mongodb
VoyageAI by MongoDB: rerank-2.5
mongodb/rerank-2.5
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
mongodb/rerank-2.5 is a text reranker from VoyageAI by MongoDB, listed on OpenRouter under the canonical ID voyageai/rerank-2.5-20260727. According to the catalog, it accepts text input, produces reranked output, and supports a context length of 32,000 tokens. The vendor description positions it as a quality-focused reranker and reports retrieval-accuracy gains over Cohere Rerank v3.5 across many datasets, but those figures are vendor-reported rather than independently measured. Only OpenRouter catalog evidence was provided; no independent model card was available in this source pack.[1]
Strengths
- Purpose-built reranker: the catalog describes a dedicated text-to-rerank modality for ordering retrieved passages by relevance rather than generating new text.[1]
- The catalog lists a 32,000-token context length, which may help when scoring longer documents or larger result sets.[1]
- The vendor description reports retrieval-accuracy gains over Cohere Rerank v3.5 across many datasets; this is a source-reported claim, not an independent measurement.[1]
Limitations
- Evidence is limited to the OpenRouter catalog; no independent model card was available in this source pack, so vendor claims remain unverified.[1]
- The reported accuracy improvements are vendor-published figures, not measured results on your data; validate ranking quality on your own workload before relying on them.[1]
- The source does not document supported languages, latency, licensing terms, or deployment requirements, so those characteristics are unknown.[1]
Where to use it
- Suggested for reranking candidates in RAG or search pipelines where better ordering of retrieved passages matters; test on your own retrieval data.[1]
- Potentially suited to document retrieval over longer texts, given the catalog-listed 32,000-token context; treat as an editorial suggestion pending validation.[1]
- May suit teams already using MongoDB or VoyageAI services who want a reranker from the same provider.[1]
Sources
- [1] OpenRouter catalog · VoyageAI by MongoDB: rerank-2.5Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
rerank-2.5 is a cutting-edge reranker optimized for quality, delivering a 7.94% improvement in retrieval accuracy over Cohere Rerank v3.5 across 93 datasets. It also outperformed Cohere Rerank v3.5 by 12.70%...
Specifications
- Model ID
- mongodb/rerank-2.5
- Canonical ID
- voyageai/rerank-2.5-20260727
- Creator
- mongodb
- Added to OpenRouter
- 27.07.2026
- Context length
- 32,000
- Modality
- text->rerank
- Input modalities
- text
- Output modalities
- rerank
- Token pricing
- No per-token price in the source snapshot — see OpenRouter for the billing unit
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | — |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| VoyageAI by MongoDB | 32,000 | — | — | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.