Five rerankers, five distinguishing traits.
**Cohere Rerank 3.5** is the dominant hosted cross-encoder in 2026. It is closed source and called via a paid API, but it is fast, Cohere reranks a top-100 candidate set in single-digit milliseconds on their managed infrastructure. It is multilingual out of the box.
**Voyage Rerank-2** is also hosted, but its differentiator is domain-tuned variants. Voyage ships specialized rerankers for code, legal, and finance on top of a general reranker. If your corpus is one of those domains, the specialized variant typically outperforms the general one.
**BGE Reranker v2** from BAAI is open-source with a permissive license. You can self-host it. It comes in several sizes (base, large, m3) so you can pick a tradeoff between latency and quality. It is the default choice when you cannot or do not want to send your corpus to a hosted API.
**Jina Reranker v2** is another open-source self-hostable reranker. Its differentiator is long-context support up to 8K tokens and multilingual training. If your chunks are long or your corpus is multilingual, it is a strong fit.
**ColBERT v2 / PLAID** is architecturally different from the others. The others are sentence-level cross-encoders that produce one score per (query, chunk) pair. ColBERT is a late-interaction model, it scores at the token level, comparing each query token against each chunk token, then aggregates. The benefit is finer-grained matching; the cost is more memory and storage for token-level embeddings.
The four sentence-level cross-encoders (Cohere, Voyage, BGE, Jina) differ in hosting model and specialization. ColBERT is the architectural outlier.
The five rerankers split along two axes: **architecture** (sentence-level cross-encoder vs token-level late-interaction) and **hosting** (closed hosted API vs open self-hostable weights).
**Cohere Rerank 3.5**, closed, hosted, multilingual, low-latency. The dominant production default for teams willing to pay per call. Optimized batching means top-100 reranks in single-digit milliseconds. The closed nature is the limitation: vendor lock-in and per-call cost.
**Voyage Rerank-2**, closed, hosted, with **domain-specialized variants**. Voyage ships dedicated rerankers for code, legal, and finance corpora on top of a general reranker. The specialized variants beat the general reranker on their domains by meaningful margins. Pair naturally with Voyage embedding models.
**BGE Reranker v2**, open-source from BAAI, permissive license, self-hostable. Available in base, large, and m3 sizes for latency vs quality tuning. The 2026 default when you need to self-host (data residency, on-prem, cost control). Pairs naturally with BGE-M3 embeddings.
**Jina Reranker v2**, also open-source and self-hostable. Differentiator is **long-context support up to 8K tokens** and multilingual training. Best fit when chunks are long (e.g. legal sections, full pages) or the corpus spans many languages.
**ColBERT v2 / PLAID**, architecturally distinct. The other four are sentence-level cross-encoders: they take a (query, chunk) pair and produce one relevance score from a single forward pass. ColBERT is a **late-interaction** model: it stores token-level embeddings for chunks, and at query time it scores each query token against each chunk token (the maxsim operation) and aggregates. The benefit is more granular matching, especially on long chunks. The cost is storage (token embeddings, not sentence embeddings) and somewhat more complex serving infrastructure.
The practical default in 2026 is Cohere Rerank 3.5 for hosted production, BGE Reranker v2 for self-hosted, Voyage Rerank-2
Quick reference
TL;DR
Cohere Rerank 3.5 is the hosted multilingual default; Voyage Rerank-2 ships domain-tuned variants; BGE and Jina are open-source self-hostable; ColBERT is architecturally different with late-interaction token-level
Imagine five careful interviewers, each with a specialty. The first one is the fast-talking generalist you hire from an agency. The second works at a firm with specialist hires for legal, finance, or coding interviews. The third is freelance and you can hire them onto your own team. The fourth is also freelance and good with long resumes in any language. The fifth has a completely different style, they read the resume word by word instead of skimming the whole thing. All five interviewers re-rank a small shortlist, but each has a personality and a quirk worth knowing.
Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.
Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example.
Workloads with strict data-residency rules Closed hosted rerankers (Cohere, Voyage) send corpus chunks to vendor infrastructure; pick a self-hostable option.
Tiny corpora under a few thousand chunks A single cross-encoder pass over the whole set is feasible without a reranker stage; picking a specific reranker matters less.
Sub-100ms latency budgets All rerankers add tens of milliseconds; a tuned bi-encoder may be the only fit, regardless of which reranker you would have used.
Quick scan · 2–4 min
Everything important, quickly.
4 minutes: name each reranker's distinguishing trait, separate the architectural axis (cross-encoder vs late-interaction) from the hosting axis (closed API vs open weights), and give the 2026 default for each common scenario.
Side-by-side
Reranker
Hosting
Architecture
Distinguisher
Cohere Rerank 3.5
Closed hosted API
Sentence-level cross-encoder
Low-latency multilingual default
Voyage Rerank-2
Closed hosted API
Sentence-level cross-encoder
Domain-tuned variants (code, legal, finance)
BGE Reranker v2
Open / self-host
Sentence-level cross-encoder
Permissive license, multiple sizes
Jina Reranker v2
Open / self-host
Sentence-level cross-encoder
Long-context up to 8K, multilingual
ColBERT v2 / PLAID
Open / self-host
Late-interaction (token-level)
MaxSim token scoring, finer granularity at storage cost
Real-world examples
Real products, models, and research that use this idea.
1Cohere Rerank 3.5 is the dominant hosted reranker for production RAG stacks in 2026, integrated natively into Pinecone, Weaviate, Qdrant, and the major orchestration frameworks.
2Voyage AI's Rerank-2-code variant is widely used in coding-agent stacks (Cursor, Windsurf, Cline) where corpus is source code.
3BGE Reranker v2-m3 is the default self-hosted reranker for organizations with on-prem or data-residency requirements.
4Jina Reranker v2 is used in production for European multilingual support corpora because of its strong long-context multilingual training.
5ColBERT v2 with PLAID serving powers some of the larger academic-search and patent-search systems where token-level matching pays off.
Interviewer follow-ups
What an interviewer would ask next. Try answering before peeking at the approach.
QWhen is ColBERT's late-interaction architecture worth the storage cost?
Sign in or go Pro to see the approach for this follow-up.
QHow do you decide between hosted Cohere and self-hosted BGE?
Sign in or go Pro to see the approach for this follow-up.
QWhat is the right eval to compare two rerankers on your workload?
Sign in or go Pro to see the approach for this follow-up.
Don't say this
Red flags and common mistakes that signal junior thinking. Click to expand.
Most common mistake
Treating all five rerankers as interchangeable. Architectural differences (cross-encoder vs late-interaction) and hosting models (closed API vs open weights) and domain tuning each change which one is right for a given workload.