m

Mxbai Embed Large v1

Mar 2024
mMxbai Embed Large v1
Compare in
on
API price not publicprice
55.4MTEB English v2
Mar 2024released
1,024Dimensions
1K tokensMax input
enLanguages

Rankingconfiguration unstated?

Full ranking →
1Gemini Embedding 00177.22F2LLM v2 14B75.23Voyage Finance 274.94Voyage Multilingual 274.65Voyage 3.574.1
···
44Paraphrase Multilingual MiniLM L12 v243.545Mxbai Embed Large v142.546LaBSE42.2

Strong at

B
Embeddings & Retrieval#58 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
LicenceApache-2.0free for commercial use

Benchmarks

in Embeddings & Retrieval
BEIR · Mean over tasks · English54.3#55
BEIR · Mean over task types · English54.3#55
BEIR · Retrieval · English54.3#55
MTEB Persian v2 · Reranking · Persian43#72
JMTEB v2 · Clustering · Japanese18.7#99
JMTEB v2 · STS · Japanese61.2#106
LongEmbed · Mean over tasks · English38.9#82
LongEmbed · Mean over task types · English38.9#82
LongEmbed · Retrieval · English38.9#82
MTEB German v1 · Mean over tasks · German43.7#38
MTEB German v1 · Mean over task types · German42.7#39
MTEB German v1 · Clustering · German28.1#58
MTEB German v1 · Retrieval · German40.4#44
MTEB German v1 · Classification · German53.1#75
MTEB German v1 · STS · German52.6#68
MTEB German v1 · Pair Classification · German50.1#81
MTEB German v1 · Reranking · German31.7#65
MTEB Europe v1 · Mean over tasks · multilingual (29 languages)49.3#37
MTEB Europe v1 · Mean over task types · multilingual (29 languages)43.5#37
MTEB Europe v1 · Retrieval · multilingual (25 languages)43.4#59
MTEB Europe v1 · STS · multilingual (8 languages)68.4#42
MTEB Europe v1 · Bitext Mining · multilingual (28 languages)40.9#110
MTEB Europe v1 · Classification · multilingual (23 languages)52.6#57
MTEB Europe v1 · Clustering · multilingual (29 languages)39.1#67
MTEB Europe v1 · Instruction Reranking · English-2#125
MTEB Europe v1 · Pair Classification · multilingual (11 languages)84.2#69
MTEB Europe v1 · Reranking · multilingual (12 languages)51.2#97
MTEB Europe v1 · Multilabel Classification · multilingual (23 languages)14#72
MTEB French v1 · Mean over tasks · multilingual (2 languages)53.1#30
MTEB French v1 · Mean over task types · multilingual (2 languages)53.7#32
MTEB French v1 · STS · French73.7#42
MTEB French v1 · Retrieval · multilingual (2 languages)40.1#58
MTEB French v1 · Reranking · French69.6#63
MTEB French v1 · Clustering · French46.5#22
MTEB French v1 · Classification · French59#58
MTEB French v1 · Summarization · French29.6#98
MTEB French v1 · Pair Classification · French57.2#106
MTEB Indic v1 · Mean over tasks · multilingual (25 languages)33.3#82
MTEB Indic v1 · Mean over task types · multilingual (25 languages)22.9#93
MTEB Indic v1 · Classification · multilingual (8 languages)44.5#78
MTEB Indic v1 · Retrieval · multilingual (14 languages)12.2#111
MTEB Indic v1 · Bitext Mining · multilingual (20 languages)3.8#107
MTEB Indic v1 · Reranking · multilingual (2 languages)40.3#155
MTEB Indic v1 · Pair Classification · Hindi53.6#131
MTEB Indic v1 · STS · multilingual (13 languages)2.8#145
MTEB Indic v1 · Clustering · multilingual (21 languages)3.2#148
MTEB Korean v2 · STS · Korean39.6#61
MTEB Korean v2 · Reranking · Korean20.1#71
MTEB Korean v2 · Classification · Korean23.6#73
MTEB Dutch v1 · Mean over tasks · Dutch42.6#71
MTEB Dutch v1 · Mean over task types · Dutch49.6#75
MTEB Dutch v1 · Classification · Dutch51#72
MTEB Dutch v1 · Clustering · Dutch26.5#66
MTEB Dutch v1 · Retrieval · Dutch38.7#75
MTEB Dutch v1 · STS · Dutch61.6#84
MTEB Dutch v1 · Multilabel Classification · Dutch31.9#66
MTEB Dutch v1 · Pair Classification · Dutch59.7#102
MTEB Dutch v1 · Reranking · Dutch77.8#138
MTEB Polish v1 · Pair Classification · Polish65.2#91
MTEB Polish v1 · Classification · Polish43.9#70
MTEB Polish v1 · STS · Polish55.4#79
MTEB Portuguese v1 · Multilabel Classification · Portuguese20.3#71
