Cohere Embed 5 launch: Shared-space corpus/query pairings
We show this table for reference; we do not rank on it.
Cohere launch retrieval report.
Evaluation results published by Cohere.
Normalized mean nDCG@10 on Cohere Embed 5 launch: Shared-space corpus/query pairings — September 30, 2026 launch; October 1 capture
We mirror the published normalized mean ndcg@10 view for Cohere Embed 5 launch: Shared-space corpus/query pairings. Query Pro / Corpus Pro leads the public snapshot at 100.0, followed by Query Fast / Corpus Pro (98.4) and Query Pro / Corpus Fast (97.3). We do not use these results to rank models overall.
Query Pro / Corpus Pro
Cohere
Cohere provider report; evaluated snapshot and hardware undisclosed
Query Fast / Corpus Pro
Cohere
Cohere provider report; evaluated snapshot and hardware undisclosed
Query Pro / Corpus Fast
Cohere
Cohere provider report; evaluated snapshot and hardware undisclosed
4 configurationsCross-domainDated provider configurationsDisplay onlyUpdated September 30, 2026 launch; October 1 capture
Normalized mean nDCG@10 table (4 configurations)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | Query Pro / Corpus ProCohereCohere provider report; evaluated snapshot and hardware undisclosed | 100.0 | Not reported | Unknown |
| 2 | Query Fast / Corpus ProCohereCohere provider report; evaluated snapshot and hardware undisclosed | 98.4 | Not reported | Unknown |
| 3 | Query Pro / Corpus FastCohereCohere provider report; evaluated snapshot and hardware undisclosed | 97.3 | Not reported | Unknown |
| 4 | Query Fast / Corpus FastCohereCohere provider report; evaluated snapshot and hardware undisclosed | 96.6 | Not reported | Unknown |
How to read this provider report
Forty development datasets covering text, image, fused, and parsed-document retrieval. Values are normalized to the Pro corpus plus Pro query pairing at 100. Both sides require the same output dimension; this is not raw percent accuracy.
Cohere reports these results in its Embed 5 launch. The linked full spreadsheet requires sign-in at capture, so this view includes only exact figures available in the public post. Model snapshots, evaluation dates, and uncertainty intervals are undisclosed.
Each input representation and metric retains its own cohort. RCP-nDCG@10 evaluates reordering a fixed candidate set; it does not measure first-stage retrieval. These provider comparisons do not enter weighted model rankings.
The published Cohere Embed 5 launch: Shared-space corpus/query pairings snapshot places Query Pro / Corpus Pro first at 100.0. The third row is 2.7 score units behind. The broader top-10 range is 3.4 score units, so many of the published results sit in a relatively narrow band.
4 configurations are shown for Cohere Embed 5 launch: Shared-space corpus/query pairings. The benchmark falls in the Cross-domain category. We keep external benchmark mirrors separate from the weighted global scoring system, so these results remain source-specific evidence. Cohere Embed 5 launch: Shared-space corpus/query pairings is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
Freshness and provenance
Version
Cohere Embed 5 launch provider report
Refresh cadence
Reviewed dated source capture
Staleness state
Dated provider configurations
Question availability
Upstream datasets and terms; aggregate results only
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does Cohere Embed 5 launch: Shared-space corpus/query pairings measure?
Cohere launch retrieval report.
Which model leads the published Cohere Embed 5 launch: Shared-space corpus/query pairings snapshot?
Query Pro / Corpus Pro currently leads the published Cohere Embed 5 launch: Shared-space corpus/query pairings snapshot with 100.0 normalized mean ndcg@10. BenchLM shows this benchmark for display only and does not use it in overall rankings.
How many models are evaluated on Cohere Embed 5 launch: Shared-space corpus/query pairings?
The September 30, 2026 launch; October 1 capture snapshot contains 4 AI models.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 5,600+ readers.
One email each week. Unsubscribe anytime.