a

GIST Large Embedding v0

Feb 2024
aGIST Large Embedding v0
Compare in
on
price not verifiedprice
54.5MTEB English v2
Feb 2024released
1,024Dimensions
1K tokensMax input
enLanguages

Rankingconfiguration unstated?

Full ranking →
1F2LLM v2 14B63.42F2LLM v2 8B63.23F2LLM v2 4B62.54Jina Embeddings v5 Text Nano62.25F2LLM v2 1.7B61.8
···
43Bge Large En v1.542.244GIST Large Embedding v04245Nomic Embed Text v1 Unsupervised41.6

Strong at

B
Embeddings & Retrieval#65 of 200

Alternatives?

ModelScoreCostPriceWhat changes
iBetterMultilingual E5 Large InstructunstatedOpen+33%—$0.01Memory (4-bit): 0.2 GB → 0.3 GBcOpenF2LLM v2 8Bunstated+51%——Memory (4-bit): 0.2 GB → 4.5 GBiBetterMultilingual E5 LargeunstatedOpen+31%—$0.01Memory (4-bit): 0.2 GB → 0.3 GBiBetterE5 Large v2unstatedOpen+6%—$0.01BetterJina Embeddings v5 Text NanounstatedOpen+48%—$0.02Languages: not verified

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 · English53.4#61
BEIR · Mean over task types · English53.4#61
BEIR · Retrieval · English53.4#61
MTEB Persian v2 · Reranking · Persian39.6#79
JMTEB v2 · Clustering · Japanese18.9#98
JMTEB v2 · STS · Japanese62.3#98
LongEmbed · Mean over tasks · English39#81
LongEmbed · Mean over task types · English39#81
LongEmbed · Retrieval · English39#81
MTEB German v1 · Mean over tasks · German42.6#46
MTEB German v1 · Mean over task types · German42#44
MTEB German v1 · Clustering · German28.1#57
MTEB German v1 · Retrieval · German40.2#46
MTEB German v1 · Classification · German49.5#95
MTEB German v1 · STS · German55#61
MTEB German v1 · Pair Classification · German50.4#77
MTEB German v1 · Reranking · German28.7#70
MTEB Europe v1 · Retrieval · multilingual (25 languages)43.7#58
MTEB Europe v1 · Bitext Mining · multilingual (28 languages)40#118
MTEB Europe v1 · Classification · multilingual (23 languages)51.2#68
MTEB Europe v1 · Clustering · multilingual (29 languages)38.5#73
MTEB Europe v1 · Instruction Reranking · English-1.8#119
MTEB Europe v1 · Pair Classification · multilingual (11 languages)83.6#77
MTEB Europe v1 · Reranking · multilingual (12 languages)51.6#90
MTEB Europe v1 · Multilabel Classification · multilingual (23 languages)13.7#77
MTEB French v1 · Mean over tasks · multilingual (2 languages)52.4#33
MTEB French v1 · Mean over task types · multilingual (2 languages)53.7#31
MTEB French v1 · STS · French74.3#38
MTEB French v1 · Retrieval · multilingual (2 languages)40.3#57
MTEB French v1 · Reranking · French72.4#52
MTEB French v1 · Clustering · French46.2#24
MTEB French v1 · Classification · French55.2#73
MTEB French v1 · Summarization · French28.9#124
MTEB French v1 · Pair Classification · French58.3#89
MTEB Indic v1 · Mean over tasks · multilingual (25 languages)34#75
MTEB Indic v1 · Mean over task types · multilingual (25 languages)25.2#72
MTEB Indic v1 · Classification · multilingual (8 languages)43.8#87
MTEB Indic v1 · Retrieval · multilingual (14 languages)15.9#89
MTEB Indic v1 · Bitext Mining · multilingual (20 languages)4.6#99
MTEB Indic v1 · Reranking · multilingual (2 languages)54.8#114
MTEB Indic v1 · Pair Classification · Hindi53.7#127
MTEB Indic v1 · STS · multilingual (13 languages)-0.1#168
MTEB Indic v1 · Clustering · multilingual (21 languages)3.7#131
MTEB Korean v2 · Reranking · Korean11.2#98
MTEB Korean v2 · Classification · Korean23#82
MTEB Dutch v1 · Mean over tasks · Dutch41.5#74
MTEB Dutch v1 · Mean over task types · Dutch49#78
MTEB Dutch v1 · Classification · Dutch48.1#84
MTEB Dutch v1 · Clustering · Dutch27.3#63
MTEB Dutch v1 · Retrieval · Dutch37.2#84
MTEB Dutch v1 · STS · Dutch61.4#85
