---
title: "text-multilingual-embedding-002 — text embeddings score and price · Undominated.ai"
canonical: https://undominated.ai/embeddings/google__text-multilingual-embedding-002/
description: "text-multilingual-embedding-002 by Google: MTEB(eng, v2) 67.67; no traceable price; no sellers on record; as of 2026-09-19. Every figure traces to its source."
---

# text-multilingual-embedding-002 — text embeddings score and price · Undominated.ai

> text-multilingual-embedding-002 by Google: MTEB(eng, v2) 67.67; no traceable price; no sellers on record; as of 2026-09-19. Every figure traces to its source.

[Text embeddings](/embeddings/)

# text-multilingual-embedding-002

Google

Vertex AI prices this model per 1,000 characters, not per token; no per-token price can be stated.

— no traceable price

Verdict: unpriced. As of 2026-09-19 .

## What was measured

| Board | Mean (Task) | Mean (TaskType) | Tasks | Revision |
| --- | --- | --- | --- | --- |
| MTEB(eng, v2) | 67.67 | 63.52 | 41 of 41 | 1 |

By task type: Classification 84.65 · Clustering 50.41 · PairClassification 86.6 · Reranking 47.48 · Retrieval 54.7 · STS 83.94 · Summarization 36.84

## What sellers charge

No price for this model traces to a page we have read. That is not a price of zero.

## Provenance

 - Quality: https://github.com/embeddings-benchmark/results, licensed cc0-1.0.
 - Prices: none on record. No figure on this page claims a price for this model.
 - Built 2026-09-19 from the catalogue snapshot in this repository.

MTEB results, https://github.com/embeddings-benchmark/results, released under CC0-1.0; MTEB(eng, v2) means computed from the per-task files as described in data/modalities/embeddings/benchmark.json.