Bge Large En v1.5

Sep 2023
Bge Large En v1.5
Compare in
on
$0.01per 1M tokens
55.4MTEB English v2
Sep 2023released
1,024Dimensions
1K tokensMax input
enLanguages

Rankingconfiguration unstated?

Full ranking →
1Octen Law 8B v176.82Litil Embed 0.6B73.33Dinghy Law 8B v172.64Dinghy Law 4B v171.25Euler Legal Embedding v170.4
···
88Snowflake Arctic Embed M39.889Bge Large En v1.539.690E5 Base v239.5

Strong at

B
Embeddings & Retrieval#57 of 200

Alternatives?

ModelScoreCostPriceWhat changes
CheaperBge Base En v1.5unstatedOpensame-50%$0.005iBetterMultilingual E5 Large InstructunstatedOpen+39%same$0.01Memory (4-bit): 0.2 GB → 0.3 GBlOpenOcten Law 8B v1+94%——Memory (4-bit): 0.2 GB → 4.5 GBtCheaperGte BaseunstatedOpensame-50%$0.005iCheaperE5 Base v2unstatedOpensame-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 · English54.3#53
BEIR · Mean over task types · English54.3#53
BEIR · Retrieval · English54.3#53
BRIGHT · Mean over tasks · English13.6#18
BRIGHT · Mean over task types · English13.6#18
BRIGHT · Retrieval · English13.6#18
ChemTEB · Mean over tasks · multilingual (13 languages)70.9#18
ChemTEB · Mean over task types · multilingual (13 languages)50.7#21
ChemTEB · Classification · English82.2#17
ChemTEB · Retrieval · English73.9#13
ChemTEB · Pair Classification · multilingual (13 languages)58#21
ChemTEB · Clustering · English39.2#28
ChemTEB · Bitext Mining · English0.2#29
MTEB Persian v2 · Reranking · Persian43.3#71
JMTEB v2 · Clustering · Japanese18.5#102
JMTEB v2 · STS · Japanese62.2#100
LongEmbed · Mean over tasks · English40.1#76
LongEmbed · Mean over task types · English40.1#76
LongEmbed · Retrieval · English40.1#76
MTEB German v1 · Mean over tasks · German43#42
MTEB German v1 · Mean over task types · German42.2#43
MTEB German v1 · Clustering · German27.6#60
MTEB German v1 · Retrieval · German41.1#42
MTEB German v1 · Classification · German50.8#87
MTEB German v1 · STS · German53.7#63
MTEB German v1 · Pair Classification · German49.1#121
MTEB German v1 · Reranking · German30.9#68
MTEB Europe v1 · Mean over tasks · multilingual (29 languages)48.5#40
MTEB Europe v1 · Mean over task types · multilingual (29 languages)43.1#39
MTEB Europe v1 · Retrieval · multilingual (25 languages)42.3#66
MTEB Europe v1 · STS · multilingual (8 languages)68.2#43
MTEB Europe v1 · Bitext Mining · multilingual (28 languages)41.8#107
MTEB Europe v1 · Classification · multilingual (23 languages)51.1#70
MTEB Europe v1 · Clustering · multilingual (29 languages)37.1#85
MTEB Europe v1 · Instruction Reranking · English-2.3#135
MTEB Europe v1 · Pair Classification · multilingual (11 languages)84.1#71
MTEB Europe v1 · Reranking · multilingual (12 languages)51.9#88
MTEB Europe v1 · Multilabel Classification · multilingual (23 languages)13.6#79
MTEB French v1 · Mean over tasks · multilingual (2 languages)51.5#37
MTEB French v1 · Mean over task types · multilingual (2 languages)52.6#39
MTEB French v1 · STS · French73.8#40
MTEB French v1 · Retrieval · multilingual (2 languages)39.9#60
MTEB French v1 · Reranking · French70#60
MTEB French v1 · Clustering · French43.7#35
MTEB French v1 · Classification · French56#65
MTEB French v1 · Summarization · French29.5#107
MTEB French v1 · Pair Classification · French55#145
MTEB Indic v1 · Mean over tasks · multilingual (25 languages)31.8#103
MTEB Indic v1 · Mean over task types · multilingual (25 languages)22.9#94
MTEB Indic v1 · Classification · multilingual (8 languages)41.6#119
MTEB Indic v1 · Retrieval · multilingual (14 languages)14#99
MTEB Indic v1 · Bitext Mining · multilingual (20 languages)3.4#114
MTEB Indic v1 · Reranking · multilingual (2 languages)41.7#151
MTEB Indic v1 · Pair Classification · Hindi52.8#144
MTEB Indic v1 · STS · multilingual (13 languages)3.9#135
MTEB Indic v1 · Clustering · multilingual (21 languages)2.9#165
MTEB Korean v2 · STS · Korean34.7#69
MTEB Korean v2 · Reranking · Korean23.8#66
MTEB Korean v2 · Classification · Korean20.6#122
MTEB Dutch v1 · Mean over tasks · Dutch42.8#70
MTEB Dutch v1 · Mean over task types · Dutch50.1#71
MTEB Dutch v1 · Classification · Dutch48.3#83
