a

GIST Small Embedding v0

Feb 2024
aGIST Small Embedding v0
Compare in
on
price not verifiedprice
52MTEB English v2
Feb 2024released
384Dimensions
1K tokensMax input
enLanguages

Rankingconfiguration unstated?

Full ranking →
1Multilingual E5 Base332Rubert Tiny232.53Sentence Croissant Alpha v0.332.54Speed Embedding 7B Instruct32.45Bilingual Embedding Small32.3
···
35E5 Mistral 7B Instruct31.136GIST Small Embedding v03137USER Base31

Strong at

B
Embeddings & Retrieval#89 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

Benchmarks

in Embeddings & Retrieval
BEIR · Mean over tasks · English50.4#100
BEIR · Mean over task types · English50.4#100
BEIR · Retrieval · English50.4#100
MTEB Persian v2 · Reranking · Persian31.1#102
JMTEB v2 · Clustering · Japanese18.6#107
JMTEB v2 · STS · Japanese62.8#98
LongEmbed · Mean over tasks · English34.8#102
LongEmbed · Mean over task types · English34.8#102
LongEmbed · Retrieval · English34.8#102
MTEB German v1 · Mean over tasks · German38.7#73
MTEB German v1 · Mean over task types · German37.5#74
MTEB German v1 · Classification · German46.9#125
MTEB German v1 · Pair Classification · German49.3#113
MTEB German v1 · STS · German51.4#80
MTEB German v1 · Clustering · German24.3#93
MTEB German v1 · Retrieval · German34.1#81
MTEB German v1 · Reranking · German19#110
MTEB Europe v1 · Classification · multilingual (23 languages)50.1#92
MTEB Europe v1 · Instruction Reranking · English-2.8#155
MTEB Europe v1 · Multilabel Classification · multilingual (23 languages)12.6#97
MTEB Europe v1 · Pair Classification · multilingual (11 languages)82.9#104
MTEB Europe v1 · Clustering · multilingual (29 languages)35.6#108
MTEB Europe v1 · Retrieval · multilingual (25 languages)39.4#91
MTEB Europe v1 · Reranking · multilingual (12 languages)48.6#124
MTEB Europe v1 · Bitext Mining · multilingual (28 languages)33#136
MTEB French v1 · Mean over tasks · multilingual (2 languages)47.2#64
MTEB French v1 · Mean over task types · multilingual (2 languages)49.5#60
MTEB French v1 · STS · French69.1#70
MTEB French v1 · Retrieval · multilingual (2 languages)33.8#91
MTEB French v1 · Classification · French52.1#92
MTEB French v1 · Clustering · French39.3#69
MTEB French v1 · Reranking · French65.1#94
MTEB French v1 · Pair Classification · French56.2#122
MTEB French v1 · Summarization · French31#36
MTEB Indic v1 · Mean over tasks · multilingual (25 languages)31.6#110
MTEB Indic v1 · Mean over task types · multilingual (25 languages)21.4#111
MTEB Indic v1 · Classification · multilingual (8 languages)42.6#108
MTEB Indic v1 · Bitext Mining · multilingual (20 languages)2.4#142
MTEB Indic v1 · STS · multilingual (13 languages)-1.6#179
MTEB Indic v1 · Reranking · multilingual (2 languages)41.9#151
MTEB Indic v1 · Retrieval · multilingual (14 languages)9.9#130
MTEB Indic v1 · Pair Classification · Hindi51.9#160
MTEB Indic v1 · Clustering · multilingual (21 languages)3#162
MTEB Korean v2 · Classification · Korean22.4#103
MTEB Korean v2 · Reranking · Korean7.6#124
MTEB Dutch v1 · Mean over tasks · Dutch38.4#93
MTEB Dutch v1 · Mean over task types · Dutch46.6#90
MTEB Dutch v1 · Retrieval · Dutch32.6#91
MTEB Dutch v1 · Classification · Dutch46.3#95
MTEB Dutch v1 · Multilabel Classification · Dutch30.5#88
MTEB Dutch v1 · STS · Dutch59.1#90
MTEB Dutch v1 · Clustering · Dutch23.1#85
MTEB Dutch v1 · Reranking · Dutch76.3#147
MTEB Dutch v1 · Pair Classification · Dutch58.5#119
MTEB Polish v1 · Mean over tasks · Polish46.8#63
MTEB Polish v1 · Mean over task types · Polish47.5#62
MTEB Polish v1 · Classification · Polish40.2#116
MTEB Polish v1 · Clustering · Polish28.3#64
MTEB Polish v1 · STS · Polish56.9#73
