SkMTEB - Clustering: leaderboard
SkMTEB is the Slovak Massive Text Embedding Benchmark: 31 datasets across seven task types (bitext mining, classification, clustering, pair classification, reranking, retrieval, semantic textual similarity). This board reports Mean V-measure (%) over the five clustering datasets; higher is better.
Metric: Mean V-measure (%) over the five clustering datasets; higher is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 28 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | multilingual-e5-large-instruct | 49.69 | |
| 2 | gemini-embedding-001 | 46.26 | |
| 3 | jina-embeddings-v4 | 44.65 | |
| 4 | jina-embeddings-v3 | 44.63 | |
| 5 | Qwen3-Embedding-0.6B | 44.28 | |
| 6 | Qwen3-Embedding-4B | 44.22 | |
| 7 | text-embedding-3-large | 44.22 | |
| 8 | embeddinggemma-300m | 43.76 | |
| 9 | text-embedding-3-small | 43.64 | |
| 10 | nomic-embed-text-v2-moe | 43.53 |
Interactive version: theaggregate.ai/benchmark?slug=skmteb-clustering · How It Works · Data refreshed daily, snapshot 2026-11-13.