Skip to content

Benchmark

MTEB(Europe, v1) - Clustering

Embedding benchmarks measure how well models find related items, for example when matching a search to relevant results. Scores are percentages.

Models measured
33
Scores recorded
33
Sources
1
IQ weight
0.93

Score distribution

40.4%
Mean
38.9%
Median
7.3%
Std dev
35.2%
10th percentile
48.2%
90th percentile
12%
Min
12%50.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.93 for embedding models, measured over 33 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Qwen3 Embedding 4BClustering· MTEB Leaderboard data50.4%
2Qwen3 Embedding 8BClustering· MTEB Leaderboard data50.4%
3Gemini Embedding 001Clustering· MTEB Leaderboard data48.5%
4Jina Embeddings v5 Omni SmallClustering· MTEB Leaderboard data48.2%
5Jina Embeddings v5 Text SmallClustering· MTEB Leaderboard data48.2%
6Jina Embeddings v5 Omni NanoClustering· MTEB Leaderboard data48%
7Jina Embeddings v5 Text NanoClustering· MTEB Leaderboard data48%
8Multilingual E5 Large InstructClustering· MTEB Leaderboard data46.9%
9E5 Mistral 7B InstructClustering· MTEB Leaderboard data46.5%
10Qwen3 Embedding 0.6BClustering· MTEB Leaderboard data45.3%
11Text Embedding 3 LargeClustering· MTEB Leaderboard data44.2%
12Text Embedding 3 SmallClustering· MTEB Leaderboard data44.2%
13Jina Embeddings v3Clustering· MTEB Leaderboard data43.4%
14embeddinggemma-2Clustering· MTEB Leaderboard data43%
15Text Multilingual Embedding 002Clustering· MTEB Leaderboard data42.4%
16snowflake-arctic-embed-l-v2.0Clustering· MTEB Leaderboard data39.6%
17snowflake-arctic-embed-m-v2.0Clustering· MTEB Leaderboard data38.9%
18UAE-Large-V1Clustering· MTEB Leaderboard data37.9%
19Gte BaseClustering· MTEB Leaderboard data37.4%
20Gte LargeClustering· MTEB Leaderboard data37.2%
21BGE Base En V1.5Clustering· MTEB Leaderboard data37.1%
22BGE Large En V1.5Clustering· MTEB Leaderboard data37.1%
23BGE M3Clustering· MTEB Leaderboard data36.9%
24nomic-embed-text-v1Clustering· MTEB Leaderboard data36.7%
25E5 Base V2Clustering· MTEB Leaderboard data36.5%
26Granite Embedding 278m MultilingualClustering· MTEB Leaderboard data36.3%
27E5 Large V2Clustering· MTEB Leaderboard data36.2%
28Paraphrase Multilingual MPNet v2Clustering· MTEB Leaderboard data35.8%
29NV-Embed-v2Clustering· MTEB Leaderboard data35.5%
30nomic-embed-text-v1.5Clustering· MTEB Leaderboard data35.2%
31bge-small-en-v1.5Clustering· MTEB Leaderboard data35%
32All MiniLM L6 V2Clustering· MTEB Leaderboard data33.6%
33Jina Embeddings v2 Base ENClustering· MTEB Leaderboard data12%