skip to content
gigarouter gigarouter
models / reranker · coming soon

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.

est. price
~$0.008
/ 1k docs · estimated, set at launch
API providers
0
downloads / mo
1M
license
apache-2.0

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.

Qwen3 Reranker 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)

ModelParamMTEB-RCMTEB-RMMTEB-RMLDRMTEB-CodeFollowIR
Qwen3-Embedding-0.6B0.6B61.8271.0264.6450.2675.415.09
Jina-multilingual-reranker-v2-base0.3B58.2263.3763.7339.6658.98-0.68
gte-multilingual-reranker-base0.3B59.5174.0859.4466.3354.18-1.64
BGE-reranker-v2-m30.6B57.0372.1658.3659.5141.38-0.01
Qwen3-Reranker-0.6B0.6B65.8071.3166.3667.2873.425.41
Qwen3-Reranker-4B4B69.7675.9472.7469.9781.2014.84
Qwen3-Reranker-8B8B69.0277.4572.9470.1981.228.05

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.

not yet live

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.