTEB English v2
May 2021released
312Dimensions
1K tokensMax input
en, ruLanguages

Rankingconfiguration unstated?

Full ranking →
1Gemini Embedding 001832Jina Embeddings v5 Omni Small82.53Jina Embeddings v5 Text Small82.54Jina Embeddings v5 Omni Nano81.74Jina Embeddings v5 Text Nano81.7
···
70Rubert Base Cased Sentence49.171Rubert Tiny48.972Arabert All Nli Triplet Matryoshka48.6

Strong at

C
Embeddings & Retrieval#192 of 200

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
49505152Jul 21Oct 21Release dateMTEB Spanish · STSRubert Tiny2
49505152Jul 21Oct 21Release dateMTEB Spanish · STSRubert Tiny2

Benchmarks

in Embeddings & Retrieval
BEIR · Mean over tasks · English8.4#192
BEIR · Mean over task types · English8.4#192
BEIR · Retrieval · English8.4#192
MTEB Persian v2 · Reranking · Persian18.6#142
JMTEB v2 · Clustering · Japanese11#141
JMTEB v2 · STS · Japanese30.2#149
LongEmbed · Mean over tasks · English7.6#165
LongEmbed · Mean over task types · English7.6#165
LongEmbed · Retrieval · English7.6#165
MTEB German v1 · Mean over tasks · German27.1#88
MTEB German v1 · Mean over task types · German25.4#91
MTEB German v1 · Clustering · German10.5#142
MTEB German v1 · Retrieval · German6.3#99
MTEB German v1 · Classification · German45.6#131
MTEB German v1 · STS · German35.9#120
MTEB German v1 · Pair Classification · German47.4#163
MTEB German v1 · Reranking · German6.4#139
MTEB Europe v1 · Retrieval · multilingual (25 languages)13.6#130
MTEB Europe v1 · STS · multilingual (8 languages)45.7#78
MTEB Europe v1 · Bitext Mining · multilingual (28 languages)18.1#166
MTEB Europe v1 · Classification · multilingual (23 languages)45.3#114
MTEB Europe v1 · Clustering · multilingual (29 languages)22.3#159
MTEB Europe v1 · Instruction Reranking · English-0.9#85
MTEB Europe v1 · Reranking · multilingual (12 languages)32.2#170
MTEB Europe v1 · Multilabel Classification · multilingual (23 languages)6#149
MTEB French v1 · Mean over tasks · multilingual (2 languages)31.3#90
MTEB French v1 · Mean over task types · multilingual (2 languages)34.8#91
MTEB French v1 · STS · French51.9#102
MTEB French v1 · Retrieval · multilingual (2 languages)6.3#124
MTEB French v1 · Reranking · French37.1#123
MTEB French v1 · Clustering · French26#109
MTEB French v1 · Classification · French43.6#113
MTEB French v1 · Summarization · French28.6#129
MTEB French v1 · Pair Classification · French50.1#178
MTEB Indic v1 · Classification · multilingual (8 languages)41.2#124
MTEB Indic v1 · Retrieval · multilingual (14 languages)2.8#144
MTEB Indic v1 · Bitext Mining · multilingual (20 languages)4.6#97
MTEB Indic v1 · Reranking · multilingual (2 languages)32.7#184
MTEB Indic v1 · STS · multilingual (13 languages)1#159
MTEB Indic v1 · Clustering · multilingual (21 languages)2.9#167
MTEB Korean v2 · STS · Korean2.3#83
MTEB Korean v2 · Reranking · Korean4.9#141
MTEB Korean v2 · Classification · Korean19.6#131
MTEB Dutch v1 · Mean over tasks · Dutch25.7#119
MTEB Dutch v1 · Mean over task types · Dutch36#123
MTEB Dutch v1 · Classification · Dutch42.3#114
MTEB Dutch v1 · Clustering · Dutch11.4#120
MTEB Dutch v1 · Retrieval · Dutch6.5#124
MTEB Dutch v1 · STS · Dutch49.2#126
MTEB Dutch v1 · Multilabel Classification · Dutch22.4#119
MTEB Dutch v1 · Pair Classification · Dutch64.6#74
MTEB Dutch v1 · Reranking · Dutch55.9#194
