The verdict
Voyage Rerank appears in 1 AI-ranked category — best position #2 for reranking model api.
Positioning brief — for the Voyage Rerank team
Why the models put Voyage Rerank at #2 for reranking model api
- instruction-following reranking GPT · Claude · Gemini“instruction-following reranking”
- longer context GPT · Claude · Grok“much longer context per document”
- complex/domain-heavy retrieval GPT · Gemini · Grok“excels on complex/domain-heavy retrieval (finance, legal)”
- near-tie on quality GPT · Claude · Gemini“Near-tie with Cohere on quality”
What the models credit Cohere Rerank (#1) with — and don’t credit Voyage Rerank
- widest enterprise availability GPT · Claude · Gemini“the widest enterprise availability”
- automatic long-document chunking GPT“automatic long-document chunking”
- dedicated low-latency fast tier GPT · Gemini“has a dedicated low-latency fast tier”
What would move the rank — the models’ fix lines, unified
- fewer integrations GPT · Claude · Gemini“fewer native vector database integrations”
- robust multilingual support Gemini“Lacks robust multilingual support”
- cut latency and per-query costs Grok“Cut p99 latency and per-query costs”
Restructured from verbatim model output · nothing invented · every quote machine-verified
Near-tied with Cohere on general quality, with instruction-following, multilingual retrieval, 32K context, and especially strong value for sophisticated RAG queries where ranking criteria need to be expressed in the query
Claude Near-tie with Cohere on quality and often beats it on retrieval benchmarks, with much longer context per document, instruction-following reranking, and lower per-token pricing; MongoDB acquisition removed the startup-longevity risk
Gemini Offers class-leading instruction-following that lets developers dynamically steer relevance scoring (e.g., focusing on specific metadata). It is in a near-tie with Jina AI for the second spot, earning it due to superior instruction-adherence precision for agentic RAG, assuming an English-centric pipeline.
Grok Highest relevance lift in many independent RAG tests; longest context (16k tokens); excels on complex/domain-heavy retrieval (finance, legal).
Where Voyage Rerank falls short, per the models
- GPT Smaller deployment and integration ecosystem than Cohere, making it less convenient for enterprises standardizing through multiple clouds and established search platforms
- Claude Thinner ecosystem — fewer cloud-marketplace and framework integrations than Cohere, and tighter rate limits on new accounts make it less turnkey for enterprise procurement
- Gemini Lacks robust multilingual support and has fewer native vector database integrations.
- Grok Cut p99 latency and per-query costs to win high-volume real-time workloads.
Poll history — On this board 7 of 7 polls since Jun 29 · now #2
#2 → #2 → #2 → #2 → #3 → #3 → #2
Top alternatives per the models: Cohere Rerank · Jina Reranker · Mixedbread Rerank · Qwen3 Reranker
Head-to-head — how the models call it
Watch Voyage Rerank
Boards re-poll weekly and the models change their minds. One short email only when Voyage Rerank's standing moves — a rank change, a rival overtaking, or new reasoning from the models. Nothing otherwise.
Embed your ranking badge
Voyage Rerank ranks #2 for best reranking model api by AI-model consensus. Put the badge in your README, docs or site — it updates automatically as the models re-rank.
[](https://modelsagree.com/best/best-reranking-model-api?utm_source=badge&utm_medium=embed&utm_campaign=badge-voyage-rerank)<a href="https://modelsagree.com/best/best-reranking-model-api?utm_source=badge&utm_medium=embed&utm_campaign=badge-voyage-rerank"><img src="https://modelsagree.com/badge/voyage-rerank.svg" alt="Voyage Rerank — ranked #2 for Best reranking model API by AI models on ModelsAgree" height="28"></a>Rankings are computed from what the models answer, re-polled on demand · raw reasoning shown verbatim · methodology