MTEB Law v1 · Mean over tasks · multilingual (3 languages)39.9#86
MTEB Law v1 · Mean over task types · multilingual (3 languages)39.9#86
MTEB Law v1 · Retrieval · multilingual (3 languages)39.9#86
MTEB Medical v1 · Clustering · English36.1#95
MTEB Medical v1 · Reranking · Mandarin Chinese19.7#142
FollowIR · Mean over tasks · English-2#125
FollowIR · Mean over task types · English-2#125
FollowIR · Instruction Reranking · English-2#125
MTEB Spanish v1 · Pair Classification · Spanish61.3#94
MTEB Spanish v1 · STS · multilingual (2 languages)66.9#47
MTEB Spanish v1 · Clustering · Spanish43.5#52
MTEB Spanish v1 · Reranking · Spanish43.1#66
MTEB Thai v1 · Clustering · Thai3#182
MTEB Thai v1 · Pair Classification · Thai51.4#146
MTEB Scandinavian v1 · Mean over tasks · multilingual (6 languages)45.3#39
MTEB Scandinavian v1 · Mean over task types · multilingual (6 languages)46.9#38
MTEB Scandinavian v1 · Clustering · multilingual (2 languages)36.4#63
MTEB Scandinavian v1 · Classification · multilingual (6 languages)48.5#100
MTEB Scandinavian v1 · Retrieval · multilingual (3 languages)42.5#45
MTEB Scandinavian v1 · Bitext Mining · multilingual (3 languages)60.4#137
MTEB Russian v1.1 · Mean over tasks · Russian32#62
MTEB Russian v1.1 · Mean over task types · Russian32.7#62
MTEB Russian v1.1 · Classification · Russian34.7#95
MTEB Russian v1.1 · STS · Russian44.7#92
MTEB Russian v1.1 · Reranking · Russian33.8#83
MTEB Russian v1.1 · Clustering · Russian19.2#104
MTEB Russian v1.1 · Pair Classification · Russian48.1#149
MTEB Russian v1.1 · Retrieval · Russian20.2#55
MTEB Russian v1.1 · Multilabel Classification · Russian28.2#85
RTEB Finnish beta · Mean over tasks · English57.4#48
RTEB French beta · Mean over tasks · multilingual (2 languages)27.2#104
RTEB German beta · Mean over tasks · German16.4#137
RTEB Health beta · Mean over tasks · multilingual (4 languages)46.9#52
RTEB Law beta · Mean over tasks · multilingual (4 languages)31.6#134
MTEB multilingual v2 · Mean over tasks · multilingual (1037 languages)45.9#65
MTEB multilingual v2 · Mean over task types · multilingual (1037 languages)39.4#64
MTEB multilingual v2 · Classification · multilingual (119 languages)49.7#85
MTEB multilingual v2 · Clustering · multilingual (208 languages)42.5#62
MTEB multilingual v2 · STS · multilingual (35 languages)60.5#75
MTEB multilingual v2 · Pair Classification · multilingual (24 languages)72.6#105
MTEB multilingual v2 · Retrieval · multilingual (120 languages)40.3#92
MTEB multilingual v2 · Bitext Mining · multilingual (1026 languages)25.7#117
MTEB multilingual v2 · Instruction Reranking · English-2#125
MTEB multilingual v2 · Multilabel Classification · multilingual (25 languages)18.1#79
MTEB multilingual v2 · Reranking · multilingual (22 languages)47.6#98

FAQ

How much does Mxbai Embed Large v1 cost?›

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

Is Mxbai Embed Large v1 free to use?›

There is no free API. The weights are open, so you can run it yourself.

How good is Mxbai Embed Large v1, and what is it best at?›

#58 of 200 in Embeddings.

Is Mxbai Embed Large v1 better than Paraphrase Multilingual MiniLM L12 v2?›

On MTEB Scandinavian v1 · Retrieval · multilingual (3 languages), Mxbai Embed Large v1 scores 42.5 vs 43.5 — lower.

When was Mxbai Embed Large v1 released? Is there a newer version?›

Released 2024-03-07. It is the current version in its line.

Is Mxbai Embed Large v1 open source?›

Yes, the weights are open (Apache-2.0 licence).

Can I run Mxbai Embed Large v1 locally?›

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

What is Mxbai Embed Large v1?›

Mxbai Embed Large v1 is an open-weights embeddings & retrieval model from mixedbread-ai, released Mar 2024.

What are the best alternatives to Mxbai Embed Large v1?›

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