pragma.vision Technology observatory & strategic foresight

Verification register Agentic Commerce & Payments

Readiness verdict

Voyage rerank-2.5

A dated reading of what is claimed, reported, and independently verified in the current evidence.

As of
2026-08-20
Revision
1
Method
v1.3.0

Current reading

Readiness band and full integer triple

AI-assisted assembly · derived results

Readiness band

Ready

Primary summary from verified readiness

Confidence
74% · stale
Computed at
2026-08-20T10:52:42.138376+00:00
Claimed
88

Public ambition and stated capability

Reported
82

Observed practitioner reporting

Verified
73

Independently supported evidence

Gap
+15

Claimed leads verified

Evidence strength Strong

Decision

What the current evidence supports

Human editorial judgment · 2026-08-20

Low-friction candidate

Why
A drop-in API reranker with consistently measured accuracy gains over v3.5, 32K context, instruction-following, and pricing identical to rerank-2 — low integration cost; tradeoffs are latency-vs-accuracy (solved by variant choice) and a now-contested top-of-leaderboard position.
Next
A/B rerank-2.5 vs rerank-2.5-lite (and benchmark against the newer Cohere Rerank 4 Pro) on production query mix; measure NDCG uplift and p95 latency, pick Lite where the <600ms budget binds.

Constraints

Blockers

No named blocker is present in the current public projection.

Evidence summary

Derived counts

AI-assisted assembly

Total
11
Tier 1
0
Tier 2
7
Tier 3
4
Supports
6
Contradicts
3
Context
2
Latest observed
2026-02-15

Counts and dates only. Raw signals, private excerpts, trust records, and internal corpus material are not published here.

Publication record

Revisions

Initial public reading

  1. 2026-07-19 Reading moved from ready to ready.

Your opinion

Tell us anything.

What works, what doesn't, what's missing — especially about our watches, lenses, and the register itself. Anonymous is fine; leave an email if you'd like a reply.