SkMTEB - Reranking: 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 reranking datasets; higher is better.
Metric: Mean score (%) over the three reranking 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 | 88.27 | |
| 2 | multilingual-e5-large | 87.96 | |
| 3 | embed-v4.0 | 87.45 | |
| 4 | snowflake-arctic-embed-l-v2.0 | 87.11 | |
| 5 | Qwen3-Embedding-8B | 87.04 | |
| 6 | text-embedding-3-large | 86.96 | |
| 7 | bge-m3 | 86.72 | |
| 8 | multilingual-e5-large-instruct | 86.49 | |
| 9 | Qwen3-Embedding-4B | 86.29 | |
| 10 | multilingual-e5-base | 85.71 |
Interactive version: theaggregate.ai/benchmark?slug=skmteb-reranking · How It Works · Data refreshed daily, snapshot 2026-11-13.