SkMTEB - Classification: 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 accuracy (%) over the seven classification datasets; higher is better.
Metric: Mean accuracy (%) over the seven classification datasets; higher is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 28 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | gemini-embedding-001 | 71.01 | |
| 2 | multilingual-e5-large-instruct | 70.28 | |
| 3 | text-embedding-3-large | 66.91 | |
| 4 | jina-embeddings-v3 | 66.89 | |
| 5 | bge-m3 | 66.81 | |
| 6 | Qwen3-Embedding-8B | 65.94 | |
| 7 | multilingual-e5-large | 65.34 | |
| 8 | Qwen3-Embedding-4B | 64.26 | |
| 9 | paraphrase-multilingual-mpnet-base-v2 | 64.05 | |
| 10 | nomic-embed-text-v2-moe | 63.98 |
Interactive version: theaggregate.ai/benchmark?slug=skmteb-classification · How It Works · Data refreshed daily, snapshot 2026-11-13.