MTEB Dutch v1 · Multilabel Classification · Dutch32.6#63
MTEB Dutch v1 · Pair Classification · Dutch59.2#110
MTEB Dutch v1 · Reranking · Dutch77.5#141
MTEB Polish v1 · Pair Classification · Polish63.2#106
MTEB Polish v1 · Classification · Polish39.9#113
MTEB Polish v1 · STS · Polish55.3#81
MTEB Portuguese v1 · Multilabel Classification · Portuguese21.3#50
MTEB Law v1 · Mean over tasks · multilingual (3 languages)41.5#75
MTEB Law v1 · Mean over task types · multilingual (3 languages)41.5#75
MTEB Law v1 · Retrieval · multilingual (3 languages)41.5#75
MTEB Medical v1 · Mean over tasks · multilingual (10 languages)40.2#63
MTEB Medical v1 · Mean over task types · multilingual (10 languages)33.9#65
MTEB Medical v1 · Retrieval · multilingual (10 languages)42.9#68
MTEB Medical v1 · Clustering · English37#71
MTEB Medical v1 · Reranking · Mandarin Chinese21.7#129
FollowIR · Mean over tasks · English-1.8#119
FollowIR · Mean over task types · English-1.8#119
FollowIR · Instruction Reranking · English-1.8#119
MTEB Spanish v1 · Pair Classification · Spanish60.3#100
MTEB Spanish v1 · Clustering · Spanish42.7#57
MTEB Spanish v1 · Reranking · Spanish39.6#73
MTEB Thai v1 · Clustering · Thai3.2#177
MTEB Thai v1 · Pair Classification · Thai52.2#119
MTEB Scandinavian v1 · Clustering · multilingual (2 languages)36.6#62
MTEB Scandinavian v1 · Classification · multilingual (6 languages)47.2#129
MTEB Scandinavian v1 · Bitext Mining · multilingual (3 languages)58.6#148
MTEB Russian v1.1 · Mean over tasks · Russian31.1#64
MTEB Russian v1.1 · Mean over task types · Russian31.6#64
MTEB Russian v1.1 · Classification · Russian33.9#99
MTEB Russian v1.1 · STS · Russian45.3#87
MTEB Russian v1.1 · Reranking · Russian29.8#91
MTEB Russian v1.1 · Clustering · Russian22.4#98
MTEB Russian v1.1 · Pair Classification · Russian48#152
MTEB Russian v1.1 · Retrieval · Russian15.9#58
MTEB Russian v1.1 · Multilabel Classification · Russian26.1#117
RTEB French beta · Mean over tasks · multilingual (2 languages)24.6#112
RTEB German beta · Mean over tasks · German15.9#145
RTEB Law beta · Mean over tasks · multilingual (4 languages)34.4#105
MTEB multilingual v2 · Classification · multilingual (119 languages)48.2#100
MTEB multilingual v2 · Clustering · multilingual (208 languages)42.4#64
MTEB multilingual v2 · Pair Classification · multilingual (24 languages)72.3#110
MTEB multilingual v2 · Retrieval · multilingual (120 languages)40.4#91
MTEB multilingual v2 · Bitext Mining · multilingual (1026 languages)25.6#118
MTEB multilingual v2 · Instruction Reranking · English-1.8#119
MTEB multilingual v2 · Multilabel Classification · multilingual (25 languages)17.5#87
MTEB multilingual v2 · Reranking · multilingual (22 languages)47.1#102

FAQ

How much does GIST Large Embedding v0 cost?›

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

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

#65 of 200 in Embeddings.

Is GIST Large Embedding v0 better than Bge Large En v1.5?›

On MTEB German v1 · Mean over task types · German, GIST Large Embedding v0 scores 42 vs 42.2 — about the same.

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

Released 2024-02-14. It is the current version in its line.

Is GIST Large Embedding v0 open source?›

Yes, the weights are open (MIT licence).

Can I run GIST Large Embedding v0 locally?›

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

What is GIST Large Embedding v0?›

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

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

Multilingual E5 Large Instruct (better), F2LLM v2 8B (open weights).