Benchmark
MTEB(cmn, 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
- 14
- Scores recorded
- 14
- Sources
- 1
- IQ weight
- 1.31
Score distribution
- 57%
- Mean
- 57%
- Median
- 11.6%
- Std dev
- 45.7%
- 10th percentile
- 77.9%
- 90th percentile
- 37.7%
- Min
This benchmark has a weight of 1.31 for embedding models, measured over 13 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Qwen3 Embedding 8BClustering· MTEB Leaderboard data | 80.1% |
| 2 | Qwen3 Embedding 4BClustering· MTEB Leaderboard data | 77.9% |
| 3 | Qwen3 Embedding 0.6BClustering· MTEB Leaderboard data | 68.7% |
| 4 | Jina Embeddings v5 Text SmallClustering· MTEB Leaderboard data | 60.2% |
| 5 | Jina Embeddings v5 Omni SmallClustering· MTEB Leaderboard data | 60.2% |
| 6 | BGE multilingual gemma2Clustering· MTEB Leaderboard data | 59.3% |
| 7 | Jina Embeddings v5 Omni NanoClustering· MTEB Leaderboard data | 57% |
| 8 | Multilingual E5 Large InstructClustering· MTEB Leaderboard data | 53.3% |
| 9 | E5 Mistral 7B InstructClustering· MTEB Leaderboard data | 52.3% |
| 10 | Jina Embeddings v3Clustering· MTEB Leaderboard data | 50.2% |
| 11 | bge-large-zhClustering· MTEB Leaderboard data | 48.4% |
| 12 | Multilingual E5 LargeClustering· MTEB Leaderboard data | 46.6% |
| 13 | Text Embedding Ada 002Clustering· MTEB Leaderboard data | 45.7% |
| 14 | Text2vec Base ChineseClustering· MTEB Leaderboard data | 37.7% |