Qwen3-Reranker-8B
Qwen/Qwen3-Reranker-8B
A popular open reranker model, with 1M downloads a month. gigarouter benchmarks and hosts it as an OpenAI-compatible API.
about this model
The Qwen3-Reranker-8B is a text reranking model available through gigarouter's hosted API. It is part of the Qwen3 Embedding series, built on the Qwen3 dense foundation model. It supports over 100 languages and a context length of 32K tokens. The model is instruction-aware, allowing custom prompts to improve task-specific performance.
Key strengths
- Multilingual capability: Supports 100+ natural and programming languages, with strong cross-lingual retrieval.
- Instruction-aware: Custom instructions can be supplied per query; using instructions typically yields 1%–5% improvement.
- Long context: Handles up to 32K tokens.
- Benchmark performance: The 8B reranker achieves state-of-the-art results on multiple reranking benchmarks, as shown below.
Benchmark results (reranking)
| Model | Param | MTEB-R | CMTEB-R | MMTEB-R | MLDR | MTEB-Code | FollowIR |
|---|---|---|---|---|---|---|---|
| Qwen3-Embedding-0.6B | 0.6B | 61.82 | 71.02 | 64.64 | 50.26 | 75.41 | 5.09 |
| Jina-multilingual-reranker-v2-base | 0.3B | 58.22 | 63.37 | 63.73 | 39.66 | 58.98 | -0.68 |
| gte-multilingual-reranker-base | 0.3B | 59.51 | 74.08 | 59.44 | 66.33 | 54.18 | -1.64 |
| BGE-reranker-v2-m3 | 0.6B | 57.03 | 72.16 | 58.36 | 59.51 | 41.38 | -0.01 |
| Qwen3-Reranker-0.6B | 0.6B | 65.80 | 71.31 | 66.36 | 67.28 | 73.42 | 5.41 |
| Qwen3-Reranker-4B | 4B | 69.76 | 75.94 | 72.74 | 69.97 | 81.20 | 14.84 |
| Qwen3-Reranker-8B | 8B | 69.02 | 77.45 | 72.94 | 70.19 | 81.22 | 8.05 |
Scores are based on top-100 candidates retrieved by Qwen3-Embedding-0.6B. MTEB-R, CMTEB-R, MMTEB-R, and MTEB-Code denote the retrieval subsets of MTEB (English v2, Chinese v1, multilingual, and code).
Best use cases
- Re-ranking retrieved candidate documents in search and RAG pipelines.
- Multilingual and cross-lingual retrieval scenarios.
- Code retrieval tasks (e.g., matching queries to code snippets).
- Applications requiring instruction-guided relevance scoring.
For further details, see the blog and GitHub repository.
We're benchmarking and onboarding Qwen3-Reranker-8B as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.