MTEB Dutch v1 · Clustering · Dutch25#74
MTEB Dutch v1 · Retrieval · Dutch42.5#64
MTEB Dutch v1 · STS · Dutch63#81
MTEB Dutch v1 · Multilabel Classification · Dutch31.9#67
MTEB Dutch v1 · Pair Classification · Dutch60.4#97
MTEB Dutch v1 · Reranking · Dutch79.6#120
MTEB Polish v1 · Pair Classification · Polish64#101
MTEB Polish v1 · Classification · Polish41.3#93
MTEB Polish v1 · STS · Polish56.2#73
MTEB Portuguese v1 · Multilabel Classification · Portuguese20.5#67
MTEB Law v1 · Mean over tasks · multilingual (3 languages)39.6#89
MTEB Law v1 · Mean over task types · multilingual (3 languages)39.6#89
MTEB Law v1 · Retrieval · multilingual (3 languages)39.6#89
MTEB Medical v1 · Clustering · English35.4#121
MTEB Medical v1 · Reranking · Mandarin Chinese19.3#144
FollowIR · Mean over tasks · English-2.3#135
FollowIR · Mean over task types · English-2.3#135
FollowIR · Instruction Reranking · English-2.3#135
MTEB Spanish v1 · Pair Classification · Spanish60.3#101
MTEB Spanish v1 · STS · multilingual (2 languages)67.7#44
MTEB Spanish v1 · Clustering · Spanish42.2#63
MTEB Spanish v1 · Reranking · Spanish42.5#69
MTEB Thai v1 · Clustering · Thai3.3#170
MTEB Thai v1 · Pair Classification · Thai51.4#152
MTEB Scandinavian v1 · Clustering · multilingual (2 languages)34.8#79
MTEB Scandinavian v1 · Classification · multilingual (6 languages)48.7#96
MTEB Scandinavian v1 · Bitext Mining · multilingual (3 languages)62.3#118
MTEB Russian v1.1 · Mean over tasks · Russian32.3#60
MTEB Russian v1.1 · Mean over task types · Russian33.3#59
MTEB Russian v1.1 · Classification · Russian33.7#101
MTEB Russian v1.1 · STS · Russian44.9#89
MTEB Russian v1.1 · Reranking · Russian36.8#78
MTEB Russian v1.1 · Clustering · Russian19#106
MTEB Russian v1.1 · Pair Classification · Russian47.6#161
MTEB Russian v1.1 · Retrieval · Russian24#52
MTEB Russian v1.1 · Multilabel Classification · Russian27.1#96
RTEB Finnish beta · Mean over tasks · English58.2#44
RTEB French beta · Mean over tasks · multilingual (2 languages)26.4#108
RTEB German beta · Mean over tasks · German16.6#135
RTEB Health beta · Mean over tasks · multilingual (4 languages)46.1#56
RTEB Law beta · Mean over tasks · multilingual (4 languages)31.7#131
MTEB multilingual v2 · Mean over tasks · multilingual (1037 languages)45.1#68
MTEB multilingual v2 · Mean over task types · multilingual (1037 languages)39.1#66
MTEB multilingual v2 · Classification · multilingual (119 languages)48#103
MTEB multilingual v2 · Clustering · multilingual (208 languages)41.4#76
MTEB multilingual v2 · STS · multilingual (35 languages)60.1#76
MTEB multilingual v2 · Pair Classification · multilingual (24 languages)72#114
MTEB multilingual v2 · Retrieval · multilingual (120 languages)39#101
MTEB multilingual v2 · Bitext Mining · multilingual (1026 languages)26.7#112
MTEB multilingual v2 · Instruction Reranking · English-2.3#135
MTEB multilingual v2 · Multilabel Classification · multilingual (25 languages)17.7#84
MTEB multilingual v2 · Reranking · multilingual (22 languages)48.8#92

FAQ

How much does Bge Large En v1.5 cost?›

$0.01 per 1M tokens.

Is Bge Large En v1.5 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 Bge Large En v1.5, and what is it best at?›

#57 of 200 in Embeddings.

Is Bge Large En v1.5 better than Snowflake Arctic Embed M?›

On MTEB Law v1 · Retrieval · multilingual (3 languages), Bge Large En v1.5 scores 39.6 vs 39.8 — about the same.

How can I use Bge Large En v1.5?›

Through the BAAI API.

When was Bge Large En v1.5 released? Is there a newer version?›

Released 2023-09-12. It is the current version in its line.

Is Bge Large En v1.5 open source?›

Yes, the weights are open (MIT licence).

Can I run Bge Large En v1.5 locally?›

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

What is Bge Large En v1.5?›

Bge Large En v1.5 is an open-weights embeddings & retrieval model from BAAI, released Sep 2023.

What are the best alternatives to Bge Large En v1.5?›

Bge Base En v1.5 (cheaper), Multilingual E5 Large Instruct (better), Octen Law 8B v1 (open weights).