Skip to content

Benchmark

MTEB(Medical, 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
40
Scores recorded
40
Sources
1
IQ weight
0.99

Score distribution

36.7%
Mean
36.1%
Median
4.8%
Std dev
33.5%
10th percentile
42.5%
90th percentile
16%
Min
16%46.1%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.99 for embedding models, measured over 40 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Gemini Embedding 001Clustering· MTEB Leaderboard data46.1%
2Qwen3 Embedding 8BClustering· MTEB Leaderboard data45.1%
3Qwen3 Embedding 4BClustering· MTEB Leaderboard data44.6%
4Jina Embeddings v5 Omni SmallClustering· MTEB Leaderboard data42.5%
5Jina Embeddings v5 Text SmallClustering· MTEB Leaderboard data42.5%
6Jina Embeddings v5 Omni NanoClustering· MTEB Leaderboard data41.4%
7Jina Embeddings v5 Text NanoClustering· MTEB Leaderboard data41.4%
8Qwen3 Embedding 0.6BClustering· MTEB Leaderboard data41.3%
9embeddinggemma-2Clustering· MTEB Leaderboard data41.1%
10All Mpnet Base V2Clustering· MTEB Leaderboard data38.4%
11E5 Mistral 7B InstructClustering· MTEB Leaderboard data38.4%
12Multilingual E5 Large InstructClustering· MTEB Leaderboard data37.9%
13Jina Embeddings v3Clustering· MTEB Leaderboard data37.7%
14nomic-embed-text-v1.5Clustering· MTEB Leaderboard data36.9%
15All MiniLM L12 V2Clustering· MTEB Leaderboard data36.6%
16All MiniLM L6 V2Clustering· MTEB Leaderboard data36.5%
17NV-Embed-v2Clustering· MTEB Leaderboard data36.5%
18Granite Embedding Small English R2Clustering· MTEB Leaderboard data36.2%
19Text Embedding 005Clustering· MTEB Leaderboard data36.1%
20Gte LargeClustering· MTEB Leaderboard data36.1%
21Paraphrase Multilingual MPNet v2Clustering· MTEB Leaderboard data36%
22Text Embedding 004Clustering· MTEB Leaderboard data36%
23BGE Base En V1.5Clustering· MTEB Leaderboard data35.9%
24UAE-Large-V1Clustering· MTEB Leaderboard data35.9%
25Gte BaseClustering· MTEB Leaderboard data35.7%
26nomic-embed-text-v1Clustering· MTEB Leaderboard data35.7%
27Text Embedding 3 SmallClustering· MTEB Leaderboard data35.6%
28bge-small-en-v1.5Clustering· MTEB Leaderboard data35.6%
29Text Multilingual Embedding 002Clustering· MTEB Leaderboard data35.4%
30BGE Large En V1.5Clustering· MTEB Leaderboard data35.4%
31Text Embedding 3 LargeClustering· MTEB Leaderboard data35.2%
32E5 Large V2Clustering· MTEB Leaderboard data34.5%
33E5 Base V2Clustering· MTEB Leaderboard data34.4%
34Granite Embedding 278m MultilingualClustering· MTEB Leaderboard data34.2%
35snowflake-arctic-embed-l-v2.0Clustering· MTEB Leaderboard data33.8%
36snowflake-arctic-embed-m-v2.0Clustering· MTEB Leaderboard data33.5%
37Multilingual E5 LargeClustering· MTEB Leaderboard data32.9%
38BGE M3Clustering· MTEB Leaderboard data32.2%
39Jina Embedding B EN v1Clustering· MTEB Leaderboard data31.2%
40Jina Embeddings v2 Base ENClustering· MTEB Leaderboard data16%