Project AURIONAI Use-Cases Research & Innovation

MTEB English

embeddings.

v2embeddings
2scores
2models
0independent
0maintainer-run
2vendor-reported

Definition

Version
v2
Category
embeddings
Maintainer
not in the notes
Status
not in the notes
Home page
not in the notes

Sources

  1. google/embeddinggemma-2 , Hugging Face huggingface.co https://huggingface.co/google/embeddinggemma-2
  2. jinaai/jina-embeddings-v5-text-small , Hugging Face huggingface.co https://huggingface.co/jinaai/jina-embeddings-v5-text-small

Scores at a Glance

Score

Higher is better for this unit.

1Jina AIjina-embeddings-v5-text-smallJina AI
71.7 score
vendor-reported2GoogleEmbeddingGemma 2Google
68.46 score
vendor-reported
020406080
Where this comes from
Each bar is one model, with its most independent recorded score. Hatched bars are vendor-reported; the word beside each bar says who ran it. Settings and dates differ between rows; the Scores table below has every result.

Scores

2 of 2 scores shown mteb-english-v2-scores.csv
ModelScoreWho ran itSettingView or populationDateSource
Jina AIjina-embeddings-v5-text-small71.7 scorevendor-reported–––huggingface.co
GoogleEmbeddingGemma 268.46 scorevendor-reported–––huggingface.co
Where this comes from
Scores from different settings, harnesses or dates are not directly comparable; the row says which. Sorted by score, highest first, as a reading aid, not a ranking.

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "MTEB English", https://aurion.semai.id/benchmarks/mteb-english-v2/, records of October 2026.