Text Embedding 005

Nov 2024
Text Embedding 005
Compare in
on
$0.025per 1M tokens
58.8MTEB English v2
Nov 2024released
2K tokensMax input

Rankingconfiguration unstated?

Full ranking →
1F2LLM v2 14B80.82C2LLM 7B80.73Seed1.6 Embedding 121580.74Qwen 3 Embedding 8B80.75F2LLM v2 8B80.2
···
36LateOn Code Pretrain63.837Text Embedding 00561.538Granite Embedding 97M Multilingual R260.4

Strong at

A
Embeddings & Retrieval#33 of 200

Benchmarks

in Embeddings & Retrieval
BEIR · Mean over tasks · English55.8#35
BEIR · Mean over task types · English55.8#35
BEIR · Retrieval · English55.8#35
MTEB Medical v1 · Clustering · English36.1#94
CoIR · Mean over tasks · multilingual (9 languages)59.7#42
CoIR · Mean over task types · multilingual (9 languages)59.7#42
CoIR · Retrieval · multilingual (9 languages)59.7#42
MTEB Code v1 · Mean over tasks · multilingual (15 languages)61.5#37
MTEB Code v1 · Mean over task types · multilingual (15 languages)61.5#37
MTEB Code v1 · Retrieval · multilingual (15 languages)61.5#37
RTEB Finnish beta · Mean over tasks · English71.9#25
RTEB French beta · Mean over tasks · multilingual (2 languages)42.3#61
RTEB German beta · Mean over tasks · German45.2#73
RTEB Health beta · Mean over tasks · multilingual (4 languages)60.6#32
RTEB Law beta · Mean over tasks · multilingual (4 languages)44.8#66

FAQ

How much does Text Embedding 005 cost?›

$0.025 per 1M tokens.

Is Text Embedding 005 free to use?›

There is no free API; it costs $0.025 per 1M tokens.

How good is Text Embedding 005, and what is it best at?›

#33 of 200 in Embeddings. Strongest at: Embeddings & Retrieval.

Is Text Embedding 005 better than LateOn Code Pretrain?›

On MTEB Code v1 · Mean over tasks · multilingual (15 languages), Text Embedding 005 scores 61.5 vs 63.8 — lower.

When was Text Embedding 005 released? Is there a newer version?›

Released 2024-11-18. It is the current version in its line.

Is Text Embedding 005 open source?›

No, Text Embedding 005 is a closed model available through an API. The closest open-weights option here is F2LLM v2 14B.

What is Text Embedding 005?›

Text Embedding 005 is a closed embeddings & retrieval model from Google, released Nov 2024.

What are the best alternatives to Text Embedding 005?›

Qwen 3 Embedding 8B (cheaper), EmbeddingGemma 300M (better), F2LLM v2 14B (open weights).