Use cases › Capability
Rerank search results
Cross-encoder or listwise rerankers that re-score a query against candidate passages after first-stage retrieval.
Benchmarks that represent this job 4
A model's row on one of these third-party boards is what earns the measured label; the same benchmark name in the model's own card earns author-reported.
Models 7
Narrow by what you can run and pay for. Rows are ordered measured → author-reported → structural, then by watch-list score; click a column to re-sort. Every chip links to its source.
| Model | Evidence | Params | Context | Price from | Runs on | License | Providers |
|---|---|---|---|---|---|---|---|
| Qwen3-Reranker-8B Qwen | author-reported Author reports CMTEB-R 77.45decision-model estimate p=1.00 +1 | 8.19B | 40K | $0.05 | Single GPU | Apache 2.0 | 1 |
| Qwen3-Reranker-0.6B Qwen | structural decision-model estimate p=1.00name: Rerank +1 | 596M | 40K | $0.01 | Laptop / edge | Apache 2.0 | 2 |
| bge-reranker-large BAAI | structural decision-model estimate p=0.99name: rerank | 560M | 514 | — | Laptop / edge | MIT | 1 |
| Qwen3-Reranker-4B Qwen | structural decision-model estimate p=0.99name: Rerank +1 | 4.02B | 40K | $0.03 | Single GPU | Apache 2.0 | 1 |
| gte-reranker-modernbert-base Alibaba-NLP | structural decision-model estimate p=0.99name: rerank +1 | 150M | — | — | Laptop / edge | Apache 2.0 | 1 |
| jina-reranker-v2-base-multilingual jinaai | structural decision-model estimate p=1.00name: rerank +1 | 278M | 1K | — | Laptop / edge | CC BY-NC 4.0 non-commercial | 0 |
| CLM-v0.1-8B Contrastive-LM | structural decision-model estimate p=0.81tag: text-ranking +1 | — | — | — | — | Apache 2.0 | 0 |
No model matches every constraint. Loosen one, or switch the evidence filter back to any.
How to read this
- measured a third-party leaderboard row for this model. Settings (agent harness, edit format, prompt) differ between boards; compare within a benchmark, not across.
- author-reported a number the model author published in the card or eval files. Not reproduced by us.
- structural a deterministic signal from the name, config or chat template, or a decision-model estimate. A weak signal: it says the model was built or tagged for the job, not how well it does it. "decision-model estimate" chips are a probability from the Jev decision model, not a measurement.
- Runs on is the memory class of the BF16 weights (method); choosing a class shows that class and smaller. Quantized builds may fit a class lower.
- Price from is the cheapest observed hosted input price, USD per million tokens; models with no observed price are hidden when a ceiling is set. License friction: permissive = none or attribution-only; high = non-commercial.
- Ordering within a tier is the watch-list score (Hub likes, downloads, recency), not a quality verdict.
Subscribe
Follow "Rerank search results"
- /feeds/for/reranking.xml(RSS 2.0) · one item per model with measured or author-reported evidence for this job
- /feeds/for/reranking.json(JSON Feed 1.1) · same items, JSON Feed
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.