a

GIST Embedding v0

Jan 2024
aGIST Embedding v0
Compare in
on
price not verifiedprice
53.6MTEB English v2
Jan 2024released
768Dimensions
1K tokensMax input
enLanguages

Rankingconfiguration unstated?

Full ranking →
1Ingot 8B R393.82Conan Embedding v293.53QZhou Embedding92.44Voyage Large 2 Instruct91.35Jasper Token Compression 600M90.2
···
47EmbeddingGemma 286.448GIST Embedding v086.349KaLM Embedding Multilingual Mini Instruct v286.2

Strong at

B
Embeddings & Retrieval#73 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 · English52.3#73
BEIR · Mean over task types · English52.3#73
BEIR · Retrieval · English52.3#73
MTEB Persian v2 · Reranking · Persian35.6#87
JMTEB v2 · Clustering · Japanese19#97
JMTEB v2 · STS · Japanese61.6#103
LongEmbed · Mean over tasks · English35.2#100
LongEmbed · Mean over task types · English35.2#100
LongEmbed · Retrieval · English35.2#100
MTEB German v1 · Mean over tasks · German40.4#55
MTEB German v1 · Mean over task types · German39.1#56
MTEB German v1 · Clustering · German26.4#68
MTEB German v1 · Retrieval · German37.6#55
MTEB German v1 · Classification · German48#116
MTEB German v1 · STS · German51.3#76
MTEB German v1 · Pair Classification · German49.5#100
MTEB German v1 · Reranking · German22.1#97
MTEB Europe v1 · Retrieval · multilingual (25 languages)41.3#71
MTEB Europe v1 · Bitext Mining · multilingual (28 languages)35.5#127
MTEB Europe v1 · Classification · multilingual (23 languages)50.8#77
MTEB Europe v1 · Clustering · multilingual (29 languages)38.1#76
MTEB Europe v1 · Instruction Reranking · English-3.3#177
MTEB Europe v1 · Pair Classification · multilingual (11 languages)83.3#81
MTEB Europe v1 · Reranking · multilingual (12 languages)50.1#110
MTEB Europe v1 · Multilabel Classification · multilingual (23 languages)13.3#88
MTEB French v1 · Mean over tasks · multilingual (2 languages)49.1#54
MTEB French v1 · Mean over task types · multilingual (2 languages)51#48
MTEB French v1 · STS · French72.1#48
MTEB French v1 · Retrieval · multilingual (2 languages)34#84
MTEB French v1 · Reranking · French68.5#69
MTEB French v1 · Clustering · French42.5#43
MTEB French v1 · Classification · French53#84
MTEB French v1 · Summarization · French30.1#81
MTEB French v1 · Pair Classification · French56.9#112
MTEB Indic v1 · Mean over tasks · multilingual (25 languages)33.3#81
MTEB Indic v1 · Mean over task types · multilingual (25 languages)25#73
MTEB Indic v1 · Classification · multilingual (8 languages)43#96
MTEB Indic v1 · Retrieval · multilingual (14 languages)15.7#91
MTEB Indic v1 · Bitext Mining · multilingual (20 languages)3.5#110
MTEB Indic v1 · Reranking · multilingual (2 languages)52#122
MTEB Indic v1 · Pair Classification · Hindi53.6#134
MTEB Indic v1 · STS · multilingual (13 languages)4.2#131
MTEB Indic v1 · Clustering · multilingual (21 languages)3#162
MTEB Korean v2 · Reranking · Korean13.3#90
MTEB Korean v2 · Classification · Korean21.1#113
MTEB Dutch v1 · Mean over tasks · Dutch40#82
MTEB Dutch v1 · Mean over task types · Dutch47.7#83
MTEB Dutch v1 · Classification · Dutch46.6#92
MTEB Dutch v1 · Clustering · Dutch25.4#73
MTEB Dutch v1 · Retrieval · Dutch36.1#87
MTEB Dutch v1 · STS · Dutch59.4#87
MTEB Dutch v1 · Multilabel Classification · Dutch31.7#69
MTEB Dutch v1 · Pair Classification · Dutch57.6#128
MTEB Dutch v1 · Reranking · Dutch77.2#143
MTEB Polish v1 · Pair Classification · Polish62.8#110