MTEB Polish v1 · Pair Classification · Polish54.7#145
MTEB Polish v1 · Classification · Polish39.8#114
MTEB Polish v1 · STS · Polish38.7#116
MTEB Portuguese v1 · Multilabel Classification · Portuguese16.5#173
MTEB Law v1 · Mean over tasks · multilingual (3 languages)20#151
MTEB Law v1 · Mean over task types · multilingual (3 languages)20#151
MTEB Law v1 · Retrieval · multilingual (3 languages)20#151
MTEB Medical v1 · Mean over tasks · multilingual (10 languages)9.9#132
MTEB Medical v1 · Mean over task types · multilingual (10 languages)13.8#130
MTEB Medical v1 · Retrieval · multilingual (10 languages)6.5#134
MTEB Medical v1 · Clustering · English25.6#213
MTEB Medical v1 · Reranking · Mandarin Chinese9.1#190
FollowIR · Mean over tasks · English-0.9#85
FollowIR · Mean over task types · English-0.9#85
FollowIR · Instruction Reranking · English-0.9#85
MTEB Spanish v1 · STS · multilingual (2 languages)48.9#71
MTEB Spanish v1 · Clustering · Spanish30.8#120
MTEB Spanish v1 · Reranking · Spanish6.6#144
MTEB Thai v1 · Clustering · Thai4.1#129
MTEB Scandinavian v1 · Clustering · multilingual (2 languages)20.9#150
MTEB Scandinavian v1 · Classification · multilingual (6 languages)46.6#134
MTEB Scandinavian v1 · Bitext Mining · multilingual (3 languages)54.4#169
MTEB Russian v1.1 · Mean over tasks · Russian35.2#58
MTEB Russian v1.1 · Mean over task types · Russian33.2#60
MTEB Russian v1.1 · Classification · Russian44.6#87
MTEB Russian v1.1 · STS · Russian53.1#77
MTEB Russian v1.1 · Reranking · Russian21.3#116
MTEB Russian v1.1 · Clustering · Russian30.8#90
MTEB Russian v1.1 · Pair Classification · Russian52.9#109
MTEB Russian v1.1 · Retrieval · Russian2.1#85
MTEB Russian v1.1 · Multilabel Classification · Russian28#87
RTEB French beta · Mean over tasks · multilingual (2 languages)0.1#211
RTEB German beta · Mean over tasks · German5.1#195
RTEB Law beta · Mean over tasks · multilingual (4 languages)16.9#197
MTEB multilingual v2 · Classification · multilingual (119 languages)43.8#141
MTEB multilingual v2 · Clustering · multilingual (208 languages)28.7#152
MTEB multilingual v2 · STS · multilingual (35 languages)40.4#110
MTEB multilingual v2 · Retrieval · multilingual (120 languages)12.1#170
MTEB multilingual v2 · Bitext Mining · multilingual (1026 languages)17.1#160
MTEB multilingual v2 · Instruction Reranking · English-0.9#85
MTEB multilingual v2 · Multilabel Classification · multilingual (25 languages)13.9#150
MTEB multilingual v2 · Reranking · multilingual (22 languages)33.2#167

FAQ

How much does Rubert Tiny cost?›

There is no per-unit API price: price not verified.

How good is Rubert Tiny, and what is it best at?›

#192 of 200 in Embeddings.

Is Rubert Tiny better than Rubert Base Cased Sentence?›

On MTEB Spanish v1 · STS · multilingual (2 languages), Rubert Tiny scores 48.9 vs 49.1 — about the same.

When was Rubert Tiny released? Is there a newer version?›

Released 2021-05-24. It is the current version in its line.

Is Rubert Tiny open source?›

Yes, the weights are open (MIT licence).

Can I run Rubert Tiny locally?›

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

What is Rubert Tiny?›

Rubert Tiny is an open-weights embeddings & retrieval model from cointegrated, released May 2021.

What are the best alternatives to Rubert Tiny?›

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