Back to all embeddings

Cohere Embed Multilingual v3

Supports 100+ languages with 512 token context length enabling within-language and cross-language retrieval. Requires input_type specification for search documents and queries to optimize multilingual search performance. If you want to compare the best embedding models for your data, try Agentset.

Leaderboard Rank
#7
of 18
ELO Rating
1512
#7
Win Rate
48.4%
#8
Accuracy (nDCG@10)
0.701
#6
Latency
7ms
#2

Model Information

Provider
Cohere
License
Proprietary
Price per 1M tokens
$0.100
Dimensions
512
Release Date
2024-02-07
Model Name
cohere-embed-multilingual-v3
Total Evaluations
830

Performance Record

Wins402 (48.4%)
Losses368 (44.3%)
Ties60 (7.2%)
Wins
Losses
Ties

Embedding Models Are Just One Piece of RAG

Agentset gives you a managed RAG pipeline with the top-ranked models and best practices baked in. No infrastructure to maintain, no embeddings to manage.

Trusted by teams building production RAG applications

5M+
Documents
1,500+
Teams
99.9%
Uptime

Performance Overview

ELO ratings by dataset

Cohere Embed Multilingual v3's ELO performance varies across different benchmark datasets, showing its strengths in specific domains.

Cohere Embed Multilingual v3 - ELO by Dataset

Detailed Metrics

Dataset breakdown

Performance metrics across different benchmark datasets, including accuracy and latency percentiles.

business reports

ELO 150045.6% WR73W-85L-2T

Accuracy Metrics

nDCG@5
0.000
nDCG@10
0.000
Recall@5
0.000
Recall@10
0.000

Latency Distribution

Mean
8ms
P50 (Median)
8ms
P90
8ms

DBPedia

ELO 150046.9% WR75W-68L-17T

Accuracy Metrics

nDCG@5
0.786
nDCG@10
0.783
Recall@5
0.061
Recall@10
0.122

Latency Distribution

Mean
7ms
P50 (Median)
7ms
P90
7ms

FiQa

ELO 150044.7% WR67W-79L-4T

Accuracy Metrics

nDCG@5
0.804
nDCG@10
0.812
Recall@5
0.624
Recall@10
0.696

Latency Distribution

Mean
7ms
P50 (Median)
7ms
P90
7ms

SciFact

ELO 150057.5% WR92W-63L-5T

Accuracy Metrics

nDCG@5
0.696
nDCG@10
0.702
Recall@5
0.804
Recall@10
0.830

Latency Distribution

Mean
7ms
P50 (Median)
7ms
P90
7ms

MSMARCO

ELO 150045.6% WR73W-59L-28T

Accuracy Metrics

nDCG@5
0.952
nDCG@10
0.941
Recall@5
0.121
Recall@10
0.218

Latency Distribution

Mean
8ms
P50 (Median)
8ms
P90
8ms

ARCD

ELO 150055.0% WR22W-14L-4T

Accuracy Metrics

nDCG@5
0.868
nDCG@10
0.875
Recall@5
0.940
Recall@10
0.960

Latency Distribution

Mean
7ms
P50 (Median)
7ms
P90
7ms

Build RAG in Minutes, Not Months

Agentset gives you a complete RAG API with top-ranked embedding models and smart retrieval built in. Upload your data, call the API, and get accurate results from day one.

import { Agentset } from "agentset";

const agentset = new Agentset();
const ns = agentset.namespace("ns_1234");

const results = await ns.search(
  "What is multi-head attention?"
);

for (const result of results) {
  console.log(result.text);
}

Compare Models

See how it stacks up

Compare Cohere Embed Multilingual v3 with other top embeddings to understand the differences in performance, accuracy, and latency.