MTEB Polish v1 · Classification · Polish41.5#90
MTEB Polish v1 · STS · Polish56.1#77
MTEB Portuguese v1 · Multilabel Classification · Portuguese19.8#91
MTEB Law v1 · Mean over tasks · multilingual (3 languages)40.7#79
MTEB Law v1 · Mean over task types · multilingual (3 languages)40.7#79
MTEB Law v1 · Retrieval · multilingual (3 languages)40.7#79
MTEB Medical v1 · Mean over tasks · multilingual (10 languages)40#65
MTEB Medical v1 · Mean over task types · multilingual (10 languages)33.8#66
MTEB Medical v1 · Retrieval · multilingual (10 languages)42.7#69
MTEB Medical v1 · Clustering · English36.8#78
MTEB Medical v1 · Reranking · Mandarin Chinese22#127
FollowIR · Mean over tasks · English-3.3#177
FollowIR · Mean over task types · English-3.3#177
FollowIR · Instruction Reranking · English-3.3#177
MTEB Spanish v1 · Pair Classification · Spanish58.8#122
MTEB Spanish v1 · Clustering · Spanish41.3#72
MTEB Spanish v1 · Reranking · Spanish33.6#89
MTEB Thai v1 · Clustering · Thai3.6#149
MTEB Thai v1 · Pair Classification · Thai51.3#156
MTEB Scandinavian v1 · Clustering · multilingual (2 languages)34.6#81
MTEB Scandinavian v1 · Classification · multilingual (6 languages)47.8#116
MTEB Scandinavian v1 · Bitext Mining · multilingual (3 languages)59#144
MTEB Russian v1.1 · Mean over tasks · Russian28.7#68
MTEB Russian v1.1 · Mean over task types · Russian29.4#67
MTEB Russian v1.1 · Classification · Russian31.8#106
MTEB Russian v1.1 · STS · Russian44.1#93
MTEB Russian v1.1 · Reranking · Russian26.5#100
MTEB Russian v1.1 · Clustering · Russian18.7#107
MTEB Russian v1.1 · Pair Classification · Russian48.3#146
MTEB Russian v1.1 · Retrieval · Russian11.2#63
MTEB Russian v1.1 · Multilabel Classification · Russian25.5#137
RTEB French beta · Mean over tasks · multilingual (2 languages)20.7#126
RTEB German beta · Mean over tasks · German16.1#140
RTEB Law beta · Mean over tasks · multilingual (4 languages)32.5#124
MTEB multilingual v2 · Classification · multilingual (119 languages)47.9#106
MTEB multilingual v2 · Clustering · multilingual (208 languages)42.3#66
MTEB multilingual v2 · Pair Classification · multilingual (24 languages)71.7#124
MTEB multilingual v2 · Retrieval · multilingual (120 languages)38.5#107
MTEB multilingual v2 · Bitext Mining · multilingual (1026 languages)24.4#124
MTEB multilingual v2 · Instruction Reranking · English-3.3#177
MTEB multilingual v2 · Multilabel Classification · multilingual (25 languages)16.7#102
MTEB multilingual v2 · Reranking · multilingual (22 languages)45.6#111

FAQ

How much does GIST Embedding v0 cost?›

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

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

#73 of 200 in Embeddings.

Is GIST Embedding v0 better than EmbeddingGemma 2?›

On MTEB English v2 · Pair Classification · English, GIST Embedding v0 scores 86.3 vs 86.4 — about the same.

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

Released 2024-01-31. It is the current version in its line.

Is GIST Embedding v0 open source?›

Yes, the weights are open (MIT licence).

Can I run GIST Embedding v0 locally?›

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

What is GIST Embedding v0?›

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

What are the best alternatives to GIST Embedding v0?›

E5 Mistral 7B Instruct (better), QZhou Embedding (open weights).