SkMTEB: 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 score (%) across the 31 Slovak MTEB datasets over seven task types; higher is better.
Metric: Mean score (%) across the 31 Slovak MTEB datasets over seven task types; 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 | 77.49 | |
| 2 | gemini-embedding-001 | 77.23 | |
| 3 | jina-embeddings-v3 | 75.1 | |
| 4 | text-embedding-3-large | 75.07 | |
| 5 | Qwen3-Embedding-8B | 74.53 | |
| 6 | bge-m3 | 74.43 | |
| 7 | multilingual-e5-large | 74.25 | |
| 8 | Qwen3-Embedding-4B | 73.7 | |
| 9 | nomic-embed-text-v2-moe | 72.58 | |
| 10 | snowflake-arctic-embed-l-v2.0 | 72.54 |
Interactive version: theaggregate.ai/benchmark?slug=skmteb · How It Works · Data refreshed daily, snapshot 2026-11-13.