MTEB Polish v1 · Pair Classification · Polish64.7#104
MTEB Portuguese v1 · Multilabel Classification · Portuguese19.8#86
MTEB Law v1 · Mean over tasks · multilingual (3 languages)39.4#95
MTEB Law v1 · Mean over task types · multilingual (3 languages)39.4#95
MTEB Law v1 · Retrieval · multilingual (3 languages)39.4#95
MTEB Medical v1 · Mean over tasks · multilingual (10 languages)36.7#88
MTEB Medical v1 · Mean over task types · multilingual (10 languages)31.8#85
MTEB Medical v1 · Retrieval · multilingual (10 languages)38.5#88
MTEB Medical v1 · Clustering · English36.9#72
MTEB Medical v1 · Reranking · Mandarin Chinese19.9#144
FollowIR · Mean over tasks · English-2.8#155
FollowIR · Mean over task types · English-2.8#155
FollowIR · Instruction Reranking · English-2.8#155
MTEB Spanish v1 · Clustering · Spanish40.8#78
MTEB Spanish v1 · Pair Classification · Spanish59.4#111
MTEB Spanish v1 · Reranking · Spanish29.8#96
MTEB Spanish v1 · Classification · Spanish76.1#53
MTEB Thai v1 · Pair Classification · Thai51.2#159
MTEB Thai v1 · Clustering · Thai3.8#141
MTEB Scandinavian v1 · Mean over tasks · multilingual (6 languages)43.3#87
MTEB Scandinavian v1 · Mean over task types · multilingual (6 languages)45.3#84
MTEB Scandinavian v1 · Classification · multilingual (6 languages)47.9#119
MTEB Scandinavian v1 · Retrieval · multilingual (3 languages)38.4#91
MTEB Scandinavian v1 · Clustering · multilingual (2 languages)33.1#102
MTEB Scandinavian v1 · Bitext Mining · multilingual (3 languages)61.7#127
MTEB Russian v1.1 · Mean over tasks · Russian26.3#77
MTEB Russian v1.1 · Mean over task types · Russian26.9#76
MTEB Russian v1.1 · Classification · Russian29.5#117
MTEB Russian v1.1 · Clustering · Russian16.5#120
MTEB Russian v1.1 · Reranking · Russian21.9#110
MTEB Russian v1.1 · Multilabel Classification · Russian26.7#107
MTEB Russian v1.1 · STS · Russian41.8#101
MTEB Russian v1.1 · Retrieval · Russian7.3#72
MTEB Russian v1.1 · Pair Classification · Russian44.5#195
RTEB French beta · Mean over tasks · multilingual (2 languages)14.7#153
RTEB German beta · Mean over tasks · German10.8#183
RTEB Law beta · Mean over tasks · multilingual (4 languages)31.7#139
MTEB multilingual v2 · Clustering · multilingual (208 languages)40.5#88
MTEB multilingual v2 · Classification · multilingual (119 languages)47.6#112
MTEB multilingual v2 · Retrieval · multilingual (120 languages)37.2#116
MTEB multilingual v2 · Multilabel Classification · multilingual (25 languages)16.8#99
MTEB multilingual v2 · Bitext Mining · multilingual (1026 languages)23.4#131
MTEB multilingual v2 · Instruction Reranking · English-2.8#155
MTEB multilingual v2 · Reranking · multilingual (22 languages)43.3#125
MTEB multilingual v2 · Pair Classification · multilingual (24 languages)71.5#135

FAQ

How much does GIST Small Embedding v0 cost?›

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

How good is GIST Small Embedding v0, and what is it best at?›

#89 of 200 in Embeddings.

Is GIST Small Embedding v0 better than E5 Mistral 7B Instruct?›

On MTEB French v1 · Summarization · French, GIST Small Embedding v0 scores 31 vs 31.1 — about the same.

When was GIST Small Embedding v0 released? Is there a newer version?›

Released 2024-02-03. It is the current version in its line.

Is GIST Small Embedding v0 open source?›

Yes, the weights are open (MIT licence).

Can I run GIST Small Embedding v0 locally?›

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

What is GIST Small Embedding v0?›

GIST Small Embedding v0 is an open-weights embeddings & retrieval model from avsolatorio, released Feb 2024.

What are the best alternatives to GIST Small Embedding v0?›

Multilingual E5 Base (open weights).