SkMTEB - Pair 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 score (%) over the three pair-classification datasets; higher is better.
Metric: Mean score (%) over the three pair-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 | multilingual-e5-large-instruct | 70.55 | |
| 2 | slovakbert-sts-stsb | 68.9 | |
| 3 | paraphrase-multilingual-mpnet-base-v2 | 68.21 | |
| 4 | paraphrase-multilingual-MiniLM-L12-v2 | 67.82 | |
| 5 | gte-multilingual-base | 67.24 | |
| 6 | gemini-embedding-001 | 67.08 | |
| 7 | bge-m3 | 67.03 | |
| 8 | multilingual-e5-large | 66.78 | |
| 9 | Qwen3-Embedding-8B | 66.65 | |
| 10 | text-embedding-3-large | 66.58 |
Interactive version: theaggregate.ai/benchmark?slug=skmteb-pair-classification · How It Works · Data refreshed daily, snapshot 2026-11-13.